services/agents/src · flagon-io/g1t

abilities-prompt.tsEach agent has an Abilities tab: g1t's built-ins, always on within the asker's access; its computer, coming; each connected integration's actions one row each, read, import, comment or resolve, with a level for each, alone, alone when the person asked for it, ask first or never, and whose connection it runs on; and MCP servers an owner adds. Reading is alone, writing inside g1t follows today's choices, anything that leaves g1t asks first, and production deploys can't go above ask. The agents service enforces every level: ask first posts a card to allow or deny and parks a session until it's answered, a refusal names its rule in the transcript and the audit log, and a missing ability posts a request to owners. The agent abilities guide says how.5d ago

abilities.test.tsEach agent has an Abilities tab: g1t's built-ins, always on within the asker's access; its computer, coming; each connected integration's actions one row each, read, import, comment or resolve, with a level for each, alone, alone when the person asked for it, ask first or never, and whose connection it runs on; and MCP servers an owner adds. Reading is alone, writing inside g1t follows today's choices, anything that leaves g1t asks first, and production deploys can't go above ask. The agents service enforces every level: ask first posts a card to allow or deny and parks a session until it's answered, a refusal names its rule in the transcript and the audit log, and a missing ability posts a request to owners. The agent abilities guide says how.5d ago

abilities.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

access.test.tsAnyone makes an agent by describing it: one box drafts the whole agent (name, job, responsibilities, voice, skills to keep, integrations it needs, model limits and budget) as a card to change and try in a chat beside it before creating it, and an agent changes later by saying what to change, shown as a diff before it's saved. Members can make personal agents, which only they talk to and which spend from their own budget, unless owners turn that off; owners promote one to a workspace agent. The agents guide says how.5d ago

access.tsAnyone makes an agent by describing it: one box drafts the whole agent (name, job, responsibilities, voice, skills to keep, integrations it needs, model limits and budget) as a card to change and try in a chat beside it before creating it, and an agent changes later by saying what to change, shown as a diff before it's saved. Members can make personal agents, which only they talk to and which spend from their own budget, unless owners turn that off; owners promote one to a workspace agent. The agents guide says how.5d ago

archived.test.tsAn archived agent can be found, brought back, or deleted for good. The Agents page ends with Archived, folded, where owners see every archived agent and members their own personal ones, each with when and by whom it was archived and what deleting it would take; Restore brings it back, under a new handle when a live agent has taken its old one, and Delete permanently asks for the handle to be typed and then removes its sessions, replies, memories, routines, versions, drafts, skills and its computer's home, leaving its messages in chat under its saved name, the workspace's spend totals and the audit log. In Chat an archived agent is deactivated the way people expect: never offered as someone to message or mention, never woken, a conversation with it kept in the list, dimmed and marked Archived, open to read with a note in place of the composer and a way to restore it for owners; after deletion the conversation still reads, its messages marked as a deleted agent's. The agents, chat and agent budgets guides say so.4d ago

archived.tsAn archived agent can be found, brought back, or deleted for good. The Agents page ends with Archived, folded, where owners see every archived agent and members their own personal ones, each with when and by whom it was archived and what deleting it would take; Restore brings it back, under a new handle when a live agent has taken its old one, and Delete permanently asks for the handle to be typed and then removes its sessions, replies, memories, routines, versions, drafts, skills and its computer's home, leaving its messages in chat under its saved name, the workspace's spend totals and the audit log. In Chat an archived agent is deactivated the way people expect: never offered as someone to message or mention, never woken, a conversation with it kept in the list, dimmed and marked Archived, open to read with a note in place of the composer and a way to restore it for owners; after deletion the conversation still reads, its messages marked as a deleted agent's. The agents, chat and agent budgets guides say so.4d ago

audience.tsThe docs folder is gone, and what it held lives where people read it: how a self-hosted g1t runs and how to deploy g1t to Cloudflare are pages on docs.g1t.sh under Run g1t yourself, and speed, rate limits and operating g1t.sh are sections of CONTRIBUTING.md; code that cited a file in docs/ now points to the page or section that covers it, or says what it means itself, and applied migrations and the runner images are left as they were.5d ago

