Stars
TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
📄 A curated list of awesome .cursorrules files
GPU-accelerated NeuroEvolution of Augmenting Topologies (NEAT)
Conditional compilation according to rustc compiler version
Enables cloud-based AI services to access local Stdio based MCP servers
Replace 'hub' with 'diagram' in any GitHub url to instantly visualize the codebase as an interactive diagram
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
verl: Volcano Engine Reinforcement Learning for LLMs
An analysis tool for Python that blurs the line between testing and type systems.
The official Python SDK for Model Context Protocol servers and clients
Model Context Protocol Servers
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
A Rust implementation of Glidesort, my stable adaptive quicksort/mergesort hybrid sorting algorithm.
System for collecting, deriving and working with facts about source code.
🦔 PostHog provides open-source web & product analytics, session recording, feature flagging and A/B testing that you can self-host. Get started - free.
A blazingly fast, open-source application server with type-safe APIs, built-in JS/ES6/TS runtime, realtime, auth, and admin UI built on Rust, SQLite & V8.
The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.