# 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.
- [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.
- [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.
- [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.
- [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.
- [Cursor](https://memclaw.net/docs/integrations/cursor): Wire MemClaw into Cursor's MCP support.
- [Generic MCP](https://memclaw.net/docs/integrations/mcp): Connect any MCP-compatible client (Windsurf, Cline, Continue, JetBrains MCP, …) to MemClaw.
- [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.