budget.test.tsThe Spend page says what a workspace spent, where it went and the budgets that hold it, in Workspace under Money: spent at price, agents' spend and the spend limit; by day; by agent, person, channel, model, kind of work and product; budgets from the workspace down to each person, agent and task, with what happens at 100%; the costliest tasks, each with a receipt of every session at the provider's price and what was charged; and how it's priced. Everyone sees what agents spent for them, and owners and billing managers the whole workspace; each person can have a monthly budget agents keep to, and the spend pill in the top bar shows your month or the workspace's against its limit. The spend guide says how.5d ago

budget.tsThe Spend page says what a workspace spent, where it went and the budgets that hold it, in Workspace under Money: spent at price, agents' spend and the spend limit; by day; by agent, person, channel, model, kind of work and product; budgets from the workspace down to each person, agent and task, with what happens at 100%; the costliest tasks, each with a receipt of every session at the provider's price and what was charged; and how it's priced. Everyone sees what agents spent for them, and owners and billing managers the whole workspace; each person can have a monthly budget agents keep to, and the spend pill in the top bar shows your month or the workspace's against its limit. The spend guide says how.5d ago

builder-call.tsAnyone makes an agent by describing it: one box drafts the whole agent (name, job, responsibilities, voice, skills to keep, integrations it needs, model limits and budget) as a card to change and try in a chat beside it before creating it, and an agent changes later by saying what to change, shown as a diff before it's saved. Members can make personal agents, which only they talk to and which spend from their own budget, unless owners turn that off; owners promote one to a workspace agent. The agents guide says how.5d ago

builder.test.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

builder.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

builtin.tsThe docs folder is gone, and what it held lives where people read it: how a self-hosted g1t runs and how to deploy g1t to Cloudflare are pages on docs.g1t.sh under Run g1t yourself, and speed, rate limits and operating g1t.sh are sections of CONTRIBUTING.md; code that cited a file in docs/ now points to the page or section that covers it, or says what it means itself, and applied migrations and the runner images are left as they were.5d ago

card-views.tsEach agent has an Abilities tab: g1t's built-ins, always on within the asker's access; its computer, coming; each connected integration's actions one row each, read, import, comment or resolve, with a level for each, alone, alone when the person asked for it, ask first or never, and whose connection it runs on; and MCP servers an owner adds. Reading is alone, writing inside g1t follows today's choices, anything that leaves g1t asks first, and production deploys can't go above ask. The agents service enforces every level: ask first posts a card to allow or deny and parks a session until it's answered, a refusal names its rule in the transcript and the audit log, and a missing ability posts a request to owners. The agent abilities guide says how.5d ago

cards.test.tsCards you act on in chat; agents comment and review as themselves; names shown cleanly; commits on the calendar6d ago

cards.tsEach agent has an Abilities tab: g1t's built-ins, always on within the asker's access; its computer, coming; each connected integration's actions one row each, read, import, comment or resolve, with a level for each, alone, alone when the person asked for it, ask first or never, and whose connection it runs on; and MCP servers an owner adds. Reading is alone, writing inside g1t follows today's choices, anything that leaves g1t asks first, and production deploys can't go above ask. The agents service enforces every level: ask first posts a card to allow or deny and parks a session until it's answered, a refusal names its rule in the transcript and the audit log, and a missing ability posts a request to owners. The agent abilities guide says how.5d ago

computer.test.tsEvery agent can have its own computer. A session that needs one wakes it: a home of its own on g1t cloud, one per agent and never shared, where it runs commands, reads and writes files and keeps what it made, with each session working in its own folder under a shared home; after ten idle minutes it sleeps, its home kept as a snapshot and restored when it wakes, and Reset wipes the home while memory and artifacts stay. Its shell and files are abilities with the usual choices, Alone, Alone when asked, Ask first or Never, offered only inside sessions and never to a chat reply; every command shows on the session with its output, and the agent's new Computer tab shows the state, the disk used of the five gigabytes included, the recent commands, and Wake, Put to sleep and Reset. Machine time counts only while it is awake, on the sandbox lines of the ledger that name the agent and who asked, held to the same spend caps as the session; the disk itself costs nothing in this version. The runner gained a long-lived supervisor that answers the computer's requests inside the container, and the runner service a computer per agent that keeps its snapshot in the agent homes bucket when one is attached, and says so when none is. The REST API and the agent tool can read a computer, wake it, put it to sleep and reset it. The agents, abilities, sessions, runners, billing and deploy guides say how it works and what an operator sets up; pinning a computer to your own runner, its browser and take-over come next.4d ago

