# MemClaw Documentation

MemClaw gives AI agent fleets persistent, governed, shared memory. This is a flat index of all documentation pages, intended for AI agents. For full body content concatenated, fetch /llms-full.txt.

## If you are an LLM agent with memclaw_* tools

Fetch [https://memclaw.net/docs/agents.md](https://memclaw.net/docs/agents.md) for the canonical skill (the prompt to follow). The HTML form at /docs/agents adds explanatory chrome; the .md form is the raw content. Call `memclaw_keystones` once at session start before any other action.

## Pages

- [For Agents](https://memclaw.net/docs/agents): The MemClaw skill — the canonical prompt LLM agents follow when they have memclaw_* tools. Fetch the plain Markdown at /docs/agents.md.
- [MemClaw Documentation](https://memclaw.net/docs): Persistent, governed memory for AI agent fleets. Start here to install MemClaw, learn the concepts, and connect your agents.
- [Skills](https://memclaw.net/docs/skills): Publish a proven workflow to the tenant skills catalog so other agents discover it via semantic search.
- [List Document Collections](https://memclaw.net/docs/api-reference/documents-collections): GET /api/v1/documents/collections — list document collections in a tenant (added in PR
- [Search Documents](https://memclaw.net/docs/api-reference/documents-search): POST /api/v1/documents/search — semantic + keyword search across stored documents (added in PR
- [Health](https://memclaw.net/docs/api-reference/health): GET /api/v1/health — liveness probe.
- [API Reference](https://memclaw.net/docs/api-reference): Auto-generated REST reference, sourced from the FastAPI OpenAPI spec.
- [Keystones](https://memclaw.net/docs/api-reference/keystones): GET / POST / DELETE /api/v1/memclaw/keystones — mandatory governance rules.
- [Recall](https://memclaw.net/docs/api-reference/recall): POST /api/v1/recall — hybrid vector + keyword + entity search.
- [Stats](https://memclaw.net/docs/api-reference/stats): GET /api/v1/memories/stats — aggregate counts (PR
- [Write a memory](https://memclaw.net/docs/api-reference/write): POST /api/v1/memories — persist content for later recall.
- [Architecture](https://memclaw.net/docs/concepts/architecture): The services that make up MemClaw, what each one is responsible for, and how a write flows from client through core-api, the event bus, the worker, and storage.
- [Cross-tenant credentials](https://memclaw.net/docs/concepts/cross-tenant-credentials): Read across every tenant in your org with a single credential — for admin agents, analytics, and rollups.
- [Governance](https://memclaw.net/docs/concepts/governance): Keystones, trust enforcement, the Karpathy Loop, and the Memory Crystallizer.
- [Keystones](https://memclaw.net/docs/concepts/keystones): MANDATORY governance rules that agents MUST obey. Scope-merged, weight-ordered, fetched deterministically — not via semantic recall.
- [Memory Pipeline](https://memclaw.net/docs/concepts/memory-pipeline): What happens between calling memclaw_write and the memory becoming recallable.
- [Trust Levels](https://memclaw.net/docs/concepts/trust-levels): The 4-tier agent permission scheme — what each level can read and write.
- [Delete your organization](https://memclaw.net/docs/getting-started/delete-organization): How to permanently delete a MemClaw organization, what gets destroyed, and when (and how) you can still recover.
- [Your First Memory](https://memclaw.net/docs/getting-started/first-write): Write a memory and recall it — the smallest end-to-end flow.
- [Enterprise — SaaS](https://memclaw.net/docs/getting-started/managed): The hosted MemClaw Enterprise deployment at memclaw.net. Caura runs the database, API, and worker for you.
- [On-Prem Enterprise](https://memclaw.net/docs/getting-started/on-prem): MemClaw Enterprise on a customer-managed VM — connected or fully air-gapped — with a license-gated Docker Compose stack.
