Lists (4)
Starred repositories
Development repository for the Triton language and compiler
SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
Proving polynomial inequalities with sum-of-squares certificates
A lightweight MCP (Model Context Protocol) server that proxies between AI agents and the Lean 4 language server.
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
World's first GPU-native CIC type checker for Lean4. 126M proofs/sec on CUDA. 89,931x faster than CPU.
A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress
A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.
AI-assisted Lean project automation with DAG blueprints, proof orchestration, and multi-agent coding/proving workflows.
A flagship 560-billion-parameter open-source MoE model that advances Native Formal Reasoning in Lean4 for Mathematics Formalization and Proving through agentic tool-integrated reasoning.
Asterinas aims to be a production-grade Linux alternative—memory safe, high-performance, and more.
Lightweight Sandbox Powered by a Purpose-Built VM and OS
OpenSeeker: A search agent with open-source data and models
Elevate your AI research writing, no more tedious polishing ✨
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
AI agents running research on single-GPU nanochat training automatically
A Lean4 script for robustly verifying submitted proofs of theorems and implementations of functions
The Cloud Sandbox Built for AI Agents