Havuz

Talk to your home. A voice-driven personal AI agent that chats, assists, and orchestrates your smart home.

Go LLM Execution Model — Go 原生 AI 编程 Agent CLI。单二进制、三层记忆、YAML 权限规则，TUI 对齐 Claude Code / Codex。

OpenScience, bilimsel araştırma görevlerini planlayıp literatür taraması, kod çalıştırma ve sonuç raporlamayı tek bir AI workbench içinde birleştirir.

Neden yükseliyor · 86 günlük bir repoda 3.645 yıldız ve son 28 günde 434 commit dikkat çekici; bilimsel araştırma agent'ı fikri de güncel AI ilgisiyle örtüşüyor. README'de Y Combinator desteği belirtiliyor. Ancak aktivite yalnızca 5 farklı yazardan geldiği için büyümenin geniş katkıcı topluluğuna dayandığı söylenemez.

Reina 桌面 AI Agent 发行仓库（仅安装包） | Release distribution for the Reina desktop AI agent — installers only. Windows x64 & macOS arm64, in-app auto

AdCraft — 首个面向营销广告的 Agentic 视频制作平台。无限画布 · 拉片复刻 · 全流程自动化，从创意到成片一站直达。AdCraft — The first agentic video production platform for marketing and a

AI coding agent that shows its work — every step visible, every patch approved by you. Build projects brick by brick, stay in control.

TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation

embeddable llm agent in c with lua plugins

AI生图工作台 (AI Image Generator)、视频工作台。支持 Agent 与工作台模式、无限画布、素材管理、提示词反推/广场及 PWA，支持外链式配置；可接入 Grok、GPT Image 2 等自定义模型生图。自适应手机端。

Build a coding agent from scratch, one harness primitive at a time. 15 chapters (ch-00..ch-14), each green on two gates.

Filesystem-first agentic task runner in TypeScript, powered by Gemini: every piece of state is a plain file you can read and edit. Not a cha

Durable, repo-native project memory for coding agents, without context bloat.

Give agents access to virtual hardware.

LLM Space, agent geliştirme sürecinde prompt ve araçları düzenlemeyi, çalıştırmaları incelemeyi, hataları yeniden oynatmayı ve performansı değerlendirmeyi sağlayan bir desktop uygulamasıdır.

Neden yükseliyor · 92 günlük yaşına göre 1.936 yıldızın yanı sıra son 28 günde 57 commit ve 8 farklı yazar kayda değer ilgi ve geliştirme hareketliliği gösteriyor. İlginin hangi kanaldan geldiği verilen verilerden anlaşılamaz.

Local-first AI learning workspace — ask, note, review and create around your own materials. Wiki KB, Agents, Skills, creation tools.Priva

The open-source trading harness for Claude Code / Codex agents.

Local-first Agent Runtime connecting LLMs to controlled tools, Chrome, desktop automation, MCP, context governance, and verifiable memory

AI World Generator 2026: Create Self-Evolving Maps & Stories

An Orchestrate multiple coding agent desktop app

基于 FastAPI + Vue 3 构建的智能客服系统，具备 RAG（检索增强生成）与 AI Agent 核心能力，可为企业提供高效、可扩展的智能客服解决方案。

🔥PaiCLI — Terminal AI Agent in TypeScript

Kata builds the best AI agent for a subnet through open competition — so anyone can mine that subnet with a proven, optimized agent.

A declarative, hermetic harness for Nix-defined agents.

🔥 CogitoAgent — An autonomous AI agent, cloud-driven but locally executed. It continuously thinks, automatically analyzes, and integrates pr

A fast, distraction-free Markdown editor for Windows And Linux. No server. No account. Your files never leave your device.

AI Engineering practice and open-source book: learning, experiments, and judgment across LLMs, agents, RAG, MCP, and AI coding.

A minimal, extensible, agent-native knowledge repository that keeps shared context current and inspectable

A powerful, lightweight agentic desktop agent built for engineers and work.

mimofan - AI coding agent platform

Gen AI Evaluation Toolkit on AWS is a flexible, cloud-native accelerator built on AWS serverless architecture that enables comprehensive eva

GUI agent using WebMCP polyfill. Control web interfaces with natural language

AI 内容试映工作台：在真正发布前，把内容交给一组 AI 观众试映。

Agentic email + calendar hub on Cloudflare Workers. One Worker owns your domain's email surface: a full self-hosted email client with an AI

Knows your world. Answers to you. — the open-source personal AI agent you own.

Java-implemented extensible AI Agent runtime — direct Anthropic protocol connection / Spring Boot 4 assembly / multi-tool collaboration / We

Loop-native agent workspace — put your AI coding agents on a canvas, wired into loops that run themselves.

Agent harness research ebook — model-agnostic architecture specification (June 2026)

加密环境文件操作 MCP 工具。当 Node.js 是加密软件白名单进程时，通过 fs 模块自动解密读写文件明文，替代 AI Agent 内置文件工具，适用于任何支持 MCP 协议的 Agent。

MindMemOS, farklı AI agent’ların kullanıcı ve görev bağlamı için ortak uzun süreli belleğe erişmesini sağlayan bir yazılım katmanıdır.

Neden yükseliyor · 96 günde 996 yıldız ve birden fazla agent entegrasyonu ilgi gördüğünü düşündürüyor; ancak README, yıldızların Pro quota üyeliğine yükseltilmesini de teşvik ediyor. Ayrıca son 28 günde commit ve farklı yazar yok; bu nedenle popülerlik, güncel geliştirme faaliyetiyle doğrulanmıyor.

本地优先的 Agent 视频分镜工作台：让 Codex、Claude Code 通过 MCP 写分镜、生成图片/视频素材和配音，并自动回填。Local-first storyboard workbench for AI agents (Codex, Claude Code).

Dex lets your agent build your analytics.

FTShare financial data Python SDK｜通过 Python 和 pandas 接入基础金融数据与 FTShare 特色因子。

Open-source agentic infrastructure & alternative to Grok Bot. Bring Claude Code, Codex, OpenClaw or your own. Start without building from sc

Methodology and deterministic evaluation tools for iterative improvement of skills, repositories and agent workflows, with independent revie

Mission control for your AI agents

Manage your GitHub starred repos: tag, note, filter, search across thousands of stars. Chrome MV3 extension.

A platform creating fully autonomous Hermes agents for your team.

A Unified Memory Benchmark Suite for Memory-Augmented Agents

🔌 CLI & MCP server for pkg.go.dev

Agent-friendly Markdown-to-PDF CLI with local PDF rendering and JSON diagnostics.