agent-run
Agent-run – Run a coding agent in a sandboxed environment
开源项目、精巧工具,还有让人眼前一亮的点子。
从 Hacker News 社区讨论中,找到你的下一份灵感。
Agent-run – Run a coding agent in a sandboxed environment
Open-plan-annotator – local annotation UI for working with agent plans
LX Coreutils – 72 Unix tools that pipe together, each backed by an LLM
Turo – An Aggressive Token-Saving Proxy for CLI AI Agents
A prompt to make LLMs write property-based tests
OpenTakeoff – open-source construction takeoff your AI agent can drive
Magpie, a CLI to Turn Your AI Agent into a Bookkeeper
Reproducibility Benchmark a Risk Quantitative Model
Effort Router: Intelligent /effort selection per Claude turn
Senbonzakura – remove the safety guardrails from open AI models
Goldseam – heal broken Cypress selectors with a local LLM
Bullshit Detector – agent skills that fact-check videos and articles
Maybe AI agents shouldn't decide what's sensitive
Yogen – 500 AI agents argue about your idea before you bet on it
Soup – organize and route Agent Skills into your LLM prompts
Clay Seal Identity – Agents need accountability
A monorepo where AI agents can safely build and maintain applications
Claude-teleport, move your Claude Code history between machines