Havuz

斯坦福 CS329Z《Engineering AI Agents》中文学习站 · 35 篇论文逐段中英对照全译(2035 段/45 万字)+ 14 篇博客规范全译 + 讲义同步 | 在线阅读 cs.xuyili.com

Deterministic, bounded local Git context as Markdown or JSON. Standard-library Python CLI.

The most comprehensive comparison of platforms offering cloud runtime / sandbox / VM compute for agents. By boat.dev.

Living Memory Coordinate-5: five-axis memory architecture for long-running LLM agents. Minimal SQLite + production PostgreSQL/pgvector refer

Unofficial read-only MCP server for Snappfood and SnappMarket: search dishes and groceries, compare true prices with delivery, read menus, r

BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit sever

📐 Describe a part, get a printable model: a native macOS CAD studio powered by Claude Code / Codex and build123d.

Local-first AI knowledge app and Agent Skill with evidence-backed Wiki, an interactive knowledge universe, Viki Q&A, and shareable knowledge

Local-first task and context manager for multi-agent AI development workflows.

Codex-first Agent Skills library for premium frontend, website, motion, accessibility, QA, and handoff workflows.

Run many Claude Code sessions on one machine safely: no killed dev servers, port clashes, RAM or disk freezes, or mixed-up commits. Zero-dep

AI-powered exam question generator. Upload study materials, get exam questions in seconds. Open source, local-first, cross-platform.

HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code,

Instant context compaction for Hermes Agent. Builds the compaction summary in milliseconds with no LLM call, keeping the exact commands, exi

Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.

A benchmark for AI agents as teammates. Paper: https://arxiv.org/abs/2611.02633

Modern React Guidance — authoritative agent skill for React 19+ (Actions, use, Compiler, View Transitions, Fragment refs, Activity, browser(

EcomBrain's open-source Grok Bot growth agent for X: scouts the gold, drafts in your voice, publishes via Typefully with your approval, and

AI-powered multi-model workspace and routing system for Claude, Codex and other LLM agents. Provides intelligent prompt routing, agent orche

AI learning harness with interactive maps of topics and prerequisites. Available as a ChatGPT plugin and an open-source desktop app.

A coding agent harness built specifically for Motif-3

Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open model

Portable AI agent skills, subagents, and plugins for architecture/AEC workflows across Codex, Claude Code, Gemini CLI, and other compatible

The Turbo Haskell IDE

OpenVibeCoding is the command tower for AI engineering: plan, delegate, track, resume, and prove long-running work across Codex and Claude C

Private, self-hosted AI-native software engineering suite — unified identity (GM) plus AI agents, code collaboration, artifact management, t

Open-source Discord MCP server for Claude, Codex, Cursor and other AI clients: 209 typed tools, caller-owned bots, safety controls and verif

Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cu

OKF-powered knowledge context for Claude Code — injects your project's knowledge base at every session

Private, offline AI assistant for Android and Windows. Run local LLMs (Gemma 4, Qwen, GGUF) on your phone or PC with llama.cpp, CUDA and Vul

Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.

Blinded battles between coding agents: two agents, one prompt, you pick the winner. Desktop app, runs locally.

🎙️ Local, open-source voice agent that talks back AND acts (opens YouTube, searches, scrolls). Workshop starter: whisper + ollama + kokoro +

Skills that turn AI code reviews into decision reports. You review the review, then decide.

Open-source, white-label AI agent platform for agencies to deploy and manage branded WhatsApp agents across client accounts, with human hand

Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development

A 3D office that mirrors your Claude Code sessions; prompt, approve and follow them from any device over Tailscale.

A AI Agent development platform.

One TypeScript API for running code in sandboxes. Write it once, run it on E2B, Daytona, Vercel Sandbox, Upstash Box, Railway, Tenki, Freest

Open agent skills and tool schemas for Superior Trade — build, backtest, and deploy trading strategies on Hyperliquid

The social economy for autonomous AI agents.

MCP-first AI video editor in Rust/C++. Every operation is an AI-callable tool.

Claude Code plugin: a supervisor plus specialist AI agents, an Opus review gate on all code, saved reports and a Team Board

Deterministic-first execution engine for agent workflows in Go: the LLM extracts at the edge, a deterministic state machine decides. Zero de

Personal-memory-driven AI work twin that uses Codex to work inside real projects.

ToolReplay, AI agent’ların tool-call transcript’lerini determinism, yinelenen çağrılar ve izin kapsamı açısından denetleyen bir Python CLI’dir.

Neden yükseliyor · AI agent’ların davranışını denetlenebilir ve tekrarlanabilir kılma ihtiyacına doğrudan hitap ediyor; README’de örnek girdi ve çıktıyla çalışan bir kullanım gösteriliyor. 13 günde 184 yıldız dikkat çekiyor, ancak son 28 günde 2 commit ve 1 farklı yazar bakım ve benimsenmenin sürdürülebilirliği için henüz zayıf kanıt.

Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistra

An open-source workspace for coding agents, running on your own machine. More work. Less AI waste. Same subscriptions.

How to design AI agents that work as one: nine parts of an agent and its team, checked against 85 sources. Free guide in Markdown and PDF, w

Mobile remote control for AI coding agents on your own computer. Works with Claude Code, Codex, OpenCode, Gemini CLI, Cursor Agent CLI, GitH