computer.tsAn archived agent can be found, brought back, or deleted for good. The Agents page ends with Archived, folded, where owners see every archived agent and members their own personal ones, each with when and by whom it was archived and what deleting it would take; Restore brings it back, under a new handle when a live agent has taken its old one, and Delete permanently asks for the handle to be typed and then removes its sessions, replies, memories, routines, versions, drafts, skills and its computer's home, leaving its messages in chat under its saved name, the workspace's spend totals and the audit log. In Chat an archived agent is deactivated the way people expect: never offered as someone to message or mention, never woken, a conversation with it kept in the list, dimmed and marked Archived, open to read with a note in place of the composer and a way to restore it for owners; after deletion the conversation still reads, its messages marked as a deleted agent's. The agents, chat and agent budgets guides say so.4d ago

connectors.test.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

connectors.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

customize-fetch.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

customize-rpc.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

customize.test.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

definition.test.tsAgents have faces, and are never mistaken for people. Every agent wears a little bot face drawn from a look it owns, shape, colour, eyes, mouth, antenna, accessory and pattern, chosen in its builder and on its Profile tab with a live preview, Shuffle and a way back to the face its seed gives it; the face blinks on its own time, breathes, narrows its eyes while the agent works, shuts them asleep and bounces when it finishes, all of it still for anyone who asked for less motion. Wherever an agent shows, in chat, in a list, on a mention, on a review or a commit, its avatar carries an agent marker, and the people reading it are told so. In Chat, direct messages are two lists: People, and Agents, which also holds the agents you haven't talked to yet; a conversation with both a person and an agent in it is marked in the list, named in the conversation's header, spelled out by the composer and explained once the first time it opens. Agents keep their look in the agents service, which every service passes along. The chat and agents guides say so, and CONTRIBUTING makes the shared avatar the only way to draw an agent.4d ago

definition.tsAgents have faces, and are never mistaken for people. Every agent wears a little bot face drawn from a look it owns, shape, colour, eyes, mouth, antenna, accessory and pattern, chosen in its builder and on its Profile tab with a live preview, Shuffle and a way back to the face its seed gives it; the face blinks on its own time, breathes, narrows its eyes while the agent works, shuts them asleep and bounces when it finishes, all of it still for anyone who asked for less motion. Wherever an agent shows, in chat, in a list, on a mention, on a review or a commit, its avatar carries an agent marker, and the people reading it are told so. In Chat, direct messages are two lists: People, and Agents, which also holds the agents you haven't talked to yet; a conversation with both a person and an agent in it is marked in the list, named in the conversation's header, spelled out by the composer and explained once the first time it opens. Agents keep their look in the agents service, which every service passes along. The chat and agents guides say so, and CONTRIBUTING makes the shared avatar the only way to draw an agent.4d ago

desk.tsThe docs folder is gone, and what it held lives where people read it: how a self-hosted g1t runs and how to deploy g1t to Cloudflare are pages on docs.g1t.sh under Run g1t yourself, and speed, rate limits and operating g1t.sh are sections of CONTRIBUTING.md; code that cited a file in docs/ now points to the page or section that covers it, or says what it means itself, and applied migrations and the runner images are left as they were.5d ago

effort.test.tsPricing says it plainly: models at the provider's price, the agent rate for what g1t runs around every model call (the gateway, secrets, routing, context and pass-through to your own provider, so your own keys too), everything else at cost plus 20%, your own runners free, no seats; Security and quality comes with the plan with no separate fee, and live activations end. Each agent has an effort setting, Auto to Max, with what a typical task has cost at each level, and Spend's Spend less, keep quality suggests a lower level only when the agent's own past work shows quality held, to apply or dismiss. The pricing, spend and agents guides say how.5d ago

file-markdown.tsEvery agent starts with g1t's foundational skills, playbooks for documents, research, data, code, communication, and files and media, each using only tools the agent already has and saying plainly what isn't possible yet: agents make PDFs, Word documents, spreadsheets, CSV and Markdown files with make_file, kept with a doc in Artifacts and served from g1tusercontent.com; an agent's Skills tab shows what each skill can do and with which tools, and owners turn a skill off per agent; the agent skills guide says how.5d ago

