#retrieval

Embedded retrieval library built on Parquet. Fast, efficient, and scalable.

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

Ridiculous speed. Readable code.

The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.

Rust Agent Development Kit (ADK-Rust): Build AI agents in Rust with modular components for models, tools, memory, realtime voice, and more. ADK-Rust is a flexible framework for developing AI agents with simplicity and power. Model-agnostic, deployment-agnostic, optimized for frontier AI models. Includes support for real-time voice agents.

The Official Exa Javascript SDK

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

Rust library for generating vector embeddings and reranking locally!

Real-time monitoring, slowlog analysis, and audit trails for Valkey and Redis

Open-source context retrieval layer for AI agents

Local-first MCP server providing Pipecat docs, examples, and API context for AI coding agents

Fast, pure-Python full-text indexing and search. Actively maintained continuation of Whoosh / whoosh-reloaded. Install: pip install whoosh3

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Run AI models on Apple Silicon and Raspberry Pi

The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a search engine you can talk to, with cited answers from your files, code, and the web. MCP server for coding agents, web crawler, TUI, CLI, REST API, Python library. No Ollama or LM Studio needed, works with both.

Up to 100x faster strings for C, C++, CUDA, Python, Rust, Swift, JS, & Go, leveraging NEON, AVX2, AVX-512, SVE, GPGPU, & SWAR to accelerate search, hashing, sorting, edit distances, sketches, and memory ops 🦖

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

Universal memory runtime for AI agents

~97% token reduction for AI coding sessions — zero deps, 33 languages, MCP server

Toolkit for testing and packaging portable AI agents across various LLMs, frameworks, and deployment targets