Go implementation of @qdrant/fastembed.
-
Updated
May 24, 2024 - Go
Go implementation of @qdrant/fastembed.
Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.
Structured local memory storage and retrieval for LLM agents
Local-first AI knowledge layer with vector embeddings and retrieval
Fast, local, hackable graph RAG engine in Go: hybrid dense+lexical retrieval, PageRank over a chunk+entity graph, community summaries for global queries, multimodal, single binary, local Ollama.
A retrieval engine that reasons over document structure — not embeddings. No chunking, no top-K, no vector DB.
Sovereign single-binary knowledge mesh for coding agents (MCP): index, search and serve your notes + code as context. Fair-code (no reselling).
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.
Evaluate retrieval and RAG runs with Precision@k, Recall@k, MAP, nDCG, and offline answer judges.
Distributed retrieval pipeline with schedulers, resolvers, protocol workers, retries, and result aggregation.
Local-first, state-aware memory engine for AI agents (MCP). Retrieves the right remembered episode for your current state — and shows why — instead of the closest text match. Claude Code-first. AGPL-3.0.
Production-ready recommender system suite: serving API, pipelines, algorithm SDK, and evaluation tooling.
Local-first docs retrieval for AI agents: mirror any docs corpus to Markdown, index with SQLite FTS5 (pure Go), search with optional embedding/LLM rerank, and measure quality with reproducible evals.
AI‑augmented document analysis and lightweight retrieval (Go) with OpenRouter and Ollama. Cross‑platform binaries, cost guardrails, and streaming.
Local-first runtime that compiles noisy web pages into verified high-signal context for AI agents
Add a description, image, and links to the retrieval topic page so that developers can more easily learn about it.
To associate your repository with the retrieval topic, visit your repo's landing page and select "manage topics."