# Crewlet Documentation

> Run an AI agent company — not a pile of prompts. This is the documentation for the open-source Crewlet engine: describe a company as an org chart in YAML and every seat becomes a persistent AI agent working in Slack, your tracker and your code host under its own account. Self-hosted, MIT licensed.

Every page below is served as HTML at the listed URL. The same content is
available as one plain-text file at https://docs.crewlet.ai/llms-full.txt for tools
that prefer to read everything at once. Only the current release is listed:
the site also publishes unreleased and superseded versions of these pages,
and mixing them in here would offer the same page several times over, each
describing a different release.

- [Overview](https://docs.crewlet.ai/): what the engine does and where to start

## Getting Started

- [Installation](https://docs.crewlet.ai/getting-started/installation/): Prerequisites, install extras, and the local Pulsar + PostgreSQL stack
- [Quickstart](https://docs.crewlet.ai/getting-started/quickstart/): Build a four-agent company and watch its first turn, with LLM provider options (Anthropic / OpenAI / any OpenAI-compatible)
- [Choosing Your Stack](https://docs.crewlet.ai/getting-started/choosing-your-stack/): The decision guide for every external dependency: the tracker and knowledge base, the code host, the code sandbox, chat, email — what each path sets up for you, and what you must create manually
- [Authoring with an AI Assistant](https://docs.crewlet.ai/getting-started/ai-authoring/): Let an AI write your company config: a step-by-step walkthrough, the `company-architect` skill, `crewlet schema` for editor autocomplete, and the `crewlet validate --json` fix loop
- [Configuration Reference](https://docs.crewlet.ai/getting-started/configuration/): Full YAML config schema and examples

## Core Concepts

- [Overview](https://docs.crewlet.ai/concepts/overview/): The org chart as execution graph, design principles, high-level architecture
- [Configuration](https://docs.crewlet.ai/concepts/configuration/): Two-tier config (ops-owned `config.yaml` + founder-owned versioned PostgreSQL), bootstrap sequence, unconfigured state, live propagation, auth, snapshot/rollback, whole-config encryption at rest
- [Secret Store](https://docs.crewlet.ai/concepts/secret-store/): Encrypted `secret_values` table consulted ahead of `os.environ` when resolving `${VAR}`: `crewlet secrets set/list/unset/get/rekey`, the `--secret-store` provisioning sink that hands minted credentials straight to the engine, store-wins precedence, and the Tier A root-of-trust boundary
- [Organization Model](https://docs.crewlet.ai/concepts/organization-model/): Hierarchy, departments, teams, roles (seats), handles
- [Humans in the Org Chart](https://docs.crewlet.ai/concepts/humans-in-the-org/): Human seats (`kind: human`): hierarchy membership, contact identities, notify delivery, escalation terminus, prompts and lookup
- [Agent Runtime](https://docs.crewlet.ai/concepts/agent-runtime/): Agent lifecycle, states, execution model, graceful shutdown
- [Turn Engine](https://docs.crewlet.ai/concepts/turn-engine/): Per-agent Plan / Execute / Review loop, sub-agents, colleague-surface tools, per-phase LLM models
- [Code Sandbox](https://docs.crewlet.ai/concepts/code-sandbox/): Sandboxed coding-agent execution: the `run_sandbox` tool, E2B cloud/self-hosted, Claude Code & OpenCode runners, git-auth recipes, mid-run clarifications
- [Tool Skills](https://docs.crewlet.ai/concepts/tool-skills/): Knowledge-base-sourced prompt fragments (Confluence or Plane pages) that teach agents *how to use* each tool / MCP server
- [Tool Capabilities](https://docs.crewlet.ai/concepts/tool-capabilities/): How the engine stays tool-stack agnostic: capability prose + MCP annotations, no hardcoded tool names
- [Event System](https://docs.crewlet.ai/concepts/event-system/): EventQueue, topics, routing, inbox batching, distributed tracing
- [Task Engine](https://docs.crewlet.ai/concepts/task-engine/): ExecutionTracker, external PM tool integration
- [Scheduling](https://docs.crewlet.ai/concepts/scheduling/): Role/unit-scoped cron-style recurring work (standups, audits, nightly jobs)
- [Knowledge System](https://docs.crewlet.ai/concepts/knowledge-system/): Query-time knowledge-base search behind the `KnowledgeSearcher` seam (Confluence CQL or Plane page search — one backend per org) + private `agent_diary`
- [Agent Learning](https://docs.crewlet.ai/concepts/agent-learning/): Reflection loop, skill induction, episodic memory, counterparty profiles
- [One-on-Ones](https://docs.crewlet.ai/concepts/one-on-ones/): Manager↔report coaching as a usage pattern over the scheduler + A2A bus + learning loop
- [Decision Framework](https://docs.crewlet.ai/concepts/decision-framework/): DACI model for multi-agent decisions

## Integrations

- [Plane](https://docs.crewlet.ai/integrations/plane/): Self-hosted tracker **and** knowledge backend in one product: webhook routing, per-role MCP tools, knowledge search, `crewlet plane import`, tool-skill sync, skill promotion, `crewlet plane provision`, and a complete local docker-compose loop
- [Jira](https://docs.crewlet.ai/integrations/jira/): Webhooks (Forge app for Cloud, direct for Data Center), MCP tools, per-team projects
- [Confluence](https://docs.crewlet.ai/integrations/confluence/): Webhooks, MCP tools, query-time CQL knowledge search, `crewlet confluence import`
- [GitLab](https://docs.crewlet.ai/integrations/gitlab/): gitlab.com or self-hosted: API-provisioned per-agent service accounts, `crewlet gitlab provision`, webhook routing, per-role MCP tools, sandbox code authoring
- [GitHub](https://docs.crewlet.ai/integrations/github/): Per-role remote MCP tools for read/review/track; sandbox code authoring
- [Slack](https://docs.crewlet.ai/integrations/slack/): One-app-per-agent setup with automated app provisioning via `crewlet slack provision` (App Manifest APIs), thread routing, and the per-phase working indicator
- [Custom Transports](https://docs.crewlet.ai/integrations/custom-transports/): Build your own notification transport

## Guides

- [Tools & MCP](https://docs.crewlet.ai/guides/tools-and-mcp/): Built-in tools, MCP integration, tool registry
- [Extensions](https://docs.crewlet.ai/guides/extensions/): Extension system, hooks, writing extensions
- [Deployment](https://docs.crewlet.ai/guides/deployment/): Docker, Pulsar sizing & auth, TimescaleDB observability, tracing
- [Configure via API](https://docs.crewlet.ai/guides/configure-via-api/): End-to-end curl recipes for bootstrapping a company through `/config/*`

## Reference

- [CLI](https://docs.crewlet.ai/reference/cli/): Command reference
- [API Endpoints](https://docs.crewlet.ai/reference/api-endpoints/): REST API routes and schemas
- [Dashboard Design System](https://docs.crewlet.ai/reference/dashboard-design/): The dashboard's visual system: tokens, the shared panel recipe, the validated categorical hues, and the rules a change has to keep
- [Environment Variables](https://docs.crewlet.ai/reference/environment-variables/): All configuration env vars
- [Design Decisions](https://docs.crewlet.ai/reference/design-decisions/): Why certain architectural choices were made

## Optional

- [Full documentation text](https://docs.crewlet.ai/llms-full.txt): every page above in one file
- [Product site](https://crewlet.com/): what Crewlet is, with its own llms.txt
- [Source repository](https://github.com/crewlet/crewlet): the engine, MIT licensed