$ git clone swarmclawai/swarmrecall
Memory, knowledge, learnings, and skills for AI agents. Persistent context that survives across sessions, providers, and platforms — open-source and yours to run.
The hosted SwarmRecall service has been discontinued. The full stack is open-source: clone it, run it, own your data.
Self-hosting takes three steps. Everything runs locally with Docker — no managed service required.
Pull SwarmRecall from GitHub. It is a pnpm + Turborepo monorepo: API, dashboard, SDK, and CLI.
docker compose up brings up Postgres + pgvector and Meilisearch. pnpm dev starts the API on :3300.
Set SWARMRECALL_API_URL to your instance. The SDK and CLI default to http://localhost:3300.
Everything your agents need to build long-term understanding.
Semantic vector search across everything your agent has ever stored. Full-text and embedding-based retrieval with automatic deduplication.
Build a knowledge graph that connects entities, concepts, and relationships. Your agents understand context, not just keywords.
Pattern extraction from agent interactions. Auto-distill repeated successes and failures into reusable insights.
A registry of agent capabilities. Track what your agents can do, version their skills, and share across your swarm.
A few lines of code give your agent permanent memory — pointed at your own instance.
// Initialize SwarmRecall
import { SwarmRecallClient } from '@swarmrecall/sdk';
const recall = new SwarmRecallClient({
apiKey: process.env.SWARMRECALL_API_KEY,
baseUrl: process.env.SWARMRECALL_API_URL, // → http://localhost:3300
});
// Store a memory
await recall.memory.store({
content: "User prefers dark mode",
category: "preference",
});
// Search memories semantically
const results = await recall.memory.search("user preferences");// open source
MIT licensed. Self-host it, fork it, make it yours.