Stars
AI-powered macOS development workspace. Git worktrees, Claude Code sessions, and dev servers in a single native app.
A TypeScript-first, Bun-native CLI framework with composable modules.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
A lightweight command-line tool that spins up a local web server to display Git commit diffs in a GitHub-like Files changed view
AI agents running research on single-GPU nanochat training automatically
Claude Code notifications without the context switch. A minimal, always-present session manager for macOS.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Fast, robust Google Flights scraper (API) for Python. (Probably)
Open source, type-safe primitives for multi-modal AI. All modelities, all providers, one interface 🌟
An agentic skills framework & software development methodology that works.
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
Official inference framework for 1-bit LLMs
Neural question generation using transformers
Laminar - open-source observability platform purpose-built for AI agents. YC S24.
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
A Tree Search Library with Flexible API for LLM Inference-Time Scaling
An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI
🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines
An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Audio synthesis, processing, & analysis platform for iOS, macOS and tvOS
A fast and light-weight multithreaded file processing library for Java.
🚀 The fast, Pythonic way to build MCP servers and clients.
A cache for AI agents to learn and replay complex behaviors.
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.