files.test.tsThe artifacts service is services/artifacts, the Worker g1t-artifacts, bound as ARTIFACTS by the API, the site and the agents; its live rooms move to it with a Durable Object transfer from g1t-docs-service, and its database, bucket, indexes and queue keep their names. The git store's binding and settings are GITSTORE, its ops scripts gitstore-*, and workflow run artifacts keep their compatible API under run_artifacts modules. The deploy tool puts a Worker that has never deployed before the Workers in its stage that bind to it, and the deploy guide gives the cutover runbook.5d ago

files.tsEvery agent starts with g1t's foundational skills, playbooks for documents, research, data, code, communication, and files and media, each using only tools the agent already has and saying plainly what isn't possible yet: agents make PDFs, Word documents, spreadsheets, CSV and Markdown files with make_file, kept with a doc in Artifacts and served from g1tusercontent.com; an agent's Skills tab shows what each skill can do and with which tools, and owners turn a skill off per agent; the agent skills guide says how.5d ago

handle.test.tsThe Marketplace adds what g1t doesn't do and connects what you already use: extensions (Mail, Support, CRM, Recruiting, On-call, and bridges to a helpdesk, CRM or ERP you run, all Soon), starter kits, and integrations connected by the workspace or by each person; agents aren't installed there. Agent templates live in Agents, as starting points you configure, at Agents → Templates, and the Marketplace's old agent addresses lead there. The marketplace and agents guides say how.5d ago

handle.tsAgents → Skills is the workspace's skill library in the open SKILL.md format: write a skill in g1t, import a SKILL.md or zip, link a repository whose .g1t/skills folders publish on every push, or save a finished session as a skill once a person reviews it; attach a skill to an agent, a team or the whole workspace, each attachment pinned to a version. Agents see each skill's name and when to use it, and read the rest with use_skill when a request needs it; a skill never adds a permission, and scripts wait for an agent's own computer. The agent skills guide says how.5d ago

handoff.test.tsMerge branch 'worktree-agent-a1398e81ad1a64c5f'5d ago

handoff.tsThe docs folder is gone, and what it held lives where people read it: how a self-hosted g1t runs and how to deploy g1t to Cloudflare are pages on docs.g1t.sh under Run g1t yourself, and speed, rate limits and operating g1t.sh are sections of CONTRIBUTING.md; code that cited a file in docs/ now points to the page or section that covers it, or says what it means itself, and applied migrations and the runner images are left as they were.5d ago

happened.tsRoutines run when something happens: a pull request ready for review or merged, checks or a deploy failing, an issue opened6d ago

index.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

installs.test.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

installs.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

marketplaces.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

mcp-client.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

memory.tsThe docs folder is gone, and what it held lives where people read it: how a self-hosted g1t runs and how to deploy g1t to Cloudflare are pages on docs.g1t.sh under Run g1t yourself, and speed, rate limits and operating g1t.sh are sections of CONTRIBUTING.md; code that cited a file in docs/ now points to the page or section that covers it, or says what it means itself, and applied migrations and the runner images are left as they were.5d ago

meter.tsSpend adds up on one ledger. Charged this month has one definition, price less discount, included usage and credit, shared by the plan card, the spend limit, Spend and the top bar; the limit had counted usage not yet closed at full price before the discount, so a comped workspace read as charged a cent. Every agent line on the ledger names the agent and who asked, repository runs by g1t included, so Spent is the sum of its products, Agents is the agent product, and by agent adds up to it; the billing API returns by_agent and by_person. The usage and billing guide says how spend is counted.5d ago

money.tsAgents work in sessions: bounded, visible, steerable work spun off from chat, with subagents and colleagues in a tree paid by its root; memory with sources and scopes; routines; a workspace budget for every agent; agents file issues for whoever asked6d ago

ooxml.tsEvery agent starts with g1t's foundational skills, playbooks for documents, research, data, code, communication, and files and media, each using only tools the agent already has and saying plainly what isn't possible yet: agents make PDFs, Word documents, spreadsheets, CSV and Markdown files with make_file, kept with a doc in Artifacts and served from g1tusercontent.com; an agent's Skills tab shows what each skill can do and with which tools, and owners turn a skill off per agent; the agent skills guide says how.5d ago

