Havuz

Claude Code 源码深度研究，包括 Foundations/Execution/Infrastructure 三大章节和 23 个子系统的架构分析拆解。

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline

The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".

Cross-agent plugin for manually excluding and editing AI conversation context, with search, filtering, hide/restore, undo, and original Sess

Open-source relational AI framework with identity persistence, memory, and MCP integration. Build relationship-aware AI agents that remember

Turn AI coding CLIs (Claude Code, Codex, Antigravity) into AI employees on LINE, Telegram, Discord, Slack and 7 more chat apps. A judge revi

AI code review with DeepSeek: headless PR review automation that verifies PR descriptions claim-by-claim against real code, checks docs agai

自进化量化选股系统 — Kronos K线预测模型 + Hermes Agent 自进化闭环 + A股三池漏斗选股

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

Grux AI: open source AI agent for macOS (MIT). One Command Panel for your mail, calendar, meetings, files and a shell it can undo. Runs on a

《智能体工程：从一句话到一个闭环》（Prompt · Context · Harness · Loop），本书将大语言模型驱动的智能体系统拆解为四种递进的工程范式，四种范式从 Token 到 System，从一次调用到完整的自主闭环，构成了智能体系统的完整工程视图。

Human as Agent（人即智能体）· Human-as-LLM 人工代理网关：把工程师变成模型，OpenAI 兼容 /v1 接入 Agent 调度池，涉密/需人工任务路由给真实工程师。为 AI Agent 提效、为平台/运维收集工单。Human-as-LLM Gate

🏛️ Hermes Gate — Terminal TUI for managing remote Hermes Agent sessions with auto-reconnect, detach support, and zero config

面向智能座舱的云边协同 AI Agent：端侧毫秒级车控，云端声明式 Multi-Agent 与 Skill/DAG 编排，支持 S2S 实时语音、声纹多用户、HMI和Android双端；LLM 只负责理解与规划，VAL 负责确定性安全执行。

Pi agent for Android — sideload the APK and run a Pi coding agent on your phone. Single-APK, on-device Termux runtime, Claude Pro/Max OAuth,

纯 Kotlin 原生 Android AI 智能体：多模型接入、子智能体协作、在线插件市场、技能自动引用、root/Ubuntu 终端、长期记忆

OpenClaw 源码深度研究：27 章技术主线 + 2 月以来 PR 演进 + fork/变种生态 + 缺陷与 roadmap（2026-04 snapshot）

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic

HunterCode, A股、港股 ve 美股 araştırması için kendi makinenizde çalıştırabileceğiniz, LLM destekli bir yatırım araştırma asistanıdır.

Neden yükseliyor · 48 günlük yaşına karşılık 559 yıldız ve son 28 günde 543 commit dikkat çekici bir ilgi ve geliştirme temposu gösteriyor. Ancak bu dönemdeki farklı yazar sayısı 5; yüksek commit sayısı tek başına geniş topluluk veya olgunluk kanıtı değil. README ayrıca bir yarışma finali derecesi bildiriyor, fakat bu iddia burada bağımsız doğrulanmış değil.

Tactical AI Workspace Monitor & EDR

Self-hosted AI customer-support platform — per-KB RAG on Qdrant, 13 LLM providers, SSE streaming, embeddable chat widget. FastAPI + Vite + S

Autonomous AI agent that plays Minecraft on its own — a server-side Fabric mod (MC 1.21.3) where a DeepSeek / OpenAI-compatible LLM drives a

NEWTON: Agentic Planning for Physically Grounded Video Generation

Top Dynamic AI World Simulation & Storytelling Tools 2026

A small terminal coding agent for DeepSeek models: it reads your repository, runs commands after asking, proposes edits as patches you apply

iOS dynamic library MCP for agents

YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with benchmarked recall, self-tuning ranking, contradictio

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit)

An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.

A framework for building intelligent agents

A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every g

Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activa

One-Stop Personal Health AI Agent "Say Hi to Healthy Me"

An AI troubleshooting workbench for internal systems: it integrates ticketing and alerting systems via HTTP APIs and webhooks, connects code

ISO 27001 (+ 42001 + NIS2 + EN 18286) ISMS framework designed to be operated by LLM Agents

让 AI 助手轻松获取抖音、TikTok、B 站、小红书等 21 个主流平台的数据｜Enable AI assistants to easily access data from 21 mainstream platforms including Douyin, TikTok,

Assessment-driven, local-first learning agent built on an observable Agent Runtime and eval harness—grounded ingestion, trace replay, HITL a

Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP

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

Enchant Version of 9Router. 304+ Providers (API-key, OAuth, free-tier, and 39 web-cookie providers), 6 combo strategies (fallback, round-rob

Pi adapter for official DeepSeek Harness minimal mode. V4 Pro thinks We need… / I need…, not Let me…

A framework-agnostic UI kit of production-ready components for building AI and LLM chat interfaces.

Open-source local AI Agent desktop app for authorized security assessment — Electron + Mastra-powered runtime, visual pentest workflow, Kali

Async Python bot that scrapes YouTube trends, analyzes viral strategies with Gemini LLM, and dispatches HTML reports to Telegram.

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

Compact AI agent runtime control plane with governed tools, HITL approval, resumable execution, trace-driven evaluation, and SWE-bench-shape

QodeX — a local-first LLM agent & AI coding CLI agent for your terminal. Runs local models (Qwen3-Coder via Ollama/LM Studio) with determini

Agente autónomo para LALIGA Fantasy: lee el juego, decide y actúa (pujas, ventas, clausulazos, alineación). Python stdlib + agente LLM opcio