Awesome/awesome-mcp-servers
1
0
Fork 0
mirror of https://github.com/punkpeye/awesome-mcp-servers.git synced 2026-09-10 09:41:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add rag-kb: local-first agent memory & knowledge service

Browse Source 
Adds **rag-kb** — a local-first, completely free agent memory & knowledge service.

- Hybrid retrieval for Chinese & English: BGE-M3 dense vectors + BM25 (jieba), fused with RRF
- Local-first & offline-capable: single process, embedded ChromaDB, no external services; retrieval works with the network cut off
- Dual protocol: REST + native MCP server from the same process
- Fully functional without any LLM; optional Ollama/cloud unlocks RAG answering
- Apache-2.0, English README included

Submitted by the project author. Happy to adjust the entry if needed.
This commit is contained in:
fish827-08
2026-08-27 21:51:10 +08:00
committed by GitHub
parent a523ec62da
commit 897554b561
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1
View File
@@ -2197,6 +2197,7 @@ Connect AI agents to industrial equipment, machinery, and operational technology
Persistent memory storage using knowledge graph structures. Enables AI models to maintain and query structured information across sessions.
- [fish827-08/rag-kb](https://github.com/fish827-08/rag-kb) 🐍 🏠 🪟 - Local-first agent memory & knowledge service with hybrid retrieval (BGE-M3 dense vectors + BM25 via jieba, fused with RRF), document & webpage ingestion, and optional RAG answering via local Ollama. Single process, embedded ChromaDB, REST + native MCP server; fully functional offline without any LLM. Apache-2.0.
- [AkashGoenka/coldstart](https://github.com/AkashGoenka/coldstart) [![AkashGoenka/coldstart MCP server](https://glama.ai/mcp/servers/AkashGoenka/coldstart/badges/score.svg)](https://glama.ai/mcp/servers/AkashGoenka/coldstart) 📇 🏠 🍎 🪟 🐧 - Codebase memory for coding agents, with no embeddings and no API key. A deterministic AST index answers "which files are relevant to this task?" in milliseconds, and agents write durable notes about the repo that are content-hash checked — a note flags itself stale the moment the code it describes changes. Notes are markdown inside the repo, so they commit and review alongside your code. `npm i -g @cstart/coldstart && coldstart init`
- [jayasukuv11-beep/agenthelm](https://github.com/jayasukuv11-beep/agenthelm) [![jayasukuv11-beep/agenthelm MCP server](https://glama.ai/mcp/servers/jayasukuv11-beep/agenthelm/badges/score.svg)](https://glama.ai/mcp/servers/jayasukuv11-beep/agenthelm) 📇 🐍 ☁️ 🏠 🍎 🪟 🐧 - Shared, versioned memory and governance control plane for AI coding agents. Compiler pipeline resolves architectural decision conflicts across Claude Code, Cursor, and custom agent fleets. `npx -y agenthelm-mcp`
- [jmpdsevilla/BovedIA](https://github.com/jmpdsevilla/BovedIA) [![jmpdsevilla/BovedIA MCP server](https://glama.ai/mcp/servers/@jmpdsevilla/BovedIA/badges/score.svg)](https://glama.ai/mcp/servers/@jmpdsevilla/BovedIA) 📇 🏠 🍎 🪟 🐧 - Personal memory for Claude Code in plain Markdown notes you own. Doesn't load context blindly: a router note decides what to load and when, plus an "alma" (soul) layer for what you think and feel, not just tasks. `npx bovedia`