Lists (1)
Stars
The first open-source agentic AI physicist, by Physical Superintelligence PBC (PSI).
Self-referential self-improving agents that can optimize for any computable task
This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"
A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse
A benchmark to measure AI progress on unsolved research problems in mathematics.
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
LabClaw – Operating Layer for LabOS (Stanford-Princeton AI Co-Scientists)
AI agents running research on single-GPU nanochat training automatically
An interface library for RL post training with environments.
AI-Driven Scientific and Algorithmic Discovery
Training neural networks on Apple Neural Engine via reverse-engineered private APIs
PreScience: A Benchmark for Forecasting Scientific Contributions
Ouroboros — self-creating AI agent. Born Feb 16, 2026.
Efficient Differentiable n-d PDE Solvers in JAX.
An open source library designed to provide community examples of Joint Embedding Predictive Architectures (JEPAs). It contains code and examples for learning representations from images, video, and…
AI agent toolkit (skills+MCP server) for Lightning Network payments. Run nodes, pay for APIs (L402), host paid endpoints, and manage credentials.
High accuracy RAG for answering questions from scientific documents with citations
ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.
A "Clawdbot" in every row with 400 lines of Postgres SQL
InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning