Developer Tool / AI Coding
An open-source multi-agent coding framework that uses a commit-bound project graph to scope worker tasks, replay failed runs, and merge accepted diffs through ordered Git reconciliation.
The page clearly describes an AI-powered developer tool with a specific workflow for coordinating coding agents. It explains the core idea, how workers are scoped, how replay works, and how the demo can be run with Claude Code, Codex, or scripted workers. That gives enough evidence for a useful public listing.
The snapshot is strong on the architecture story, but it does not show installation steps, API usage, screenshots, licensing, or release/activity details. A visitor still cannot tell how polished or easy the project is to adopt from this page alone.
Last evaluated 24 days ago. Current rank #625. Holding steady 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.
