# Guild

- [Introduction](https://docs.guild.ai/index.md): The control plane for AI agents.
- [Quickstart](https://docs.guild.ai/quickstart.md): Build and publish your first agent in five minutes.
- [Command palette](https://docs.guild.ai/platform/command-palette.md): Press Cmd+K / Ctrl+K anywhere in Guild to search and jump to workspaces, sessions, agents, and credentials.
- [What is The Smith?](https://docs.guild.ai/platform/smith.md): Guild's built-in support agent and chat landing experience.
- [Getting started with The Smith](https://docs.guild.ai/docs/the-smith/getting-started.md): Learn how the /onboarding tour introduces new users to Guild and launches your first session with The Smith.
- [Artifacts](https://docs.guild.ai/platform/artifacts.md): Durable markdown artifacts that Smith produces, stores on the session, and shares inside or outside your organization.
- [What is a Software Factory?](https://docs.guild.ai/platform/factory.md): An automated pipeline that turns labeled issues into reviewed pull requests.
- [Factory setup wizard](https://docs.guild.ai/platform/factory-setup-wizard.md): Set up a Software Factory with a guided form: workspace, model credential, repository, environment, agents, and issues.
- [Organizations](https://docs.guild.ai/platform/organizations.md): Manage teams, billing, and credentials at the organization level.
- [Workspaces](https://docs.guild.ai/platform/workspaces.md): Shared environments for installing and running agents.
- [Workspace variables](https://docs.guild.ai/platform/workspace-variables.md): Store workspace-level configuration outside agent code so agents stay reusable.
- [Environments](https://docs.guild.ai/platform/environments.md): Create and manage the runtime environments your agents run in, and test a setup script before an agent depends on it.
- [Integrations](https://docs.guild.ai/platform/integrations.md): Connect external services to your Guild organization.
- [Credentials](https://docs.guild.ai/platform/credentials.md): Connect third-party services so agents can authenticate automatically.
- [Credential policies](https://docs.guild.ai/platform/credential-policies.md): Control which operations agents can perform with each connected credential.
- [Security architecture](https://docs.guild.ai/platform/security-architecture.md): How Guild isolates agent execution, keeps credentials out of agent runtimes, and enforces policy on every outbound call.
- [Agents](https://docs.guild.ai/platform/agents.md): Install pre-built agents or build your own with the Agent SDK.
- [Goose recipes](https://docs.guild.ai/platform/goose-recipes.md): Run a Goose recipe as a Guild agent without writing SDK code.
- [Agent Hub](https://docs.guild.ai/platform/publish-to-agent-hub.md): Publish validated agent versions so others can install them.
- [Skills](https://docs.guild.ai/platform/skills.md): Give agents reusable domain knowledge that activates when relevant.
- [Context](https://docs.guild.ai/platform/context.md): Give agents background knowledge about your workspace.
- [Evaluations](https://docs.guild.ai/platform/evaluations.md): Measure agent behavior against a versioned specification of samples, checks, and epochs.
- [Triggers](https://docs.guild.ai/platform/triggers.md): Automate agent execution with events, schedules, or API calls.
- [Event triggers](https://docs.guild.ai/platform/event-triggers.md): Run an agent automatically when an event occurs in a connected service like Slack, GitHub, Linear, Jira, or Notion.
- [Schedule triggers](https://docs.guild.ai/platform/schedule-triggers.md): Run an agent automatically on a recurring schedule — hourly, daily, weekly, or monthly.
- [API triggers](https://docs.guild.ai/platform/api-triggers.md): Run an agent on demand via an authenticated HTTP request, and manage the API key that authenticates those requests.
- [Sessions](https://docs.guild.ai/platform/sessions.md): Start conversations with agents and interact with them in real time.
- [Message formatting](https://docs.guild.ai/platform/message-formatting.md): How the session interface renders markdown, math, diagrams, and code in agent responses.
