Havuz

交接 Skill（Jiaojie）：跨窗口、跨模型、跨设备、跨语言的 AI 上下文交接工具。换窗口，不失忆；换模型，不重来。Open-source AI context handoff.

Recursive Self-Improvement for AI agents and models, helping your agents self-improve with every run

Always up-to-date open-source mirror of Claude Code (currently v2.1.152). Run from source with Claude subscription/API, ChatGPT subscription

Yao 的开源小工具集合：聚焦本地优先的 AI 编码、网页截图、视频转写、终端诊断和磁盘空间分析工作流。

MCP server for AI agent for cybersecurity: automate assessment of documents, questionnaires & reports. Multi-format parsing, RAG knowledge b

OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, manage

QuantBot（AI 量化机器人）的全量源码。基于 **Go+React + TypeScript + Vite** 构建，通过 **Wails** 与 Go 后端通信，提供 A 股量化交易的图形界面：六维判势、多因子选股、AI 智能体决策、策略回测、实时活动、审计日志等。

Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek model

学习 learn-claude-code 后的 PR Review Agent 实践项目：构建 Debate Council 多 Agent 审查、Tool Calling、结构化报告与 AI Judge 评估。

EurekAgent: an autonomous research system for metric-driven tasks, built with Claude Code. Define the problem and metric. Get breakthrough r

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

A tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying ful

Graphon is a Python graph execution engine for agentic AI workflows.

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression wit

Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact changes, downstream beliefs are auto

mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insi

🚇 A plugin-based MCP server for React Native runtime debugging, inspection, and automation. Connects to Metro bundler via Chrome DevTools Pr

Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + sy

Local-first AI memory — runs offline on any machine with 8 GB+ RAM (SBC, mini PC, laptop, workstation). Zero-loss verbatim archive, knowledg

Agent Skills for competitive GTM work - battlecards, win-loss, positioning, pricing, launches, deal prep and sales enablement. Installs into

A stock picking tool that has 21 legendary investors like Warren Buffet, Peter Lynch, Michael Burry etc debate every stock pick and show you

Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate — 99%+ token savings vs raw file reads.

An open-source desktop AI agent foundation powered by OpenCode and connected through OpenConnector, with local tools, permission controls, a

A compounding LLM-wiki, best fit as a personal second brain that organizes and updates itself as it grows, zero upkeep.

Persistent memory, reflection & safety for AI agents. No vector DB, no embedding server — BM25 + multi-hop retrieval runs in-process. MCP se

Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option.

绿群日报——绿群保研信息提炼：帮你每日快速跟进

AI agent orchestration for open and closed source — a fully customizable fleet of AI agents covering every level of project maintenance, fro

🌿 StoryMoss (草苔) — AI导演式小说创作系统。Tauri+Rust驱动的桌面写作软件，集成知识图谱、伏笔追踪、StyleDNA风格引擎、协同编辑、7阶段全自动创作工作流。让AI成为你的创作搭档，越写越懂你。

Synapse — Temporal knowledge graph memory for AI agents. Self-hosted FalkorDB + Graphiti with hippocampus-layer memory management.

Emotional drive system for AI personas — 15-dimension sidecar that evolves in real time based on conversations and sleep cycles

Entry point for AMALIA related resources.

TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker

This project is an AI Agent orchestration platform. It uses an LLM-driven decision engine, combined with capabilities (built-in tools, MCP p

If you can read ~200 lines of Python, you understand MCP.

Automatically route each Pi prompt to a model based on task complexity, price, speed, or context length. Smart model router for pi.

JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.

赛博人物库 · 把中国互联网最有辨识度的人物蒸馏成 AI Skill / Claude Code Skill / LLM character distillation

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

🤖 喊一声「贾维斯」动口就办事 —— Mac 中文语音管家：本地识别 + 任意大模型(中转站/DeepSeek/GPT) + 工具调用 + 克隆音 + 钢铁侠全息桌宠

Battle-tested model-dispatch doctrine for Claude Code — portable ops rules that let Sonnet/Haiku reliably run projects. Iterated in real dep

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

Run coding agents unattended. Agents write the code. Axocoatl writes the receipt. Claude Code, Codex or a local model in a sandbox; the host

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any sc

Moved to EKKOLearnAI/hermes-web-ui; this repo is kept for historical releases.

Less harness. More model. A lightweight local AI assistant. / 极简 harness 的本地全能 AI 助理。

Multi-agent pipeline that turns a research topic into a draft paper grounded in real literature, with citation hallucination detection and c

Radicalbit AI Gateway

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

A nightly newspaper that writes itself: an agent runs the desks, the figures come from code, and it refuses to publish an edition with marks