- [Quickstart](https://memclaw.net/docs/getting-started/quickstart): Connect any AI agent to MemClaw in five minutes — pick managed, self-hosted, or REST.
- [OSS](https://memclaw.net/docs/getting-started/self-host): Run the open-source MemClaw on your own infrastructure with Docker. Apache 2.0.
- [The Broker Fleet Screen](https://memclaw.net/docs/broker-fleet/dashboard): A field guide to every column, status, panel, and action on the dashboard's Broker Fleet screen — installs, statuses, fleet policy, commands, the reported-agents panel, and revoke.
- [How Onboarding Works](https://memclaw.net/docs/broker-fleet/how-it-works): The credential model behind broker onboarding — the register-only join key vs the per-machine install credential, how fleets bind, single-use vs reusable keys, where credentials live, the write-ownership boundary, and the security properties. Read this to plan a fleet rollout.
- [Broker Fleet](https://memclaw.net/docs/broker-fleet): What the MemClaw broker is, how personal and fleet mode differ, and how a fleet of brokers is governed from the dashboard.
- [Onboarding a Broker](https://memclaw.net/docs/broker-fleet/onboarding): Install and join a new broker to your fleet with one command — what to run on macOS, Linux, and Windows, what each step does, and how to verify it worked.
- [Authoring skills](https://memclaw.net/docs/skill-factory/authoring): Write a skill directly via memclaw_doc — the required fields, the slug and size rules, create vs update with hash-binding, and how a write is validated and staged.
- [Delivery](https://memclaw.net/docs/skill-factory/delivery): How an active skill actually reaches an agent — the MCP pull tier, the OpenClaw push tier, the active-only gate on both, and how the bundled usage skill differs.
- [Forge](https://memclaw.net/docs/skill-factory/forge): The server-side resident that mines fleet behavior into skill candidates — how it runs, how operators trigger and observe it, and the knobs that tune it.
- [Skill Factory](https://memclaw.net/docs/skill-factory): How MemClaw turns proven fleet behavior into governed, delivered SKILL.md skills — authored by agents or distilled by Forge, gated through a lifecycle, and pushed to the harnesses that run your agents.
- [Lifecycle & governance](https://memclaw.net/docs/skill-factory/lifecycle): The skill status model, who can set each status, the six auto-promotion gates, the Sentinel security scan, and the Skills Inbox review flow.
- [OpenClaw plugin delivery](https://memclaw.net/docs/skill-factory/openclaw-plugin): How the OpenClaw plugin's reconciler pushes active skills onto a node — managed vs shared target dirs, the ownership marker, registering on the load path, and per-node observability.
- [Reference](https://memclaw.net/docs/skill-factory/reference): One-page reference for Skill Factory — config keys, statuses, auto-gates, endpoints, the skill schema, and the plugin target env var.
- [Skills Inbox](https://memclaw.net/docs/skill-factory/skills-inbox): The human-in-the-loop review queue for staged skills — the card an operator sees, the five actions, and how to recover a quarantined skill.
- [Build an agent fleet on MemClaw Cloud](https://memclaw.net/docs/tutorials/cloud-fleet): The managed (Cloud) tutorial — a self-contained, end-to-end build. Wire a governed three-agent fleet to memclaw.net: sign up, connect Claude Code, and watch shared memory compound, with just an API key.
- [Content Policy: PII screening & the business-vs-personal gate](https://memclaw.net/docs/tutorials/content-policy-setup): Configure the dashboard's Content Policy tab — screen every write for PII, PCI & secrets, and keep personal content out of the shared corporate graph.
- [Your first memories on MemClaw Cloud](https://memclaw.net/docs/tutorials/first-memories): The five-minute Cloud starter — sign up, mint a key, write three memories, recall them with completely different words, and see them in Prism.
