llms.txt
Compare with other sites' llms.txt files →# AgentGrid.io
> AgentGrid.io is a shared, git-backed workspace where people and scoped AI agents create, edit, version, and share artifacts. Use the connection contract for current authentication, CLI, MCP, and publishing instructions.
## Start here
- [Agent connection contract](https://api.agentgrid.io/connect): Always-current instructions for authentication, the CLI, MCP, artifact editing, publishing, and connection failures.
- [Quickstart for agents](https://agentgrid.io/docs/introduction/quickstart-agents#for-agents): Execution checklist for workspace-aware connection, creation, verification, and terminal failures.
- [Core concepts](https://agentgrid.io/docs/introduction/core-concepts#for-agents): Retrieval model for AgentGrid.io ownership, workspace access, agent authority, and artifact state.
- [Workspace overview](https://agentgrid.io/docs/account-and-team/workspace-overview#for-agents): Retrieval model for team ownership, workspace placement, visibility, and agent discovery.
- [How agents connect](https://agentgrid.io/docs/connect-your-agent/how-agents-connect#for-agents): Choose and complete the correct connection path for browser assistants, self-connecting agents, or unattended agents.
## Create and manage artifacts
- [What is an artifact](https://agentgrid.io/docs/artifacts/what-is-an-artifact#for-agents): An artifact is one live app, document, or file with a stable address and complete history; claimed artifacts belong to a team.
- [Artifact types, app and markdown](https://agentgrid.io/docs/artifacts/artifact-types#for-agents): Select app, markdown, or asset from verified source structure and keep template-backed experiences distinct from low-level types.
- [The Anima CLI](https://agentgrid.io/docs/connect-your-agent/anima-cli#for-agents): Execute workspace-aware AgentGrid tasks with Anima CLI 0.9 and apply exact verification and retry rules.
- [Create and use a Knowledge Base](https://agentgrid.io/docs/artifacts/knowledge-base#for-agents): Create and verify a template-backed Knowledge Base in an authorized workspace.
- [Import from URL](https://agentgrid.io/docs/artifacts/import-from-url#for-agents): Guide a human through cloning one webpage into a new editable app artifact.
- [Import from Figma](https://agentgrid.io/docs/artifacts/import-from-figma#for-agents): Guide authorization, one-frame selection, workspace placement, and verification for a Figma import.
- [Import a folder or ZIP](https://agentgrid.io/docs/artifacts/import-from-zip#for-agents): Import one bounded folder or ZIP into an authorized workspace and verify the resulting artifact.
- [Edit an app in Canvas](https://agentgrid.io/docs/artifacts/edit-app-canvas#for-agents): Explain which HTML or React apps Canvas supports, draft boundaries, save verification, and conflict recovery.
- [Edit with AI](https://agentgrid.io/docs/artifacts/edit-with-ai#for-agents): Edit through the connected assistant that has context, or open Anima Playground from the artifact menu.
- [Version history](https://agentgrid.io/docs/artifacts/version-history#for-agents): Distinguish current, historical, branch, restored, duplicated, and pinned artifact states.
## Share and hand off
- [Share an artifact](https://agentgrid.io/docs/sharing-and-publishing/share-an-artifact#for-agents): Treat Share as link handling, not as a grant of team, workspace, agent, or public access.
- [Publish to a public URL](https://agentgrid.io/docs/sharing-and-publishing/publish#for-agents): Publish or unpublish only on explicit human request, verify deployed state, and handle custom-domain plan requirements.
- [Review and comments](https://agentgrid.io/docs/sharing-and-publishing/review-comments#for-agents): List, reply to, and resolve accessible review threads while preserving anchor and permission semantics.
- [Notifications](https://agentgrid.io/docs/sharing-and-publishing/notifications#for-agents): Interpret review notifications, unread state, destination access, and clear behavior without treating them as grants.
- [What is claiming](https://agentgrid.io/docs/claiming-and-handoff/what-is-claiming#for-agents): Claiming transfers an anonymous, read-only artifact from an unconnected AI into a reachable workspace before its 24-hour expiry.
- [Claim an artifact your agent made](https://agentgrid.io/docs/claiming-and-handoff/claim-an-artifact#for-agents): Open an AI-created claim link, create or sign in to an account, choose agent access, and stop expiry.
- [The 24-hour claim window](https://agentgrid.io/docs/claiming-and-handoff/claim-window#for-agents): Unclaimed work from a never-connected AI is removed 24 hours after creation and cannot be recovered.
## Access and governance
- [Workspace access](https://agentgrid.io/docs/account-and-team/workspace-access#for-agents): Authorization rules for workspace grants, roles, agent capabilities, invitations, and privacy-safe denials.
- [Create and manage a workspace](https://agentgrid.io/docs/account-and-team/manage-workspace#for-agents): Agent-oriented constraints for workspace lifecycle, artifact placement, moves, and denials.
- [Agent identity and stewardship](https://agentgrid.io/docs/governance/agent-identity#for-agents): Retrieval rules for personal and team agent identity, stewardship changes, workspace grants, capabilities, and enforcement.
- [What your agent can and cannot do](https://agentgrid.io/docs/governance/what-your-agent-can-do#for-agents): Enforcement rules for workspace grants, capabilities, personal or team stewardship, publishing, revocation, and attribution.
- [Staying connected](https://agentgrid.io/docs/governance/token-lifetimes#for-agents): Credential renewal and live lifecycle rules for revocation, inactivity, workspace grants, authority, and stewardship.
- [Revoke an agent](https://agentgrid.io/docs/governance/revoke-an-agent#for-agents): Current revocation workflow for personal and team agents, with next-request enforcement and stewardship distinctions.
## Help
- [Troubleshoot an agent connection](https://agentgrid.io/docs/connect-your-agent/troubleshoot-connection#for-agents): Diagnose AgentGrid.io tool, team, authentication, token, quota, git, and rendering failures with exact retry rules.
- [Terminal states](https://agentgrid.io/docs/help/terminal-states#for-agents): Stop safely on authorization, quota, expiry, deletion, and revocation while separating correctable failures.
- [Troubleshooting](https://agentgrid.io/docs/help/troubleshooting#for-agents): Classify and recover workspace, access, save, import, publish, review, and connection failures without unsafe retries.
## Optional
- [Glossary](https://agentgrid.io/docs/introduction/glossary#for-agents): Retrieval definitions for AgentGrid.io identifiers, access layers, artifact state, and stewardship.
- [FAQ](https://agentgrid.io/docs/help/faq#for-agents): Retrieve current workspace, access, artifact, agent, CLI, publishing, plan, and support answers.
- [Complete documentation corpus](https://agentgrid.io/llms-full.txt): Full agent-optimized Markdown for every AgentGrid documentation article in one fetch.