orchestrator.test.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

orchestrator.tsAgents have faces, and are never mistaken for people. Every agent wears a little bot face drawn from a look it owns, shape, colour, eyes, mouth, antenna, accessory and pattern, chosen in its builder and on its Profile tab with a live preview, Shuffle and a way back to the face its seed gives it; the face blinks on its own time, breathes, narrows its eyes while the agent works, shuts them asleep and bounces when it finishes, all of it still for anyone who asked for less motion. Wherever an agent shows, in chat, in a list, on a mention, on a review or a commit, its avatar carries an agent marker, and the people reading it are told so. In Chat, direct messages are two lists: People, and Agents, which also holds the agents you haven't talked to yet; a conversation with both a person and an agent in it is marked in the list, named in the conversation's header, spelled out by the composer and explained once the first time it opens. Agents keep their look in the agents service, which every service passes along. The chat and agents guides say so, and CONTRIBUTING makes the shared avatar the only way to draw an agent.4d ago

pdf.tsEvery agent starts with g1t's foundational skills, playbooks for documents, research, data, code, communication, and files and media, each using only tools the agent already has and saying plainly what isn't possible yet: agents make PDFs, Word documents, spreadsheets, CSV and Markdown files with make_file, kept with a doc in Artifacts and served from g1tusercontent.com; an agent's Skills tab shows what each skill can do and with which tools, and owners turn a skill off per agent; the agent skills guide says how.5d ago

person-budget.tsThe Spend page says what a workspace spent, where it went and the budgets that hold it, in Workspace under Money: spent at price, agents' spend and the spend limit; by day; by agent, person, channel, model, kind of work and product; budgets from the workspace down to each person, agent and task, with what happens at 100%; the costliest tasks, each with a receipt of every session at the provider's price and what was charged; and how it's priced. Everyone sees what agents spent for them, and owners and billing managers the whole workspace; each person can have a monthly budget agents keep to, and the spend pill in the top bar shows your month or the workspace's against its limit. The spend guide says how.5d ago

plugins.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

policy.tsAnyone makes an agent by describing it: one box drafts the whole agent (name, job, responsibilities, voice, skills to keep, integrations it needs, model limits and budget) as a card to change and try in a chat beside it before creating it, and an agent changes later by saying what to change, shown as a diff before it's saved. Members can make personal agents, which only they talk to and which spend from their own budget, unless owners turn that off; owners promote one to a workspace agent. The agents guide says how.5d ago

ports.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

prompt.test.ts@g1t welcomes you when you join a workspace, and that is the one introduction any agent makes. Identity now says when a person becomes a member, workspace.member_joined, by invitation, by an invite code, or by creating the workspace, and webhooks can hear it; the agents service hears it too, and for anyone who joined, never the creator, the workspace's @g1t opens your direct message and says in its own voice who it is, what to ask it, how agents answer, and where things are, once per person per workspace and charged to @g1t like any reply, with a fixed welcome when no model can be used. The agents, workspaces, authentication and webhooks guides say so.4d ago

prompt.ts@g1t welcomes you when you join a workspace, and that is the one introduction any agent makes. Identity now says when a person becomes a member, workspace.member_joined, by invitation, by an invite code, or by creating the workspace, and webhooks can hear it; the agents service hears it too, and for anyone who joined, never the creator, the workspace's @g1t opens your direct message and says in its own voice who it is, what to ask it, how agents answer, and where things are, once per person per workspace and charged to @g1t like any reply, with a fixed welcome when no model can be used. The agents, workspaces, authentication and webhooks guides say so.4d ago

recall.test.tsWorkspace agents find, read, write and share the workspace's artifacts with search_artifacts, read_artifact, create_artifact (docs for now), edit_artifact, stale_artifacts, share_artifact and list_spaces, and their recall reads artifacts and projects' docs through the folio RPCs instead of Docs' pages.6d ago

recall.tsThe artifacts service is services/artifacts, the Worker g1t-artifacts, bound as ARTIFACTS by the API, the site and the agents; its live rooms move to it with a Durable Object transfer from g1t-docs-service, and its database, bucket, indexes and queue keep their names. The git store's binding and settings are GITSTORE, its ops scripts gitstore-*, and workflow run artifacts keep their compatible API under run_artifacts modules. The deploy tool puts a Worker that has never deployed before the Workers in its stage that bind to it, and the deploy guide gives the cutover runbook.5d ago

