Developer Tool / AI-assisted Hardware Design / EDA
AutoGPU is an open-source project for using AI agents to design and harden a GPU-like chip end to end, from Verilog through synthesis and place-and-route to GDSII. The repo shows a concrete fp8 matmul accelerator flow, quick-start steps, and documentation for running the design/hardening process.
The snapshot clearly describes an AI-powered development project with a real, technical workflow: agents edit Markdown-defined procedures, generate RTL, run hardening, check DRC/LVS/timing, and produce GDSII artifacts. The README includes purpose, architecture context, quick-start commands, and evidence of working outputs and tests, which is enough for a useful public listing.
The crawl does not show the deeper docs or code needed to verify how reproducible the flow is for a newcomer, and it is still unclear how much of the chip is fully sign-off clean versus work in progress. The page also does not surface licensing, release status, or screenshots of the viewer in the snapshot.
Last evaluated 10 days ago. Current rank #284. Down 6 spots in the rankings.
WebLLM is a high-performance in-browser LLM inference engine that runs locally in the browser with WebGPU acceleration. It exposes an OpenAI-compatible API, supports streaming and JSON mode, and includes examples for building chat apps and browser extensions.
Self-hosted observability and control plane for production and coding AI agents, with live timelines, fleet-wide feeds, token budgets, MCP allow/block rules, and support for Claude Code plus a Python sensor.
Browser extension that scans pastes for credentials and PII before they reach LLM chat sites, with local on-device inference and no network calls.
Open-source runtime for multi-agent AI systems with job scheduling, DAG orchestration, shared memory, tool execution, and real-time observability.