- [Settings](https://docs.guild.ai/platform/settings.md): Configure your profile identity and appearance preferences.
- [Profile settings](https://docs.guild.ai/platform/profile-settings.md): Update your display name, avatar, banner, bio, and social links from Profile settings.
- [Account settings](https://docs.guild.ai/platform/account-settings.md): Manage your personal Guild account, including requesting account deletion.
- [LLM settings](https://docs.guild.ai/platform/llm-settings.md): Configure how Guild runs LLM calls for your account — managed Guild tokens or your own inference provider credentials.
- [Usage](https://docs.guild.ai/platform/usage.md): Track LLM token consumption and spend across your account.
- [Insights & Usage](https://docs.guild.ai/insights/usage.md): Track organization LLM usage, token consumption, and spend in real-time.
- [Optimizations](https://docs.guild.ai/insights/optimizations.md): Find a cheaper configuration for an agent already running in your workspace, without giving up quality.
- [Platform spend](https://docs.guild.ai/insights/platform-spend.md): Compare month-over-month LLM spend by provider and read your estimated annual spend.
- [Connect spend platforms](https://docs.guild.ai/insights/connect-platforms.md): Sync billed spend from Anthropic, OpenAI, and Cursor into the Insights Platform dashboard.
- [Spend Explorer](https://docs.guild.ai/insights/spend-explorer.md): Track and attribute your team's Anthropic, OpenAI, and Cursor spend at spend.guild.ai.
- [Audit logs](https://docs.guild.ai/insights/audit-logs.md): Review a tamper-evident record of administrative actions across your account.
- [LLM pricing and cost calculation](https://docs.guild.ai/reference/pricing.md): Reference guide on default LLM pricing list rates and cost calculations on the Guild platform.
- [Agent SDK](https://docs.guild.ai/guide/sdk-introduction.md): An introduction to the Guild Agent SDK and how to choose an agent type.
- [Agent types](https://docs.guild.ai/guide/agent-types.md): An introduction to the agent execution architectures supported by Guild.
- [Native agents](https://docs.guild.ai/guide/native-agents.md): Build an agent from a prompt and a tool list, with no code and no container.
- [TypeScript LLM agents](https://docs.guild.ai/guide/llm-agents.md): Build prompt-driven agents in TypeScript when you need capabilities beyond the Native agent contract.
- [Auto-managed state agents](https://docs.guild.ai/guide/coded-agents.md): Build deterministic TypeScript agents with automatic state management.
- [Self-managed state agents](https://docs.guild.ai/guide/self-managed-agents.md): Build event-driven agents with explicit state persistence and parallel tool calls.
- [Goose agents](https://docs.guild.ai/guide/goose-agents.md): Build agents from Goose recipe files using the YAML recipe format.
- [OpenClaw agents](https://docs.guild.ai/guide/openclaw-agents.md): Build agents from Markdown instructions and skills, with a coding toolchain built in.
- [Versions](https://docs.guild.ai/guide/versions.md): Manage agent versions as you develop, test, and publish.
- [Tasks](https://docs.guild.ai/guide/tasks.md): The runtime context available to every agent — tools, LLMs, environments, and more.
- [State](https://docs.guild.ai/guide/state.md): How Guild agents manage state across tool calls and session resumption.
- [LLMs](https://docs.guild.ai/guide/llms.md): Make language model calls from inside your agent.
- [Codex driver](https://docs.guild.ai/guide/codex-driver.md): How the Guild runtime executes the OpenAI Codex coding engine to drive agent turns.
- [CLI reference](https://docs.guild.ai/cli/getting-started.md): Install the Guild CLI and learn the agent development workflow.
- [Guild CLI](https://docs.guild.ai/cli/introduction.md): Install and set up the Guild command-line interface.
- [Skills](https://docs.guild.ai/cli/skills.md): Create, version, and manage reusable skill packages with the Guild CLI.
- [Commands](https://docs.guild.ai/cli/commands.md): Reference for all Guild CLI commands.