recommend.test.tsPricing says it plainly: models at the provider's price, the agent rate for what g1t runs around every model call (the gateway, secrets, routing, context and pass-through to your own provider, so your own keys too), everything else at cost plus 20%, your own runners free, no seats; Security and quality comes with the plan with no separate fee, and live activations end. Each agent has an effort setting, Auto to Max, with what a typical task has cost at each level, and Spend's Spend less, keep quality suggests a lower level only when the agent's own past work shows quality held, to apply or dismiss. The pricing, spend and agents guides say how.5d ago

recommend.tsAgents have faces, and are never mistaken for people. Every agent wears a little bot face drawn from a look it owns, shape, colour, eyes, mouth, antenna, accessory and pattern, chosen in its builder and on its Profile tab with a live preview, Shuffle and a way back to the face its seed gives it; the face blinks on its own time, breathes, narrows its eyes while the agent works, shuts them asleep and bounces when it finishes, all of it still for anyone who asked for less motion. Wherever an agent shows, in chat, in a list, on a mention, on a review or a commit, its avatar carries an agent marker, and the people reading it are told so. In Chat, direct messages are two lists: People, and Agents, which also holds the agents you haven't talked to yet; a conversation with both a person and an agent in it is marked in the list, named in the conversation's header, spelled out by the composer and explained once the first time it opens. Agents keep their look in the agents service, which every service passes along. The chat and agents guides say so, and CONTRIBUTING makes the shared avatar the only way to draw an agent.4d ago

reply.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

routines.tsThe docs folder is gone, and what it held lives where people read it: how a self-hosted g1t runs and how to deploy g1t to Cloudflare are pages on docs.g1t.sh under Run g1t yourself, and speed, rate limits and operating g1t.sh are sections of CONTRIBUTING.md; code that cited a file in docs/ now points to the page or section that covers it, or says what it means itself, and applied migrations and the runner images are left as they were.5d ago

routing.test.tsChat and workspace agents: channels, DMs and named agents you talk to6d ago

routing.tsPricing says it plainly: models at the provider's price, the agent rate for what g1t runs around every model call (the gateway, secrets, routing, context and pass-through to your own provider, so your own keys too), everything else at cost plus 20%, your own runners free, no seats; Security and quality comes with the plan with no separate fee, and live activations end. Each agent has an effort setting, Auto to Max, with what a typical task has cost at each level, and Spend's Spend less, keep quality suggests a lower level only when the agent's own past work shows quality held, to apply or dismiss. The pricing, spend and agents guides say how.5d ago

schedule.tsRoutines run when something happens: a pull request ready for review or merged, checks or a deploy failing, an issue opened6d ago

sessions.test.tsFour small things seen today. An agent can attach a file it made to any doc the person who asked can edit, whatever the space's agent mode: attaching changes nothing in the doc, so the suggest mode that stopped every PDF and spreadsheet no longer does; the ability is its own, attach, beside read, suggest and edit. Home no longer counts robots among the people: events that name an agent by its own id, or g1t's upkeep as the workspace or as g1t, read as the agent and as g1t, in the digest and on the page, so the faces say who instead of someone. Tooltips are the inverted bubble, the page's foreground behind the page's background, with no border. The Spend page's slice tabs keep their ring inside the row instead of losing its top to the scroll edge, and the Apps launcher keeps its search box and footer in place while it reads which apps there are, with skeleton tiles between.4d ago

sessions.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

skill-draft.tsAgents → Skills is the workspace's skill library in the open SKILL.md format: write a skill in g1t, import a SKILL.md or zip, link a repository whose .g1t/skills folders publish on every push, or save a finished session as a skill once a person reviews it; attach a skill to an agent, a team or the whole workspace, each attachment pinned to a version. Agents see each skill's name and when to use it, and read the rest with use_skill when a request needs it; a skill never adds a permission, and scripts wait for an agent's own computer. The agent skills guide says how.5d ago

skill-library.test.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

skill-library.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

skill-rpc.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

skill-zip.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

skills.test.tsFour small things seen today. An agent can attach a file it made to any doc the person who asked can edit, whatever the space's agent mode: attaching changes nothing in the doc, so the suggest mode that stopped every PDF and spreadsheet no longer does; the ability is its own, attach, beside read, suggest and edit. Home no longer counts robots among the people: events that name an agent by its own id, or g1t's upkeep as the workspace or as g1t, read as the agent and as g1t, in the digest and on the page, so the faces say who instead of someone. Tooltips are the inverted bubble, the page's foreground behind the page's background, with no border. The Spend page's slice tabs keep their ring inside the row instead of losing its top to the scroll edge, and the Apps launcher keeps its search box and footer in place while it reads which apps there are, with skeleton tiles between.4d ago

