Lists (11)
Stars
Companion code for the global workspace interpretability paper
Enterprise-grade Private Model-as-a-Service Platform
Training Sparse Autoencoders on Language Models
A universal phone recognizer that can transcribe speech in 70+ languages into IPA
Interactive live visualizer for gepa runs
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Review-first terminal diff viewer for agentic coders
A local markdown preview server. npx mdts — and you're done.
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
Reusable CVPR 2026 poster planning skill for Codex and Claude Code.
Open-source framework for the research and development of foundation models.
Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
Gym-Anything: Turn any Software into an Agent Environment
"what, how, where, and how well? a survey on test-time scaling in large language models" repository
[AAAI 2026] Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".
ICLR 2026 - official implementation for "MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval"
The Munich Open-Source Large-Scale Multimedia Feature Extractor
Textbook on reinforcement learning from human feedback
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more