Q-learning memory for Claude Code. Persistent memory that learns which context helps you get work done. Memories that lead to productive sessions (commits, PRs, tests)
earn higher retrieval rank automatically. 16 MCP tools, hybrid BM25 + vector + Q-value scoring, local-first with Qdrant + FastEmbed.
Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.
Integrates the Qwen3-Coder 30B parameter model with Claude Code through 5 specialized tools for code review, explanation, generation, bug fixing, and optimization. Optimized for 64GB RAM systems with advanced performance settings including flash attention and parallel processing.
An autonomous software-engineering pipeline for Claude Code that runs on real evidence: codebase intelligence tools, git analytics, deterministic verification rules, and zero LLM-judges-LLM. Every claim traces to a paper and every PR passes its own gates.
Semantic vector DB as an MCP server for Claude Code — SQLite + FTS5 + local ONNX embeddings. Gives Claude persistent, searchable project knowledge across conversations.
