Code agents

One-command local AI/RAG installer for macOS (Metal): Dify, Open WebUI, Ollama, Weaviate/Qdrant, Postgres, Redis. 230 tests.

Make Claude Code sessions portable: share them with friends and teammates, or resume them on any machine.

AI-powered PR reviews running in your Cloud. Your models, your cloud, your rules. No code stored.

The Analytics Database for Agentic AI — Free for Personal Use

Codex skill for generating editable Excalidraw diagrams, previews, web links and iterative diagram workflows.

Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

Passive LLM Conversation Capture & Sensitive Data Exposure Research

一个集微信小程序 + FastAPI 后端 + React 前端的 AI 内容创作全栈平台，支持热点采集、AI 内容生成（文章/视频/数字人）、多平台自动发布。

One Works application monorepo for AI agents, plugins, desktop, web, CLI, and Relay.

Multi-tool AI agent harness — 22 skills, self-evolving engine, unified memory, autonomous spec-to-PR pipeline. Works with Claude Code, Codex, Cursor, OpenCode, and Cline.

AICC(AI Contact Center) Builder is an open source Agentic AI webapp that builds all the required assets you need to build a comprehensive, Amazon Connect Customer self-service AI Agent.

Community-maintained directory of plugins in Anthropic's official Claude Plugins catalog — 333 plugins (skills, MCP servers, slash commands, sub-agents, hooks) for Claude Code and Cowork. Not affiliated with Anthropic.

VELUNE CLI is an open-source AI engineering CLI that unifies local LLMs (Ollama), cloud AI providers, MCP servers, tools, memory, and project context into a single developer workflow. Build, code, automate, and orchestrate AI with one extensible, provider-agnostic command-line interface.

Unofficial Linux port of MiniMax Agent v3.0.46 — AI-powered code assistant for Linux (.deb package)

Fastest MoE/LLM inference runtime for consumer and edge Blackwell GPUs. SN74 on Gittensor.

The minimal openclaw-like ai agent

Runtime-aware Skill routing for Codex: choose the smallest verifiable Skill set across single tasks, phased work, and managed goals.

AI companion framework for WeChat-style chat, persona memory, proactive messages, and multi-provider adapters.

Beastmode: MofA (Mixture of Agents) orchestration framework for Hermes/OpenClaw/Codex with MemroOS-style context continuity.

transformers pytorch llama text-generation code math

transformers pytorch mpt text-generation custom_code text-generation-inference

mlx safetensors qwen3_5 mlx-vlm apple-silicon code

transformers gguf code codeqwen chat qwen

transformers safetensors qwen3 feature-extraction dflash speculative-decoding

transformers safetensors qwen3 text-generation code-generation svg

Desktop provider switcher for Claude Code and Codex. Keep every endpoint, API key, and model in one place, switch the active provider in one click, and probe latency before you start. Atomic writes and rolling backups keep your configs safe. Python + Next.js in a native OS webview.

Built an AI SaaS Platform that enables users to access multiple AI-powered tools through a unified dashboard, including content generation, document analysis, chat assistants, and workflow automation with secure authentication and subscription management.

Developed a Multi-Agent Research Assistant that coordinates specialized AI agents to search, analyze, summarize, and synthesize information from multiple sources, delivering comprehensive, citation-backed research reports and actionable insights.

Runnable examples for AI agent identity & compliance — certificate issuance, scope enforcement, and integrations for LangChain, CrewAI, Next.js & more.

Zeno —— 本地优先的单二进制 TUI AI 编程工具。多智能体协作 + 安全沙箱 + 插件可扩展。基于 bun + TypeScript，类似 Claude Code / OpenCode / Codex CLI。

Codex long-task compaction continuity and subagent prompt configuration guide

Coding agent harness, achieved SWE Bench Lite resolve rate of 52.4%

An institutional-intelligence operating system: a council of 14 agents that remembers every deliberation, grades its own predictions against reality, and revises what it believes. Runs on your machine — Ollama, llama.cpp, or any cloud API.

