#retrieval

SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.

.NET library for on-demand local AI model inference — zero bundled models, lazy loading, hardware-aware GPU/CPU selection, 10 task types including embeddings, generation, vision, and audio.

Fast BM25 search in Python, powered by Numpy and Numba

Code similarity search by compression - find near-duplicate files, clone families, and where a pasted snippet came from. No embeddings, no model, no vector database.

Free local web search/extraction router for AI agents. Go CLI + MCP, BYOK/free-first routing, keyless DDGS/Scrapling fallback, setup writers and client guides.

Federated, evidence-first retrieval for personal AI agents

Production-ready .NET 10 RAG library with hybrid vector + keyword search, multi-backend storage (SQLite, PostgreSQL, Neo4j, Qdrant), and MCP server integration.

Local code search for AI agents: six fast, purpose-built tools that return ranked answers, not raw grep. Because maybe grep isn't all you need... 🍬

Typed building blocks for everything around your LLM call.

Graph memory for AI agents: facts in, entities and cause->effect relations extracted with small open models, multi-hop recall with a cited chain. Library, HTTP/MCP service, LangChain, hosted at memory.primaxiom.ai

Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under MIT license.

Evidence-first, multilingual, S3-native RAG — answers only from cited evidence (exact quote, page, bbox) and abstains when the evidence is weak, missing or conflicting. The guarantee is "no ungrounded claim". Byte-identical core across Python, Go and JavaScript. Docs: https://muthuishere.github.io/citenexus/

Standalone AI agent memory engine — hybrid search (BM25 + vectors), Q-learning scoring, Ebbinghaus decay, tiered storage, knowledge graph. Part of TRW Framework.