# RuMemory/maxgraph

> A self-hosted MCP server that gives AI agents persistent project memory: decisions, bugs and open tasks stored locally as a knowledge graph with hybrid semantic search. Connects to Claude, Cursor, VS Code, DeepSeek and any MCP or REST client.

- Magnitude: 0.1 out of 10 — Quiet
- Stars: 3 total · +0 stars measured 2026-10-25, 12:24–15:19 UTC, ≈ 0 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · Created: 2026-10-12 · Last push: 2026-10-25
- GitHub: https://github.com/RuMemory/maxgraph · Homepage: https://rezon-ai.ru · Page: https://gitnova.dev/en/r/RuMemory/maxgraph

## Useful for

- Connect MaxGraph to Claude Code so each session starts with a project summary
- Search past bug fixes and decisions by meaning instead of exact keywords
- Keep separate memory for work code, personal notes and freelance projects

## Why it’s here

- Star-counter measurements on 2026-10-25 (UTC), 12:24–15:19: 3 → 3 stars (+0). This is the change over that interval.
- The repository is 13 days old and already has 3 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- New listing on glama.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1
- Issues and pull requests: 1
- Watchers: 0
- Average over the last week: 0 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0
- Latest release: v1.9.9 (2026-10-25)

## Stars per day, last 14 days (oldest → newest, today is partial)

2026-10-12 … 2026-10-25: 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0

## Spotted in now

- New listing on glama

## More in this category

1. **makecindy/cindy** — 8.0 · Breakout · AI agents · TypeScript · +481 stars measured 2026-10-25, 00:10–15:09 UTC, ≈ 736 by evening
   Cindy is an open-source AI agent that combines multiple harnesses (Claude Code, Codex), models and tools into one agent working locally with your real files and apps. This repo is the client: Electron desktop and Expo/React Native mobile…
   Full card: https://gitnova.dev/en/r/makecindy/cindy.md
2. **google-gemini/gemini-cli** — 7.3 · Breakout · AI agents · TypeScript · +329 stars measured 2026-10-25, 00:09–15:09 UTC, ≈ 538 by evening
   Google's open-source AI agent that runs Gemini directly in the terminal: understands and edits code, answers questions about a repository and automates tasks. Supports MCP servers and a non-interactive mode for scripts.
   Full card: https://gitnova.dev/en/r/google-gemini/gemini-cli.md
3. **morganlinton/BeautifulRust** — 6.9 · Early signal · AI agents · Rust · +260 stars measured 2026-10-25, 00:12–15:10 UTC, ≈ 394 by evening
   A Claude Code plugin with a rust-best-practices skill that teaches Claude to write idiomatic, robust Rust. The skill loads automatically whenever a task involves Rust, cargo, crates, the borrow checker, clippy, or .rs files.
   Full card: https://gitnova.dev/en/r/morganlinton/BeautifulRust.md
4. **JoasASantos/REA-Prompts** — 6.6 · Peaking · AI agents · +252 stars measured 2026-10-25, 00:10–15:10 UTC, ≈ 395 by evening
   A curated collection of prompts for using REA (Reverse Engineer Anything) with AI coding agents to inspect binaries, firmware, kernels, games, APKs, Electron apps and websites. Covers installation, feature tracing, cloning, vulnerability…
   Full card: https://gitnova.dev/en/r/JoasASantos/REA-Prompts.md
5. **aws/agent-toolkit-for-aws** — 6.1 · Breakout · AI agents · Python · +136 stars measured 2026-10-25, 00:10–15:09 UTC, ≈ 218 by evening
   Official AWS-supported set of MCP servers, skills, and plugins that give AI coding agents the tools and knowledge to work with AWS services. Supports Claude Code, Codex, Cursor, Kiro, and fx.
   Full card: https://gitnova.dev/en/r/aws/agent-toolkit-for-aws.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-25 15:20 UTC, updated every 30 minutes.