Recall MCP server

<!-- @wbx-modified copilot-a3f7 | 2026-04-30 01:30 MTN | v0.5.5-readme | add mcp-name marker for MCP Registry namespace verify | prev: copilot-a3f7@2026-04-30 03:25 MTN --> <!-- mcp-name: io.github.RecallWorks/recall -->

Recall&trade;

A better memory server for AI agents — works for one, scales to many. Local, free, zero-config, MCP-native. Your data stays on your machine.

Quickstart · vs. mem0/Letta/Zep · Multi-agent · Recall Pro → · Book a demo

Without a memory server, every Claude / Copilot / Cursor conversation

starts cold. You re-explain the codebase, the conventions, the

decisions, the gotchas — every time. Recall fixes that.

Start here: what Recall does for one developer, one AI

Install it once, point your MCP client at it, and your AI now:

flow last week?" returns the actual decision, not a hallucination

• Remembers across sessions — "what did we decide about the auth

semantic RAG over your repo

• Indexes your code and docs — index_file + recall = local

the chunks it pulled from

• Cites where the answer came from — answer returns text plus

anti_pattern becomes searchable later

• Builds project knowledge — every checkpoint, reflect, and

rebuildable from them

• Survives restarts — append-only artifacts on disk, vector store

One pip install, one config block, done. No API key. No external service. No per-token bill. MIT license. This is what 95% of users will ever use Recall for.

How is this different from mem0 / Letta / Zep?

Recall does the same job they do — persistent memory across AI sessions, semantic recall, "remember what the user said last week." The difference is where and how:

If you're happy paying a hosted memory provider per token, those are great products and you don't need Recall. If you'd rather your AI's memory live on your laptop or your own server, free and offline, that's what Recall is for.

Scaling up: coordination when you run more than one agent

Shortened. The full README is on GitHub.