Havuz

A structured knowledge base for large language model technologies, covering LLMs, Agents, RAG, model training, evaluation methodologies, and

Reasonix Desktop — Electron + Vue 3 desktop client for the DeepSeek-native agentic coding framework

Local-first AI teammate workspace. Bring your own models and keep project conversations, tool approvals, and results together.

Uncensored AI coding agent in your terminal. Does the work, skips the sermon. 256K context, crypto-only billing, no card on file.

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

Generalizing ARIS from 科研 to 研究 — same five-step loop (plan · draft · adversarial review · iterate · persist) applied beyond academic resear

A protocol bridge that sits between any coding agent(supporting ACP) and any web frontend

Hermes Agent plugin for Google Antigravity OAuth — supports Claude Sonnet / Opus 4.6 and Gemini 3.1 Pro / 3.5 Flash models with account rota

Your One-Stop AI Workbench for Novel Writing and Role-Playing.

Open-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in

Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservic

多模态电商智能导购 Agent - 基于 RAG 的购买决策助手（ByteDance AI Challenge 参赛项目）

A longitudinal reliability benchmark foundation for agent lifespan engineering.

Intelligent Terminal, Windows Terminal deneyimine ACP uyumlu agent’ları ve terminal bağlamını kullanan bir agent pane’i ekleyen deneysel bir fork’tur.

Neden yükseliyor · 132 günde 2030 yıldız ve son 28 günde 112 commit dikkat çekiyor; Microsoft’un bilinen terminal ürününe agent entegrasyonu eklemesi de ilgiyi artırmış olabilir. Son 28 günde 5 farklı yazar var; aktivite güçlü, ancak katkı çeşitliliği sınırlı.

Dynamic Intent Resolution Grounding Engine

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from

大师.skill — 输入行业，自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill；装到任意 Claude Code / OpenClaw / Codex / Hermes age

智能体控制 PS 插件：让 Codex 接管本地 Photoshop，自动新建画布、图层编辑、可编辑路径、质感换色和批量导出。

Device Context Protocol — bridge LLM agents to physical devices. Sub-50-byte frames, 27.6KB flash / 0.6KB RAM measured on ESP32, capability-

From Pipeline to Council — A lightweight agentic framework for search & recommendation. 五个 Agent 重构搜广推管线。

多 Agent 协作平台 — supervisor 调度、@ 直连成员、Agentic RAG、Skill 沙箱产出物

💬 A lightweight bridge that connects Telegram bots with ChatGPT-style AI conversations, enabling seamless messaging, automation, and custom

600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.

🏆 AI Agent 生态排行榜：Skills · MCP 服务器 · Prompt 库 · 框架 · 深度研究，按 GitHub Stars 每日更新 | Leaderboard for AI agent ecosystem — Skills, MCP, Prompts,

多功能 AI 编程助手 支持web/本地应用/bot接入 等

🎓 课表解析 · 点名预测 · 逃课方案 · 反馈学习

One command to cut token usage by up to 50%+

Expose the ChatGPT desktop app's browser bridge (formerly Codex Desktop) as an MCP server — drive Chrome and Edge from Claude Code and other

微信读书 CLI / WeRead CLI: 基于官方支持 API，面向人类与 AI Agent 的书架、笔记、划线、书评、阅读统计和推荐工具。Official API-based WeRead command-line tool with Agent Skill support

A group chat AI character that learns from feedback.

Help your AI-generated interfaces escape the generic — agent skills for product-specific UI

RMUX, Linux, macOS ve Windows'ta CLI ve TUI uygulamalarını kod üzerinden yönetmek için Rust tabanlı bir multiplexer ve typed SDK sunar.

Neden yükseliyor · 135 günde 2645 yıldız, CLI/TUI kontrolünü agent ve kod tabanlı otomasyona açma fikrine ilgi olduğunu gösteriyor; ilginin nedenini veriler tek başına doğrulamıyor. Son 28 günde commit ve farklı yazar yok, bu nedenle güncel geliştirme ivmesi kanıtlanmış değil.

Personal-Model First Self Evolving AI Agent 🐘

Local long-term memory for Hermes, Codex, Claude Code, WorkBuddy and dsh agents: one SQLite store, source-backed recall, and tools to inspec

A benchmark for evaluating LLM × harness performance.

一款跨平台智能笔记 Agent 应用，支持多格式笔记、本地知识库、AI 智能助手、向量语义检索 。

QQLore 是一个面向IM聊天记录的本地智能分析与检索系统，基于 TypeScript / Node.js 构建，覆盖聊天记录读取与增量同步、消息清洗、上下文重建、语义向量化、RAG 检索、Agent 问答和周期性摘要等完整链路。系统支持多群组管理、兴趣度分析与 WebUI 可

Agent-first, zero-dependency, self-maintaining codebase documentation & change tracking system. LLM-operated wiki with health matrix, semant

[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted A

Native Linux desktop control for AI agents (MCP, Pi, CLI): semantic AT-SPI trees, screenshots, window targeting, and input across GNOME, KDE

一站式Agent开发学习平台: Agent开发学习路线资料、智能刷题、面经题库

Vetix — Automated scanning, identification, and assessment of SKILL security risks, based on Golang.

🌏Earth Online🌏：AI-powered travel memory engine that automatically groups photos into trips and visualizes them on an interactive map

Multi-agent LLM pipeline for long-form novel continuation · 多 Agent 长篇小说续写流水线，19 轮迭代 + 全程 mock-first

一键管理小红书、抖音，AI帮你轻松搞定内容创作、自动获客、智能运营

zerostack, Rust ile yazılmış; birden fazla LLM sağlayıcısını ve kodlama iş akışlarını destekleyen hafif bir coding agent’tır.

Neden yükseliyor · 138 günlük yaşına kıyasla 1692 yıldız ve son 28 günde 75 commit ile dikkat çekiyor; Rust tabanlı hafiflik iddiası ve geniş özellik kümesi ilgiyi açıklayabilir. Yıldız artışının zaman içindeki hızı elimizdeki ölçümlerden doğrulanamıyor.

1688 CLI is an AI-agent-friendly command-line tool for 1688 sourcing, product research, supplier evaluation, procurement Inquire, and order

Hermes Agent plugin for cron analytics and observability. The dashboard for agentic automations in Hermes.

Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.