A lightweight, lightning-fast, in-process vector database

TinyClaw is a team of personal agents that collaborate with each other

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

The Z3 Theorem Prover

Run MCP stdio servers over SSE and SSE over stdio. AI gateway.

Google's Operations Research tools:

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

Bash is all You need - Write a nano Claude-Code-like Agent 0 - 1

These are commands I use with agents, mostly Claude

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

Undetected version of the Playwright testing and automation library.

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Lightweight coding agent that runs in your terminal

Ask the oracle when you're stuck. Invoke GPT-5 Pro with a custom context and files.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

SkyRL: A Modular Full-stack RL Library for LLMs

A calm, CLI-native way to semantically grep everything, like code, images, pdfs and more.

Fly through your shell history. Great Scott!

🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open source models, works offline, fast and accurate.

Minimal CLI coding agent by Mistral

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

Harbor is a framework for running agent evaluations and creating and using RL environments.

A simple, easy-to-hack GraphRAG implementation

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…

MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 80.8% Avg@8 score on the challenging GAIA benchmark.

MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23