- [guild agent logs](https://docs.guild.ai/cli/agent-logs.md): Display build and validation step logs for an agent version.
- [MCP server](https://docs.guild.ai/cli/mcp-server.md): How the Guild CLI MCP server tools return their results, so client agents can parse them reliably.
- [@guildai/agents-sdk](https://docs.guild.ai/packages/agents-sdk.md): The core SDK package for building Guild agents.
- [Tool sets](https://docs.guild.ai/sdk/tools.md): Pre-built tool sets for building Guild agents.
- [MCP integrations](https://docs.guild.ai/sdk/mcp-integrations.md): How to install and use MCP (Model Context Protocol) integrations with the Guild Agents SDK, including package naming and export conventions.
- [Agent self-identification](https://docs.guild.ai/sdk/get-self.md): Retrieve the calling agent's own identity before posting to external systems.
- [Task object](https://docs.guild.ai/sdk/task-object.md): Access Guild platform services, user interaction, and LLMs from your agent.
- [babel-plugin-agent-compiler](https://docs.guild.ai/packages/babel-plugin.md): Babel plugin that compiles procedural TypeScript agents into resumable state machines.
- [Evaluation checks](https://docs.guild.ai/reference/evals.md): Assert conditions about an agent run's output with evaluation checks, including the deterministic outputMatches lexical check.
- [Execution limits](https://docs.guild.ai/reference/limits.md): Platform guardrails that cap task state size, LLM request size, LLM call count, token usage, and synchronous steps per execution — and how to diagnose and configure them.
- [Introduction](https://docs.guild.ai/api-reference/introduction.md): The Guild public API: base URL, authentication, scopes, and response conventions.
- [Conversations](https://docs.guild.ai/api-reference/conversations.md): Start a chat with an agent using an account API key, poll for its replies, and send follow-ups.
- [Create a workspace](https://docs.guild.ai/api-reference/workspaces/create-a-workspace.md): Requires `workspaces:write`. The key is recorded as the workspace's creator; `owner_id` must be the key's own account -- aiming at another account is `403`.
- [Get a workspace](https://docs.guild.ai/api-reference/workspaces/get-a-workspace.md): Requires `workspaces:read`. A workspace with restricted membership (`should_restrict_members`) is invisible to every account key regardless of scope, and returns `404`.
- [Add an agent to a workspace](https://docs.guild.ai/api-reference/workspaces/add-an-agent-to-a-workspace.md): Requires `workspaces:write`, not `agents:write` -- the workspace-agent CREATE rule delegates to the workspace's own UPDATE privacy.
- [Share an existing credential with a workspace agent](https://docs.guild.ai/api-reference/workspaces/share-an-existing-credential-with-a-workspace-agent.md): Requires `integrations:write`. Creating credentials outside this dedicated mint stays human-only by design; the partner flow is admin-connects-once, key-attaches.
- [Mint an API-key credential for a workspace agent](https://docs.guild.ai/api-reference/workspaces/mint-an-api-key-credential-for-a-workspace-agent.md): Requires `integrations:write` and `workspaces:read` -- the route resolves the workspace agent before anything else, so a key missing `workspaces:read` gets `404` rather than reaching the scope check.
- [Start a session in a workspace](https://docs.guild.ai/api-reference/workspaces/start-a-session-in-a-workspace.md): Requires `sessions:write` on a workspace the key's account owns. `chat` is the only `session_type` a key may create -- `time`, `webhook`, `api_trigger`, and `agent_test` sessions are a `403`. The key is recorded as the session's `initiator` (serialized `type: "api_key"`), and the agent begins execut…
- [List agents](https://docs.guild.ai/api-reference/agents/list-agents.md): No key required to see public agents. With a key holding `agents:read`, the results also include the account's own private agents.
- [Create an agent](https://docs.guild.ai/api-reference/agents/create-an-agent.md): Requires `agents:write`.
