Architecture 2.0 public materials, including the synthesis lecture and preview site.

PicoRV32 - A Size-Optimized RISC-V CPU

Agent skill that removes signs of AI-generated writing from text

Personal AI, On Personal Devices

AXI SystemVerilog synthesizable IP modules and verification infrastructure for high-performance on-chip communication

Multiplayer agent harness for work.

Pluto: A Benchmark for Evaluating Efficiency of LLM-generated Hardware Code

Lightpanda: the headless browser designed for AI and automation

The CORE-V CVA6 is a highly configurable, 6-stage RISC-V core for both application and embedded applications. Application class configurations are capable of booting Linux.

Domain-agnostic multi-agent software design and evolution harness

Framework for specifying and proving properties—such as robustness, fairness, and interpretability—of machine learning models using Lean 4.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

Dafny is a verification-aware programming language

Digital Design Equivalence Checking

Designing Full Chip from IEEE Paper using AI in SKY130

Evidence profiles for AI-generated RTL that expose what functional benchmarks miss. Seeking collaborators, design partners, and validation

Open-source implementation of AlphaEvolve