swarmrecall

name	swarmrecall
description	Use SwarmRecall when an AI agent needs persistent memory, a knowledge graph, learnings, a skill registry, shared pools, or background dream consolidation across sessions. Works via the SwarmRecall CLI (for stdio MCP) or directly over HTTP/SDK. Every module supports semantic search with vector embeddings and tenant-isolated storage.
version	1.2.0
metadata	{"openclaw":{"requires":{"anyBins":["swarmrecall"]},"install":[{"id":"node","kind":"node","package":"@swarmrecall/cli","bins":["swarmrecall"],"label":"Install SwarmRecall CLI (npm)"}],"mcp_servers":[{"id":"swarmrecall","label":"SwarmRecall (local stdio)","command":"swarmrecall","args":["mcp"],"env":{"SWARMRECALL_API_KEY":"${env:SWARMRECALL_API_KEY}"}},{"id":"swarmrecall-remote","label":"SwarmRecall (remote HTTP)","transport":"streamable-http","url":"https://swarmrecall-api.onrender.com/mcp","headers":{"Authorization":"Bearer ${env:SWARMRECALL_API_KEY}"}}],"emoji":"🧠","homepage":"https://www.swarmrecall.ai/docs/mcp","privacyPolicy":"All data is stored on SwarmRecall servers (swarmrecall-api.onrender.com). Data is scoped per agent and owner. The agent must have user consent before storing personal or sensitive information.","dataHandling":"All data is transmitted over HTTPS. Data is stored in PostgreSQL with pgvector embeddings. Data is tenant-isolated by owner ID and agent ID across all modules.","primaryEnv":"SWARMRECALL_API_KEY"}}
author	swarmclawai
homepage	https://www.swarmrecall.ai
tags	["memory","knowledge-graph","learnings","skills","pools","dreaming","consolidation","mcp","ai-agents","persistence"]

SwarmRecall

Self-host only. The hosted SwarmRecall service has been discontinued. SwarmRecall is now open-source; run your own instance and point clients at it via SWARMRECALL_API_URL (defaults to http://localhost:3300). The onrender.com URLs below are illustrative — substitute your own host. See https://github.com/swarmclawai/swarmrecall/blob/main/docs/self-hosting.md.

Persistent memory, a knowledge graph, learnings, a skill registry, shared collaboration pools, and background "dream" consolidation — for any AI agent — via a self-hosted SwarmRecall API (default http://localhost:3300).

For onboarding, examples, command references, or troubleshooting, read the bundled README.md, examples/, references/, and TROUBLESHOOTING.md before improvising workflow advice.

Setup

Three ways to connect, in increasing order of flexibility:

1. MCP (recommended for Claude Desktop, Claude Code, Cursor)

Local stdio (default):

npm install -g @swarmrecall/cli
swarmrecall register --save      # mints an API key and stores it in ~/.config/swarmrecall/config.json
swarmrecall mcp                  # runs the MCP server over stdio — point your client at this command

Remote HTTP (no install):

URL:     ${SWARMRECALL_API_URL}/mcp   # e.g. http://localhost:3300/mcp
Auth:    Authorization: Bearer ${SWARMRECALL_API_KEY}
Transport: streamable-http

Both transports expose the same 52 tools and 4 resources. See https://www.swarmrecall.ai/docs/mcp for client-specific configuration snippets.

2. CLI

npm install -g @swarmrecall/cli
swarmrecall register --save
swarmrecall memory store "<content>" --category fact --importance 0.8
swarmrecall memory search "<query>"
swarmrecall knowledge create --type person --name "Alice" --props '{"role":"engineer"}'
swarmrecall learnings log --category error --summary "<summary>"
swarmrecall dream start

See for the full command surface.