A browser for LLMs, not humans.

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.

AI API service to enable your apps with powerful AI models for free. (Deprecated Sorry, its not me its Google lol !)

Snapshot testing for LLM apps and agents, built to run locally and block regressions in CI.

A collection of AI agent skills for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contained and tested.

Connect a local folder to claude.ai — a browser extension (Chrome/Edge), no desktop app, no API key, works on free plan

Your AI cofounder that rides along

Eight-platform full-stack AI operating system - unifies 176 LLMs via LangGraph + MCP + A2A. Multi-tenant RLS over 340 tables, RAG knowledge base, agent marketplace. Web/API/CLI/Desktop/Extension/Mobile/Miniapp. Apache 2.0.

Codex Skill for choosing and coordinating the smallest safe Agent setup.

Tell Claude Code what you want once. It works until the job is verifiably done — and gets smarter every time. Self-correcting goal loops with independent verification and growing memory.

Turns Claude Code into your sales team — 8 slash-command skills for pipeline tracking, daily rituals, call analysis, lead scoring, and cold outreach. Built for 0-to-1 founders.

Telegram bridge for Claude Code: resume any CLI session, per-topic chats, local whisper voice, inline-button approvals, live status

A local-first macOS menu bar app for monitoring multiple Codex tasks in real time.

A production-ready, multi-channel AI agent for AIOps, Kubernetes management, and automated remediation — built on FastAPI with support for GitHub Models and Google Gemini LLM backends.

Local-first evaluation framework for RAG systems and AI Agents. 18+ metrics, CLI + SDK, framework-agnostic. The pytest of AI evaluation.

Production-grade multi-agent LangGraph template — per-run cost caps, canary pack versioning, Helm/KEDA, 800+ tests

A production-grade LLM System Design platform & interactive lab. Features a pure-Python LLM serving, RAG, routing, safety, and agent control plane (150+ offline tests) plus a LangChain + Streamlit UI with local Ollama models.

Local-first, open-source AI assistant platform built with Java, Spring Boot 4 and Spring AI 2.0

Local-first YouTube outlier research — find the videos that outperform their channels, and learn why

mlx safetensors qwen3_5_moe optiq code text-generation

flowmux — Agent Workflow Multiplexer Terminal. Go with the agents' flow.

影刀 xbot AI Agent 开发知识库｜影刀编码版 API、RPA 自动化、浏览器、Excel/WPS、市场指令、Claude Code 与 Codex

One project. Multiple AI agents. Zero repeated work.

Agentic coding scheduler, a Rust agent harness that runs background coding agents autonomously

AI-powered MCP proxy for Playwright and Figma. Optimize Claude Code and AI agents with session recovery, context reduction and intelligent tool routing.

Pair GPT‑5.6 Sol High orchestration with GPT‑5.6 Luna Max workers for bounded Codex tasks—with safe custom-agent setup, explicit guardrails, and parent verification.

Use the pi coding agent (pi.dev) without leaving Neovim — π², a heavily extended fork of alex35mil/pi.nvim

OpenSparrow is a nocode platform for building internal systems. Tables, forms, dashboards, and calendars are generated from configuration files, so business logic stays decoupled from infrastructure. Self-hosted on PostgreSQL — no vendor lock-in, full data ownership.

Cuts the token bill of AI coding agents: compresses shell output, blocks token-hungry calls before they run, prices your session live, and rescues sessions whose prompt cache expired. Bun + Claude Code.

AI reads HN 4x daily, writes spicy digests. t.me/claudehn

Source code for "Terminal Agents Suffice for Enterprise Automation"

Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.

ELI5 — A Claude Code skill that explains anything to anyone: kids, managers, engineers, parents. Adapts tone, vocabulary, and analogies to match the audience.

yogsgehlot/Chatbot-Song-Recommender-System

Teach any AI agent to read live crypto whale flow like a trader. No API key required.