skills.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

store.tsAn archived agent can be found, brought back, or deleted for good. The Agents page ends with Archived, folded, where owners see every archived agent and members their own personal ones, each with when and by whom it was archived and what deleting it would take; Restore brings it back, under a new handle when a live agent has taken its old one, and Delete permanently asks for the handle to be typed and then removes its sessions, replies, memories, routines, versions, drafts, skills and its computer's home, leaving its messages in chat under its saved name, the workspace's spend totals and the audit log. In Chat an archived agent is deactivated the way people expect: never offered as someone to message or mention, never woken, a conversation with it kept in the list, dimmed and marked Archived, open to read with a note in place of the composer and a way to restore it for owners; after deletion the conversation still reads, its messages marked as a deleted agent's. The agents, chat and agent budgets guides say so.4d ago

suggest.tsWorkspace agents find, read, write and share the workspace's artifacts with search_artifacts, read_artifact, create_artifact (docs for now), edit_artifact, stale_artifacts, share_artifact and list_spaces, and their recall reads artifacts and projects' docs through the folio RPCs instead of Docs' pages.6d ago

surface.test.tsIn a group message with several agents, a message that names no agent goes to the one you are talking with: the agents that answered you last, else the ones you last mentioned, else, before anyone has been addressed, all of them; a message that mentions agents still goes only to those, and a conversation with one agent is as it was. Each agent is also told, when several are here, who you are talking with, so one that is woken alongside answers only what is clearly for it and does not redo a colleague's work. And an agent shows as typing for as long as it works, not for eight seconds: its desk says so every five seconds until the answer is posted, and after ten seconds the line reads that it is still working on it. The chat and agents guides say so.4d ago

surface.ts@g1t welcomes you when you join a workspace, and that is the one introduction any agent makes. Identity now says when a person becomes a member, workspace.member_joined, by invitation, by an invite code, or by creating the workspace, and webhooks can hear it; the agents service hears it too, and for anyone who joined, never the creator, the workspace's @g1t opens your direct message and says in its own voice who it is, what to ask it, how agents answer, and where things are, once per person per workspace and charged to @g1t like any reply, with a fixed welcome when no model can be used. The agents, workspaces, authentication and webhooks guides say so.4d ago

team-move.test.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

team-move.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

teammates.test.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

teammates.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

templates.tsAn agent is on teams the way a person is: through team membership, with no team or department of its own. Add it to teams when you create it, from its profile or from the team's page; the Agents sidebar groups agents by the teams they're on, with those on none last; what an agent is told about its teammates, team budgets, skills reach, Spend's By team and the People pages all read memberships. Agents with an old team name matching a team are moved onto it once; the rest are left off a team. Templates name a role only. The agents, teams and people guides say how.5d ago

tools.test.tsMerge the workspace shell: navigation and phone shell, g1t as orchestrator, agents in roles with audience-checked reads, reactions and custom emoji, live notifications and browser push, the homepage tour (agents 0002, chat 0002)6d ago

tools.tsCustomize replaces the Marketplace underneath: the agents service reads marketplaces, plugins, skills, subagents and MCP servers in the formats Claude Code reads, so public ones install on g1t as they are. A workspace starts with claude-plugins-official and anthropic-agent-skills and adds marketplaces by owner/repo, a repository here, a git address or a link to marketplace.json; installing a plugin (read from GitHub, from this g1t or from a zip, at a pinned commit) puts its skills in the library as plugin:skill, keeps its subagents as templates to hire from, and turns the remote servers of its .mcp.json into connectors. Connectors are MCP servers the workspace connects once, from the directory, a plugin or an address, signing in with the browser (OAuth with PKCE and dynamic client registration), a key, or not at all, their secrets sealed under CONNECTORS_KEY, and given to every agent, a team or one agent like skills; an agent's turn gets them beside its own servers, so levels, Ask-first cards and audit are unchanged. The linked skills repository is .claude/skills now (.g1t/skills still read). The old extension installs go; requests stay and name plugins, skills and connectors too. In the rail, Agents follows Code, and the top bar's + menu loses Put an agent on it and New workspace.3d ago

