---
How to install caura-memclaw?
caura-ai/caura-memclaw
$git clone https://github.com/caura-ai/caura-memclawInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install caura-memclaw by running `git clone https://github.com/caura-ai/caura-memclaw`, then use it for the current task and follow its documentation at https://github.com/caura-ai/caura-memclaw.
README.md
| 1 | <p align="center"> |
| 2 | <img src="static/images/memCLAW_logo_dark.png" alt="MemClaw" width="420" /> |
| 3 | </p> |
| 4 | |
| 5 | <h3 align="center">Fleet memory for AI agents — governed, shared, self-improving.</h3> |
| 6 | |
| 7 | <p align="center"> |
| 8 | <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="License" /></a> |
| 9 | <a href="https://github.com/caura-ai/caura-memclaw/stargazers"><img src="https://img.shields.io/github/stars/caura-ai/caura-memclaw?style=social" alt="GitHub Stars" /></a> |
| 10 | <a href="https://github.com/caura-ai/caura-memclaw/actions"><img src="https://img.shields.io/github/actions/workflow/status/caura-ai/caura-memclaw/ci.yml?label=CI" alt="CI" /></a> |
| 11 | <a href="https://github.com/caura-ai/caura-memclaw/releases"><img src="https://img.shields.io/github/v/release/caura-ai/caura-memclaw" alt="Release" /></a> |
| 12 | <a href="https://discord.com/invite/aNfpgfpj"><img src="https://img.shields.io/badge/Discord-join-5865F2?logo=discord&logoColor=white" alt="Join us on Discord" /></a> |
| 13 | </p> |
| 14 | |
| 15 | <p align="center"> |
| 16 | <a href="#quick-start">Quick Start</a> · |
| 17 | <a href="#features">Features</a> · |
| 18 | <a href="#performance">Performance</a> · |
| 19 | <a href="#mcp-model-context-protocol">MCP</a> · |
| 20 | <a href="#api-reference">API Reference</a> · |
| 21 | <a href="static/docs/integration-guide.md">Plugin Docs</a> · |
| 22 | <a href="CONTRIBUTING.md">Contributing</a> · |
| 23 | <a href="https://discord.com/invite/aNfpgfpj">Discord</a> |
| 24 | </p> |
| 25 | |
| 26 | --- |
| 27 | |
| 28 | ## MemClaw — Fleet memory for AI agents |
| 29 | |
| 30 | MemClaw is open-source memory for **multi-tenant, multi-agent** AI fleets. Your agents store what they learn, find what the fleet knows, and get smarter with every interaction — learning from each other instead of repeating mistakes. |
| 31 | |
| 32 | Agents write plain text. MemClaw turns it into searchable, governed, self-improving memory. |
| 33 | |
| 34 | **One loop, three pillars: write, recall, compound** — every interaction makes the next one smarter. |
| 35 | |
| 36 | **Built for fleets, not single agents.** Public agent-memory benchmarks (LoCoMo, LongMemEval) measure one agent, one user, one long conversation — the single-chatbot shape. The deployment shape we see in production is the opposite: dozens or thousands of agents working on behalf of a company, sharing what they learn under governance. MemClaw is architected around that shape from day one — scoped memory, cross-agent outcome propagation, fleet-wide trust tiers — and competes on the axes that compound with agent count: latency, token efficiency, and governance. See [Performance](#performance) for the numbers, or read the [benchmarks write-up](https://memclaw.net/blog/memclaw-benchmarks). |
| 37 | |
| 38 | > **In production at eToro (NASDAQ: ETOR):** 300+ AI agents on one governed |
| 39 | > memory — 26,500+ memories, 1,372 shared skills, 23 ms p50 search. |
| 40 | > [Architecture deep-dive →](https://memclaw.net/blog/etoro-company-brain/) |
| 41 | |
| 42 | <p align="center"> |
| 43 | <img src="static/images/memclaw-concept.png" alt="MemClaw — Fleet Memory that Compounds" width="700" /> |
| 44 | </p> |
| 45 | |
| 46 | <p align="center"> |
| 47 | <img src="static/images/memclaw-demo.gif" alt="MemClaw demo — write, recall, and governed cross-fleet memory in action" width="700" /> |
| 48 | </p> |
| 49 | |
| 50 | --- |
| 51 | |
| 52 | ## Quick Start |
| 53 | |
| 54 | ### Try it locally — no API key, no signup |
| 55 | |
| 56 | The fastest way to see MemClaw work. Standalone mode runs single-tenant with auth bypassed — write and recall a memory in four commands. (It boots with dummy embeddings so there's nothing to configure; add an AI provider key for semantic search — see [Self-Hosted](#self-hosted-open-source) below.) |
| 57 | |
| 58 | ```bash |
| 59 | git clone https://github.com/caura-ai/caura-memclaw.git |
| 60 | cd caura-memclaw |
| 61 | cp .env.example .env && echo "IS_STANDALONE=true" >> .env # single-tenant, no API key |
| 62 | docker compose up -d # Postgres + pgvector + Redis + API (~30s) |
| 63 | |
| 64 | # Write a memory — no API key needed |
| 65 | curl -X POST http://localhost:8000/api/v1/memories \ |
| 66 | -H "X-API-Key: standalone" -H "Content-Type: application/json" \ |
| 67 | -d '{"tenant_id": "default", "content": |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