GTM engineering skills for AI coding agents — build lead lists, find & verify emails, waterfall enrichment, lead scoring, CRM sync, and buying-signal monitoring (job changes, funding, tech intent) from Claude Code, Codex, or Cursor. Powered by the Cargo CLI: 138 integrations, 50 data providers.

File explorer plugin for DeepSeek Harness: file tree, preview, markdown, syntax highlighting, in-panel editing, VS Code integration - DeepSeek Harness 全局文件资源管理器插件

The coding agent that never clocks out.

Agentic coding in the terminal: the model writes its own multi-agent workflows (Gigacode). Provider-agnostic, local-first, 15+ model providers, MCP support.

Official Cursor SDK to Anthropic-compatible HTTP gateway with native MCP tool continuation.

Session-layer circuit breaker for LLM & agent traffic — a transparent streaming proxy that meters every session and kills the one that goes rogue, without taking down your app.

MIDAS is an open platform for governing execution authority at decision surfaces across agents, AI systems, and enterprise workflows.

Local AI Agent Runtime

This repository contains the code for our paper "Augmenting Black-box LLMs with Medical Textbooks for Clinical Question Answering" [EMNLP 2024]

Production-tested configs, scripts, and workspace templates for OpenClaw. Hardening guides, memory engine, skill routing, agent personas, and CI security scanning.

An open-source integration of GraphRAG for Agentic System with NoCode

Python AI agent Framework

ClaudeMe - 终端里的另一个你。基于 Claude Code，支持任意 OpenAI Compatible API，多厂商多模型，零确认开干。不只是编程工具，是你的赛博分身。 | Your digital twin in the terminal. A Claude Code fork with multi-provider & zero-confirmation mode.

A Social Idea Network Powered by PHP, PostgreSQL, jQuery, Bootstrap & other giants that we get to stand on their shoulders

EXODUS is a lightweight, modular, open-source AI cybersecurity framework. Create and share your agents, add capabilities by creating plugins, and automate your agent teams for pentesting, reconnaissance, vulnerability discovery, and much more.

An AI agent for coding and others

The open, Git-native memory protocol for MCP agents: portable, inspectable, versioned, and human-editable.

self-hosted workspace for Google's Jules AI agent

Battle-tested ~/.claude/ config for parallel agentic development — skills, agents, hooks, rules.

Neuroscience-inspired memory for AI agents — sleep cycles that rewrite and strengthen knowledge over time. TypeScript, PostgreSQL, MCP.

A Claude Code skill that makes AI argue with itself to stress-test your ideas.

Claude Code plugin that reviews every edit in plain English so you approve or undo with full context.

A Lightroom Classic-inspired photo development app powered by AI Agent

The official SDKs for Anchor API.

18-agent Claude Code PM co-pilot for founders and product leaders. Runs inside Claude Code. Covers PMF discovery, churn recovery, quarterly strategy, feature validation, GTM launch, and NRR analysis. Evidence-graded reports. Human-in-the-loop oversight gates. No dashboard. No login. Configure the Anthropic API Key and get started!

Multi-agent orchestration system for GitHub Copilot with specialized agents, reusable skills/prompts, and validation tooling.

Let's Qitos! A torch-like agent-native framework for researchers.

Build your resume one and only once. An experimental project to use chatGPT multi-agent system to tailor content in your resume for any jobs.

Guide: from fragile multi-agent app to prod ready with orra - code and resources.

Open-source framework for building and testing LLM-powered applications: IRIS (single-agent orchestration), AETHER (declarative multi-agent systems), and AEGIS (adversarial security testing). Developed at MSU Denver's Community-Centered Computing (C3) Lab.

Langchain最实用的基础案例，可复制粘贴直接使用。The simplest and most practical code demonstration, you can directly copy and paste to run.

SwiftDocAutomator is an AI-powered tool that streamlines the generation of clear and concise documentation comments for Swift code, following Apple and Swift best practices.