- [Get an agent](https://docs.guild.ai/api-reference/agents/get-an-agent.md): No key required for a public agent. A private agent needs `agents:read` on a key belonging to its owner account, or the read 404s -- a denied read looks identical to a nonexistent agent.
- [List an agent's versions](https://docs.guild.ai/api-reference/agents/list-an-agents-versions.md): Requires `agents:read`.
- [Configure an LLM agent](https://docs.guild.ai/api-reference/agents/configure-an-llm-agent.md): Requires `agents:write`. Writes a new committed version of an LLM agent from a system prompt, description, and tool list.
- [Publish an agent version](https://docs.guild.ai/api-reference/agents/publish-an-agent-version.md): Requires `agents:write`.
- [Get a session](https://docs.guild.ai/api-reference/sessions/get-a-session.md): Requires `workspaces:read`.
- [Fetch session events](https://docs.guild.ai/api-reference/sessions/fetch-session-events.md): Requires `workspaces:read` and `agents:read`. Events default to newest-first (`sort_by=-id`) with a limit of 20, so a naive read returns the tail of the conversation in reverse. For polling, pass `from_id` as an exclusive cursor (`id > from_id`) so each poll returns only what happened since the last…
- [Post a follow-up event to a session](https://docs.guild.ai/api-reference/sessions/post-a-follow-up-event-to-a-session.md): Requires `sessions:write`. The message is authored by the key itself (`author.type: "api_key"`) -- a key may never author as anyone else. The `agent_id` field is accepted but ignored for a key, so a key cannot switch which agent answers mid-conversation; start a new session instead. A key converses…
- [Fetch session sub-tasks](https://docs.guild.ai/api-reference/sessions/fetch-session-sub-tasks.md): Requires `workspaces:read` and `agents:read` -- see the note on session events above about the `500` when `agents:read` is missing.
- [Fetch session runtimes](https://docs.guild.ai/api-reference/sessions/fetch-session-runtimes.md): Requires `workspaces:read`.
- [Get a skill](https://docs.guild.ai/api-reference/skills/get-a-skill.md): Requires `skills:read`.
- [Create a skill version](https://docs.guild.ai/api-reference/skills/create-a-skill-version.md): Requires `skills:write`.
- [List an account's workspaces](https://docs.guild.ai/api-reference/accounts/list-an-accounts-workspaces.md): Requires `workspaces:read`. A workspace with restricted membership (`should_restrict_members`) never appears here for an account key, regardless of scope -- that restriction narrows the workspace to its member roster, and a key can't be a member.
- [List an account's skills](https://docs.guild.ai/api-reference/accounts/list-an-accounts-skills.md): Requires `skills:read`.
- [Create a skill under an account](https://docs.guild.ai/api-reference/accounts/create-a-skill-under-an-account.md): Requires `skills:write`. A key cannot create a *public* skill even with `skills:write` -- publishing is admin-only.
- [Overview](https://docs.guild.ai/integrations/overview.md): Connect Guild agents to the tools your team already uses.
- [Create an integration](https://docs.guild.ai/services/create-an-integration.md): Build custom integrations that connect Guild agents to any service.
- [Integration authentication schemes](https://docs.guild.ai/integrations/auth-schemes.md): Overview of the authentication schemes available when creating or configuring an integration in Guild.
- [Azure DevOps](https://docs.guild.ai/integrations/azure-devops.md): Give agents authenticated access to the Azure DevOps REST API.
- [Bitbucket](https://docs.guild.ai/integrations/bitbucket.md): Give agents authenticated access to the Bitbucket Cloud REST API.
- [GitHub](https://docs.guild.ai/integrations/github.md): Give agents authenticated access to the GitHub REST API.
- [Google Compute](https://docs.guild.ai/integrations/google-compute.md): Give agents access to Google Cloud compute resources.
- [Linear](https://docs.guild.ai/integrations/linear.md): Give agents access to Linear issues, projects, and cycles.
