mimirs
Active·★ 17·Apache-2.0·Updated 2026-05-28
★ Trending★ RAG / Knowledge Base★ Memory & Context
Local MCP server that gives AI coding agents persistent, searchable memory of your codebase
Mímirs provides persistent project memory for AI coding agents, reducing token consumption and context overhead through local indexing, semantic search, cross-session memory, and dependency graphs. It works with multiple editors and is privacy-preserving with no cloud dependencies. The tool achieves 90-98% recall@10 on real codebases.
#ai-coding#claude-code#code-search#llm-tools#mcp#mcp-server#mcp-servers#rag
01
Features
01Semantic Search with hybrid retrieval (vector + BM25)
02Auto-generated Wiki from indexed code and documentation
03Cross-session Memory with conversation tailing and checkpoints
04Dependency Graphs built from AST import/export analysis
05Annotations attached to files or symbols surfaced in search results
02
Compatibility
Claude Code
Claude Code
Verified via docs
Cursor
Cursor
Verified via docs
Windsurf
Windsurf
Verified via docs
JetBrains (Junie)
JetBrains (Junie)
Verified via docs
GitHub Copilot
GitHub Copilot
Verified via docs
03
Quick start
1
$ brew install sqlite
2
$ bunx mimirs init --ide claude
04
Use cases
↳Reduce token consumption and latency in AI coding sessions
↳Enable agents to maintain context across multiple sessions
↳Improve code search accuracy with AST-aware chunking and hybrid retrieval
05
Alternatives
Brave Search MCP★ 86.5k
Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.
FunASR★ 16.6k
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
context-mode★ 16.0k
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms
Related searches
Comments
Log in to leave a comment
- Kai ChenApr 28, 2026
Local persistence means memory stays with you, not in a cloud service.
- Marlowe LeeApr 24, 2026
Good for developers who want their AI to remember what was worked on previously.
- EEllis LeeMar 4, 2026
Search across past work surfaces relevant context without manual organization.
- CCorey JohnsonFeb 27, 2026
Local MCP server giving AI coding agents persistent, searchable memory of your work.