ai-agents

Kolo 是一個基於文字的 Python 除錯器，專為 AI 代理設計。可捕捉每個執行的函式呼叫、回傳值、區域變數、HTTP 請求等，並儲存為可搜尋的追蹤檔案。

開源、以本機為優先的 3D 參數化 CAD，可在瀏覽器中執行，適用於人類與具備權限的型別代理，由 OpenCascade WASM 提供技術支援。

Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).

200 production-grade DESIGN.md design systems for the world's best apps. Framework-neutral plus SwiftUI, Jetpack Compose, and Expo. Hand one to your AI agent, ship pixel-matched UI.

GMGN OpenAPI skills for AI Agent — query tokens, wallets, and market data, and execute on-chain trades across Solana, BSC, and Base.

用於 AI 程式設計代理的本地程式碼庫智慧 CLI 與 MCP 伺服器：包含 SQLite 程式碼圖譜、支援 28 種語言、285 個指令、244 個 MCP 工具、變更安全閘道、稽核證據，且無需 API 金鑰。

CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.

完全以 bash 實作的 MCP 伺服器 SDK/範例 — 建立無需 POSIX shell 以外執行環境依賴的 Model Context Protocol 伺服器。

Mega 是 Google Piper 的開源實作，這是一個為 AI Agent 時代打造的 Git 相容 Monorepo 引擎。

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

HackAgent is an open-source security toolkit to detect vulnerabilities of your AI Agents

🌐網頁代理協定 (WAP) - 支援 MCP，可在瀏覽器中記錄並重播使用者互動

Hunter Community Edition · 私人金融 AI 团队 · AI 智能体 + AI 量化 · 开源自托管 · powered by opencode + Claude Code + MCP + multi-agent · your private financial AI team · open-source self-hosted · 15 min docker start

The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex & OpenCode from your browser or any chat app.

關於我許多 Terraform、AWS、DevOps 與 AI 專案的資訊。

Vibe Check 是一個為 AI Agent 提供導師級回饋的工具，可防止複雜與長週期 Agent 工作流中的隧道視野、過度工程與推理鎖定。告別過度熱心的 AI Agent！適用於：程式編寫、模糊任務與高風險任務。

A curated list of awesome AI agents inspired by OpenClaw

開源、頻道原生的 Slack 代理閘道。可將團隊執行緒路由至 Claude Code、Codex、OpenCode、Docker、HTTP 代理與自訂 CLI，並具備策略、核准、記憶體、稽核記錄與產出物功能

54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.