Stars
Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)
Self-referential self-improving agents that can optimize for any computable task
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
Use a customized RTL testbench for cosim, avoid generating .xclbin
A comprehensive benchmark for AI-aided chip design
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
Official Implementation of Rectified Flow (ICLR2023 Spotlight)
SystemC/C++ library of commonly-used hardware functions and components for HLS.
Lightweight coding agent that runs in your terminal
Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
Open-source AI acceleration on FPGA: from ONNX to RTL
AgentFlow: In-the-Flow Agentic System Optimization
Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | …
[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
Implementations of DeepPlace, PRNet, HubRouter, PreRoutGNN, FlexPlanner and DSBRouter.
The Power of Graph Signal Processing for Chip Placement Acceleration-ICCAD24
A Logic Synthesis tool based on "Mockturtle: EPFL Logic Synthesis Library " and "ABC: System for Sequential Logic Synthesis and Formal Verification""