Junto Memory

MCP Shared Memory Server (`junto-memory`)

[](https://github.com/tlemmons/junto-memory/actions/workflows/ci.yml) [](https://opensource.org/licenses/MIT)   

The **memory** component of the **[Junto](https://github.com/tlemmons/junto-stack)** multi-agent coordination system. For a working stack with docker-compose + adopter walkthrough, start at [`junto-stack`](https://github.com/tlemmons/junto-stack).

**A shared memory and coordination server for multiple AI coding agents, built on the Model Context Protocol (MCP).**

When you run multiple AI agents on the same codebase, three things break fast:

1. They forget everything between sessions. Agent parks, knowledge dies. The next agent re-reads the same code, re-discovers the same bugs, re-learns the same gotchas.
2. They step on each other. Two agents modify the same file. Nobody knows what anyone else is doing or has locked.
3. They get dumber as sessions get long. Research calls this "context rot" — model performance degrades as the context window fills up, even well below capacity. Longer sessions don't mean better work.

This server fixes all three. It gives your agents a shared brain that persists across sessions, coordinates work across agents, and lets them record what they learn so the next agent starts where the last one left off.

**Battle-tested.** This has been running in production coordinating 6 specialized agents across 500+ sessions on a commercial IoT platform — C#/.NET server, Python on Raspberry Pi, .NET MAUI mobile, MQTT, Redis, the works. The problems it solves were discovered the hard way.

---

What It Does

• **Persistent knowled