transcript.tsEvery agent can have its own computer. A session that needs one wakes it: a home of its own on g1t cloud, one per agent and never shared, where it runs commands, reads and writes files and keeps what it made, with each session working in its own folder under a shared home; after ten idle minutes it sleeps, its home kept as a snapshot and restored when it wakes, and Reset wipes the home while memory and artifacts stay. Its shell and files are abilities with the usual choices, Alone, Alone when asked, Ask first or Never, offered only inside sessions and never to a chat reply; every command shows on the session with its output, and the agent's new Computer tab shows the state, the disk used of the five gigabytes included, the recent commands, and Wake, Put to sleep and Reset. Machine time counts only while it is awake, on the sandbox lines of the ledger that name the agent and who asked, held to the same spend caps as the session; the disk itself costs nothing in this version. The runner gained a long-lived supervisor that answers the computer's requests inside the container, and the runner service a computer per agent that keeps its snapshot in the agent homes bucket when one is attached, and says so when none is. The REST API and the agent tool can read a computer, wake it, put it to sleep and reset it. The agents, abilities, sessions, runners, billing and deploy guides say how it works and what an operator sets up; pinning a computer to your own runner, its browser and take-over come next.4d ago

triggers.test.tsRoutines run when something happens: a pull request ready for review or merged, checks or a deploy failing, an issue opened6d ago

triggers.tsThe docs folder is gone, and what it held lives where people read it: how a self-hosted g1t runs and how to deploy g1t to Cloudflare are pages on docs.g1t.sh under Run g1t yourself, and speed, rate limits and operating g1t.sh are sections of CONTRIBUTING.md; code that cited a file in docs/ now points to the page or section that covers it, or says what it means itself, and applied migrations and the runner images are left as they were.5d ago

turn.test.tsMerge the workspace shell: navigation and phone shell, g1t as orchestrator, agents in roles with audience-checked reads, reactions and custom emoji, live notifications and browser push, the homepage tour (agents 0002, chat 0002)6d ago

turn.tsPricing says it plainly: models at the provider's price, the agent rate for what g1t runs around every model call (the gateway, secrets, routing, context and pass-through to your own provider, so your own keys too), everything else at cost plus 20%, your own runners free, no seats; Security and quality comes with the plan with no separate fee, and live activations end. Each agent has an effort setting, Auto to Max, with what a typical task has cost at each level, and Spend's Spend less, keep quality suggests a lower level only when the agent's own past work shows quality held, to apply or dismiss. The pricing, spend and agents guides say how.5d ago

views.tsAn archived agent can be found, brought back, or deleted for good. The Agents page ends with Archived, folded, where owners see every archived agent and members their own personal ones, each with when and by whom it was archived and what deleting it would take; Restore brings it back, under a new handle when a live agent has taken its old one, and Delete permanently asks for the handle to be typed and then removes its sessions, replies, memories, routines, versions, drafts, skills and its computer's home, leaving its messages in chat under its saved name, the workspace's spend totals and the audit log. In Chat an archived agent is deactivated the way people expect: never offered as someone to message or mention, never woken, a conversation with it kept in the list, dimmed and marked Archived, open to read with a note in place of the composer and a way to restore it for owners; after deletion the conversation still reads, its messages marked as a deleted agent's. The agents, chat and agent budgets guides say so.4d ago

welcome.test.ts@g1t welcomes you when you join a workspace, and that is the one introduction any agent makes. Identity now says when a person becomes a member, workspace.member_joined, by invitation, by an invite code, or by creating the workspace, and webhooks can hear it; the agents service hears it too, and for anyone who joined, never the creator, the workspace's @g1t opens your direct message and says in its own voice who it is, what to ask it, how agents answer, and where things are, once per person per workspace and charged to @g1t like any reply, with a fixed welcome when no model can be used. The agents, workspaces, authentication and webhooks guides say so.4d ago

welcome.ts@g1t welcomes you when you join a workspace, and that is the one introduction any agent makes. Identity now says when a person becomes a member, workspace.member_joined, by invitation, by an invite code, or by creating the workspace, and webhooks can hear it; the agents service hears it too, and for anyone who joined, never the creator, the workspace's @g1t opens your direct message and says in its own voice who it is, what to ask it, how agents answer, and where things are, once per person per workspace and charged to @g1t like any reply, with a fixed welcome when no model can be used. The agents, workspaces, authentication and webhooks guides say so.4d ago