aif
On device Firewall for Coding and Personal Agents
This is the broadest group: chat interfaces, SDKs and frameworks, prompt and evaluation tools, and applications built on large language models. Many work with models from several providers, and some can run models on your own hardware.
For anything you plan to ship, check three facts first: the licence, because some popular projects restrict commercial use; whether it supports the model provider you already use; and whether it is still maintained. The At a glance box on every project page answers the licence and maintenance questions from GitHub data.
On device Firewall for Coding and Personal Agents
A lightweight cli for running single-purpose AI agents. Define focused agents in TOML, trigger them from anywhere; pipes, git hooks, cron, or the terminal.
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
Open-source earning-focused swarm intelligence engine. Self-governing AI collectives (queen, workers, quorum voting) running locally via MCP. Works with Claude Code, Codex, or pay-per-use APIs.
Scale LLM Engine public repository
Aiden — Autonomous AI agent that operates your computer with prompts: browser control, terminal execution, workflows, tools, recovery systems, and persistent memory. Built solo. AGPL-3.0.
Private control plane for AI agents
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes
MCP Gateway is a reverse proxy and management layer for MCP servers, enabling scalable, session-aware stateful routing and lifecycle management of MCP servers in Kubernetes environments.
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
The most advanced, fully offline client-side AI suite on Android today.
oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
2026最新ChatGPT Plus/Pro 代充教程:如何代充值GPT会员?怎样购买 ChatGPT Plus 成品账号?如何代充值 Codex 会员?(附国内使用ChatGPT Codex指南)
Materials for the LLM Engineering Essentials course
MCP-NixOS - Model Context Protocol Server for NixOS resources
Real time communication for agents. Wake on message, channels, DMs and actions. Useful for orchestrating agents.
A 股多智能体智能投研系统 — 基于 TradingAgents 架构,15 名 AI Agent 模拟机构协作与实时辩论对抗,全流程可视化,支持 OpenClaw / Claude Code 集成,Docker 一键部署。
MCP server for reverse engineering tasks in Ghidra 👩💻
这是一个金融领域相关的mcp,本项目通过集成 Tushare API 和 Binance API 为语言模型(如Claude)提供全面的实时金融数据访问能力,支持股票、基金、债券、宏观经济指标、稳定币、虚拟货币等多维度金融数据分析。其中也包含了金融数据查询、财经新闻查询、国家统计局数据查询等
Principia extracts reusable principles, composes those principles into traceable research ideas, and helps researchers inspect why an idea may be worth testing.
🪿 LinGoose is a Go framework for building awesome AI/LLM applications.
End-to-end documentation to set up your own local & fully private LLM server on Debian. Equipped with chat, web search, RAG, model management, MCP servers, image generation, and TTS.