📡 MCP Radar

shinegang/baron

Baron Munchausen — local memory for coding agents that outlives the chat, with a verdict on every answer. Public alpha.

⭐ 13 stars
⑂ 0 forks
Python
momentum ▲ 26.0
created 2026-09-10
on radar since 2026-09-12
star trend 11 → 13 since 2026-09-12
ai-agentsclaude-codecodexcursorgroundingknowledge-graphllmmcpmcp-servermemorypython
View on GitHub ↗Homepage ↗

About baron

Baron Munchausen — local memory that outlives the chat

Everything above is a real run against a clean clone. rpc is the two-line curl wrapper defined in docs/demo/baron-demo.sh; re-record the whole thing with cd docs/demo && ./record.sh.

Public alpha (0.6.1). The engine has run daily in the authors' own work for months; this repository is one day old. The code is Apache-2.0 and complete — the packaging, the docs and the install path are what "alpha" refers to. Report anything that breaks.

Your session ends. Your project doesn't. One call brings back where the project stopped, what was decided and what comes next — after a closed tab, a spent limit or a change of model. And every answer built on that memory comes back with a verdict: grounded, partial or ungrounded, with the sentences nothing backs named one by one.

A memory server in Python 3.12 with no third-party runtime dependency. MCP over stdio for your client, JSON-RPC on 127.0.0.1:8765 for everything else. Nothing here calls a model and nothing leaves your machine. A fresh install starts with an empty graph: we ship the tools, never the data.

Three numbers, each one measured, each one with what it does not say written next to it.

1. One context return: 7 146 tokens → 2 388. The 7 146 is a real compaction summary out of a session transcript; the 2 388 is the slice a live memorygroundprepare returned for the same moment of the same project. Both counted with tiktoken/cl100kbase on 2026-09-10. What it does not say: it is one pair of instances, not a distribution — a second summary from the same corpus came to 5 91

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/shinegang--baron.html)

Related MCP servers

00200200/usagetrim

Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.

⭐ 11Python
00200200/tokencut

Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.

⭐ 10Python
replenhq/replen

Smarter AI Development Workflows

⭐ 5TypeScript
osaxyz/sepiace

Long-term memory for coding agents. The sepiace plugin for Claude Code and Codex.

⭐ 3TypeScript
jiawei686/jev-ultrafast-mcp

Hand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. Ref-based element tables, code-checked assertions, zero-model m

⭐ 18Python
KernelLord/pickysteve

Skill router and context picker for Claude Code, Cursor, and Aider. Auto-picks the right skill for every prompt, with prompt-injection filtering for MCP.

⭐ 6Python

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.