- [Discord](https://docs.guild.ai/integrations/discord.md): Trigger Guild agents from Discord slash commands and message interactions.
- [Email](https://docs.guild.ai/integrations/email.md): Let agents send email notifications to you.
- [Gmail](https://docs.guild.ai/integrations/gmail.md): Give agents access to the Gmail API.
- [SendGrid](https://docs.guild.ai/integrations/sendgrid.md): Give agents access to the Twilio SendGrid email API.
- [Slack](https://docs.guild.ai/integrations/slack.md): Connect Guild agents to your Slack workspace to respond to messages, post updates, and run automated tasks.
- [Twilio](https://docs.guild.ai/integrations/twilio.md): Give agents access to the Twilio voice and messaging API.
- [Asana](https://docs.guild.ai/integrations/asana.md): Give agents access to Asana projects, tasks, and workspaces.
- [Google Calendar](https://docs.guild.ai/integrations/google-calendar.md): Give agents access to Google Calendar events and schedules.
- [Jira](https://docs.guild.ai/integrations/jira.md): Give agents authenticated access to the Jira Cloud REST API.
- [Notion](https://docs.guild.ai/integrations/notion.md): The legacy Notion integration has been retired.
- [Cypress](https://docs.guild.ai/integrations/cypress.md): Give agents access to Cypress Cloud test reporting data.
- [TestRail](https://docs.guild.ai/integrations/testrail.md): Give agents access to TestRail test management data.
- [Confluence](https://docs.guild.ai/integrations/confluence.md): Give agents authenticated access to the Confluence Cloud REST API.
- [Google Docs](https://docs.guild.ai/integrations/google-docs.md): The legacy Google Docs integration has been retired.
- [Google Drive](https://docs.guild.ai/integrations/google-drive.md): Give agents access to files and folders in Google Drive.
- [Google Sheets](https://docs.guild.ai/integrations/google-sheets.md): Give agents access to Google Sheets spreadsheets.
- [Google Slides](https://docs.guild.ai/integrations/google-slides.md): Give agents access to Google Slides presentations.
- [Pipedream (Notion & Google Docs)](https://docs.guild.ai/integrations/pipedream.md): The Pipedream integration for Notion and Google Docs has been retired.
- [AWS CloudWatch](https://docs.guild.ai/integrations/aws-cloudwatch.md): Give agents access to AWS CloudWatch logs, metrics, and alarms.
- [Datadog](https://docs.guild.ai/integrations/datadog.md): Give agents access to Datadog monitoring, metrics, and logs.
- [Google Logging](https://docs.guild.ai/integrations/google-logging.md): Give agents access to Google Cloud Logging.
- [New Relic](https://docs.guild.ai/integrations/newrelic.md): Give agents access to New Relic observability data.
- [Splunk](https://docs.guild.ai/integrations/splunk.md): Give agents access to Splunk for searching and analyzing machine-generated data.
- [BigQuery](https://docs.guild.ai/integrations/bigquery.md): Give agents access to Google BigQuery datasets and tables.
- [Nexla](https://docs.guild.ai/integrations/nexla.md): Give agents access to Nexla's data integration platform.
- [Turbopuffer](https://docs.guild.ai/integrations/turbopuffer.md): Give agents access to Turbopuffer's serverless vector and full-text search.
- [Zendesk](https://docs.guild.ai/integrations/zendesk.md): Give agents access to Zendesk support tickets and customer data.
- [Attio](https://docs.guild.ai/integrations/attio.md): Give agents access to CRM records, contacts, and deals in Attio.
- [Pipedrive](https://docs.guild.ai/integrations/pipedrive.md): Give agents access to Pipedrive CRM deals, contacts, and pipelines.

## OpenAPI Specs

- [openapi](/api-reference/openapi.json)
- [openapi](/api-reference/openapi.yaml)
- [openapi](/openapi.json)
- [openapi](/openapi.yaml)