Agents, MCPs, skills, and plugins worth running, curated daily. Test-drive anything without wrecking your setup.
Tools grouped by the job they do. Pick one to see it on the board.
1,316 tools, fastest-growing first
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, i...
Turn any workflow into reusable AI agent skills that install on 17 platforms — Claude Code, Copilot, Cursor, Windsurf...
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST...
Multi-device terminal server for AI coding agents. Server-side VTE, session persistence, file browser, web preview, p...
Quality gate for Agent Skills: lint, security audit, and Claude/Cursor/Codex/OpenCode compatibility.
Run multiple account profiles for AI coding tools simultaneously instead of switching accounts.
Codex Runway 是一个原生 macOS 状态栏应用,帮你在菜单栏查看 Codex 与 Grok 额度,并提供 Codex 的今日是否重置、reset credits、API 等价成本与本机会话能力,以及两个供应商各自独立的多...
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dict...
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local in...
OpenAI-compatible proxy that stacks the free tiers of 28 LLM providers (~4B tokens/month) behind one /v1 endpoint — p...
14MB foundation model for tiny devices; phones, wearables, smart home, and robots.
Open source inference server that runs the best local models for your hardware, plugged into the agent you already us...
All you need. Nothing you don't. Open source project management that works for you, not against you.
21 Lessons, Get Started Building with Generative AI
like netcat, but over Tailscale's data plane, without Tailscale's control plane
Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endp...
Why is this running? Trace any process, port, container, or file back to what started it - CLI + TUI.