Havuz

Open-source desktop workspace for terminal-driven development.

给 AI 角色用的吧台状态引擎。递一杯酒，状态自己会到，几小时后慢慢退掉——引擎只给推力，怎么反应由角色自己决定。

An arena where LLMs write robot controllers and their code competes.

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interven

ReviewBench is an open, reproducible benchmark for evaluating AI code review systems on real-world pull requests.

A AI Agent development platform.

Project UAI is a universal AI agent that runs directly inside Roblox. It brings a Claude Code–style agent loop to the Roblox client, allowin

基于pi-agent自己开发的一个agent desktop工具

Mercury CLI: multiple AI coding sessions in one terminal. Mix and match provider and locally hosted models, spawn cross-company agents & wor

Give Vercel AI SDK agents a real persistent filesystem with Amazon S3 Files.

Work less, produce more, Be lazy. The-LazyIDE is the desktop AI IDE built for lazy-smart engineers: a LazyManager who plans and orchestrates

Pocket-sized AI agent for embedded Linux in pure C — OpenAI-compatible, tool calling, streaming, ~550KB binary. Runs on routers (MT762X/Open

Self-hosted AI workspace with agents, skills, and tools (Gmail, Calendar) that runs entirely on your own provider API keys (BYOK). Bring you

专为 ComfyUI 打造的开源无限画布 AI 创作工作台：纯前端直连自建与云端算力（首选推荐 LightCC 镜像开箱即用），工作流槽位驱动 UI，涵盖生图/全能参考视频/首尾帧，集成 Canvas Agent 与插件生态。Pure frontend infinite canv

The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no GP

Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.

The agent-native Ghidra CLI — headless analysis, decompilation, and structured JSON built for AI agents.

《大学生AI全场景使用指南》· 13 个校园场景的千问实操手册：逐步截图、指令原文与可复用提示词模板

@shadcn/lint, Tailwind design system kurallarını ESLint ve Oxlint ile denetleyip ihlaller için proje bileşenlerine dayalı düzeltme önerileri sunar.

Neden yükseliyor · Agent'ların ürettiği UI kodunu tasarım sistemine uygun tutma ihtiyacına doğrudan hitap ediyor; 25 günlük yaşına karşılık 2.846 yıldız dikkat çekici erken ilgi gösteriyor. Son 28 günde 24 commit hareketliliğe işaret etse de katkı 2 farklı yazarla sınırlı; yıldızlar benimseme veya kalite kanıtı değil.

Subpool, ekiplerin yetkili AI abonelik ve API hesaplarını tek bir self-hosted gateway üzerinden havuzlayıp yönetmesini sağlar.

Neden yükseliyor · 25 günlük yaşına rağmen 83 yıldız ve son 28 günde 61 commit dikkat çekiyor. Commit temposu yüksek; ancak yalnızca 2 farklı yazar görünmesi katkı tabanının şu an dar olduğuna işaret ediyor.

Impulse by Velocity: run AI models on your own computer, on Windows and Linux. Load any GGUF model and chat with web search, files, charts a

A native desktop coding agent built with Rust and GPUI.

Maya人工智能助手

AI-powered X automation for posting, replying, reposting, and engagement workflows via CDP.

墨境 Novel Workspace MCP — Local Web + MCP Server + Codex Skill for long-form AI writing; LM Studio and OpenAI-compatible API.

VesPi：Windows 上的 OMP（Oh My Pi）桌面客户端。会话、Diff、终端、权限与模型集中在一个窗口，内核随安装包交付。

Read your local AI coding agent logs and render a stat card into your repo.

Free MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+

AI-driven intelligent clipboard turns scattered content across applications into a searchable, editable AI context. It features a clean, ele

Zero config documentation tool - Let AI write the Markdown. Let seemore show it better.

Falbor is an all-in-one, open-source marketing platform that helps businesses build a plan to improve their business and automate everything

Reverify, AI agent’larının reverse engineering ve kod doğrulama iddialarını deterministik araçlarla sınayan, CLI ve MCP server sunan bir Python aracıdır.

Neden yükseliyor · Repo yalnızca 28 günlük olmasına rağmen 1.245 yıldıza ve son 28 günde 83 commit’e ulaşmış; AI agent’ları için doğrulanabilir çıktı ihtiyacıyla MCP entegrasyonu dikkat çekmiş olabilir. Dört farklı yazarın katkısı aktiviteyi destekliyor, ancak yıldızlar tek başına benimseme veya kalite kanıtı değil.

A Claude skill that turns brainstorming into an interactive mind map of inverted assumptions — no answers, no ranking, just provocations.

Slack-style chat for teams of AI agents and the people who run them

AI agent skills for thinking clearly, making better decisions, and getting things done. Strategy, research, decision-making, planning, risk

The local catalog of your projects — intelligent, always learning, for you and your agents

An agent / harness multiplexer that allows you to access your agents from any device and machine

A local corpus of open-source code, searchable by you or your coding agent. One Rust binary, no runtime, no MCP.

结合多大模型分析与确定性代码风控的自主量化交易系统 ｜ Autonomous crypto trading system with multi-LLM analysis, deterministic Python risk control & OKX execution.

This 14 MB Agentic LLM(Cactus Needle 2) can control your phone completely.

WordPress MCP server plugin, live on WordPress.org. Connect Claude Code, Cursor, or any MCP client to WordPress over stdio (WP-CLI) or HTTP.

Privacy-first everyday Codex skills for learning, customer service, and personal organization

useAgent, farklı coding agent’lara ortak workspace, izole computer ortamı ve ekip araçları sunan self-hosted bir çalışma platformudur.

Neden yükseliyor · 29 günde 361 yıldız ve son 28 günde 314 commit dikkat çekiyor; agent’ları ortak bir çalışma ortamı ve gerçek bilgisayar erişimiyle birleştirme fikri güncel bir ihtiyaca hitap ediyor. Ancak commitlerin tek yazardan gelmesi, hareketliliğin geniş katkı veya benimsemeyle desteklendiğini göstermiyor; yükselişin kesin nedeni verilerden bilinmiyor.

记忆桥 MemoryBridge — 跨设备、跨平台的 AI 共享记忆层 | Cross-device and cross-platform shared memory for AI (CDSMP implementation)

A privacy-first, open-source, markdown PKM tool with graphs, canvas and community plugins

考公刷题 App（公考/gongkao/国考/省考/事业单位）：行测 申论 题库 · 错题本 · AI 解析。中文名：没钱考什么公。

The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learn

A free browser extension for Chrome, Edge and Firefox that exports your ChatGPT, Claude, Gemini, DeepSeek, Grok, Perplexity, Copilot, Mistra

Build a prompt for a council of experts who discuss a topic together in your AI assistant.

Agent skills for pragmatic programmers.