- [Governed memory: scopes, trust tiers & keystone policies](https://memclaw.net/docs/tutorials/governance-keystones): Who sees what, who can change the fleet's knowledge, and what every agent must obey — visibility scopes, trust tiers, and keystone policies.
- [Tutorials](https://memclaw.net/docs/tutorials): Hands-on tutorials for building governed, shared, self-improving memory for AI agent fleets — on managed MemClaw Cloud or self-hosted OSS.
- [The Karpathy Loop: memory that learns from outcomes](https://memclaw.net/docs/tutorials/karpathy-loop): Make shared memory improve with use — report outcomes, reinforce what works, auto-generate rules from failures, and tune retrieval per agent.
- [The knowledge graph: entities, relations & graph-boosted recall](https://memclaw.net/docs/tutorials/knowledge-graph): The graph view from Part 2 wasn't decoration — it's the substrate MemClaw builds on every write, and the reason recall finds memories you never lexically matched. Entity extraction, synonym resolution, evidence-carrying relations, and the graph-expansion search blend.
- [The Memory Dashboard: a browsable window into your fleet's mind](https://memclaw.net/docs/tutorials/memory-dashboard): See, search, and govern your fleet's shared memory — from one HTML file and a reverse proxy.
- [Memory hygiene at scale: contradictions, supersession & the crystallizer](https://memclaw.net/docs/tutorials/memory-hygiene): What keeps a fleet's shared memory from rotting at scale — automatic contradiction detection and supersession, an 8-state lifecycle, the crystallizer hygiene scan, and memclaw_insights.
- [Building a Multi-Agent Fleet with MemClaw and Claude Code](https://memclaw.net/docs/tutorials/multi-agent-fleet): Give three agents one shared, governed brain — in about 30 minutes, with zero custom code.
- [AutoGen](https://memclaw.net/docs/integrations/autogen): Give a Microsoft AutoGen agent persistent, governed memory with MemClaw over MCP.
- [Claude Code](https://memclaw.net/docs/integrations/claude-code): Wire MemClaw into Anthropic's Claude Code CLI.
- [Claude Desktop](https://memclaw.net/docs/integrations/claude-desktop): Add MemClaw as an MCP server in Claude Desktop.
- [CrewAI](https://memclaw.net/docs/integrations/crewai): Give a CrewAI agent persistent, governed memory with MemClaw over MCP.
- [Cursor](https://memclaw.net/docs/integrations/cursor): Wire MemClaw into Cursor's MCP support.
- [LangChain](https://memclaw.net/docs/integrations/langchain): Give a LangChain or LangGraph agent persistent, governed memory with MemClaw — over MCP or the REST API.
- [LlamaIndex](https://memclaw.net/docs/integrations/llamaindex): Give a LlamaIndex agent persistent, governed memory with MemClaw over MCP.
- [Generic MCP](https://memclaw.net/docs/integrations/mcp): Connect any MCP-compatible client (Windsurf, Cline, Continue, JetBrains MCP, …) to MemClaw.
- [OpenAI Agents SDK](https://memclaw.net/docs/integrations/openai-agents): Give an OpenAI Agents SDK agent persistent, governed memory with MemClaw over MCP.
- [OpenClaw](https://memclaw.net/docs/integrations/openclaw): Drop MemClaw into an OpenClaw gateway and every agent in the fleet inherits shared memory.
- [Per-agent keys (no plugin)](https://memclaw.net/docs/integrations/per-agent-keys): Bootstrap a long-lived integration without the OpenClaw plugin — provision an agent-scoped credential, identify, and call MCP.
- [REST](https://memclaw.net/docs/integrations/rest): Hit MemClaw directly from any language. No SDK required.
- [Operational Commands](https://memclaw.net/docs/reference/cli): Common commands for self-hosted MemClaw. Defers to the OSS scripts/ directory for the canonical list.
- [Environment Variables](https://memclaw.net/docs/reference/env-vars): The authoritative list lives in the OSS .env.example. Highlights below.
- [Errors and Status Codes](https://memclaw.net/docs/reference/errors): The canonical error envelope shared by REST and MCP, plus the HTTP status → code mapping.