30 posts
Fast transcript search for humans & agents. Supports Claude Code, Codex CLI & OpenCode
Build an AI advisor SKILL from any YouTube channel — transcripts, BM25 + semantic RAG, verbatim quotes with timestamps.
MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup
Personal RAG engine — simple, fast, Rust. One binary (15 MB), one DB, native collections. MCP-native.
RAG pipeline for documents (Markdown, PDF, images). 10-step hybrid search, LLM enrichment, taxonomy, MCP server. Cloud or local.
Your AI forgets everything between sessions. This fixes that — 98%+ retrieval accuracy, 100% on LongMemEval, 99% token savings. 44 MCP tools...
A personal memory layer for your AI tools. Intelligent authoring (gap detection, self-enriching graph, session-synthesis loop) + measurably...
Fast, local semantic search over web content for AI agents. Hybrid BM25 + potion-retrieval-32M embeddings, cross-page dedup, token-budget mo...
AmanMCP is a local-first RAG MCP server for developers - providing hybrid search (BM25 + semantic) over codebases for AI assistants like Cla...
MCP server for AI memory -- hybrid search (BM25 + semantic + knowledge graph), temporal decay, local-first
Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offli...
MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.
