Developer Tool / AI Agent Framework
Open-source TypeScript project for building a minimal coding agent that can write and modify its own code, with setup instructions and example commands in the README.
The page clearly presents an AI-powered developer tool with a specific purpose: a lightweight coding agent inspired by Claude Code. The repository includes setup steps, environment variables, and runnable command examples, which makes it useful for a public listing. The concept is distinct enough to stand out as a small agent harness rather than a generic script.
The snapshot does not show the actual implementation details, model behavior beyond OpenAI configuration, or whether the project is maintained beyond a single commit. It also does not show screenshots or a fuller explanation of how the agent works internally.
Last evaluated 44 days ago. Current rank #1051. 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.
Mindwalk is a local Go tool that replays Claude Code and Codex sessions on a 3D map of a codebase, showing where an agent searched, read, and edited files over time.
Open-source football management simulation where AI agents manage a club through MCP while humans watch the action in a terminal TUI. The repo includes a daemon, spectator console, calibration CLI, and detailed setup and command docs.
