GitHub agents

An AI-powered SDLC workflow system that turns feature ideas into planned, built, verified, shipped, and maintained software through structured agent-driven phases.

MedCTA: A Benchmark for Clinical Tool Agents

AI video pipeline with a self-correcting critique loop. Brief → script → AI visuals + ElevenLabs narration + music → Gemini Video critique → auto-patch → re-render until target quality.

Open, agentic platform for hydrological modelling — an agentic runtime orchestrates data, model selection, training, runs & audit; LSTM for large-scale catchment streamflow & floods, SWMM for urban drainage & LID. Built on open data.

Manage containers on docker, podman, compose, and docker swarm through an MCP Server for Agentic AI

One FastMCP server, one port — expose each tool group at its own native MCP URL, so every agent sees only the tools it needs. No proxy, no gateway.

Loop engineering for Claude Code — a skill that turns an idea into a production-grade, memory-backed agent loop. Classify, scope, derive state, emit a /loop-ready prompt. Stop prompting; design the loop.

A lightweight agent framework. Start with the core, add only what is needed.

Public Claude Code plugin marketplace — installable skills and agents for AI coding agents. Drop-in capabilities you add with one command.

A curated survey of embodied agents:robotic memory, planning, world models, verification, and failure recovery

🚀 Agentic Agile V Scaffold - Production-ready template for verifiable AI-augmented engineering. Structured briefs, evidence bundles, CI gates, and automated traceability. Build trustworthy software/hardware with AI agents following the Agile V™ framework.

This repository contains information about issues we are working on and allows all of you to give direct feedback.

🎯 AI-powered customer 360° recommender system using LangGraph, FastAPI, and Streamlit — generates cross-sell/upsell reports from customer data in real-time.

Predictable Agentic Spec-Driven Development

An autonomous agent orchestrator for your software work.

ARCS — Agent Routing & Context System. DAG-based task orchestration for AI agents with persistent workflow continuity.

TwilioWorld Agentic Coding Toolkit: Arm your AI coding agent with deep Twilio expertise

Clean-room, Rust-first, Asupersync-native Snowflake SQL API connector built for coding agents. 14-crate workspace, live reads and writes, no ODBC or JDBC.

桌面AI智能伙伴 | 16家LLM自由切换 | 飞书深度集成 | 3D虚拟角色 | Desktop AI Companion with Feishu Integration

A self-hosted wardrobe app with weather-aware outfit suggestions, AI integration via MCP, wear tracking, favourites, a nail polish collection, and a sassy snail who names your outfits. Free. Open source. No subscription fees for your own data. Customisable with a single config file.

Framework-agnostic Go package for integrating AI-powered chat functionality into any web application. It features out-of-the-box support for popular Go web frameworks, a flexible model abstraction for using OpenAI, Anthropic, xAI, Google Gemini, Meta, and more.

Minimum viable chat components

AI Study Assistant is a Streamlit-based AI-powered learning app that helps users get instant explanations, summaries, and answers using Groq API. It supports multi-user login, PDF summarization, voice input, and chat history storage. Designed for students to study smarter with interactive and personalized AI assistance.

Peak Intelligence

Run Claude Code-style AI coding in the terminal with free Groq, OpenAI, or Gemini API support

A **standalone** Discord bot with LLM, VOICEVOX, and KaTeX support.

A chat moderation bot written in PHP and terrible structure out of hatred to overpriced chatbots for https://kick.com

Turn any YouTube video into agent-ready research markdown: transcript -> structured LLM breakdown -> optional deep technical dive.

Xcode Intelligence 使用 deepseek

This is my very first model written with the OpenAI library with express.

Runnable LangGraph workflow examples covering conditional routing, parallel execution, iterative refinement, approvals, and checkpoint recovery.

Detect whether a cheap third-party Claude/GPT API key is actually a man-in-the-middle proxy that intercepts and degrades your traffic. Claude Code skill + check scripts + reporting guide.

Describe images in the WordPress Media Library using a local large language model. Generates titles, captions, descriptions, and alt tags.

AI memory layer for .NET - runs in Blazor WASM, no backend required

EU AI Act compliance gateway for Claude Code and OpenAI/Anthropic-compatible LLMs: redacts PII locally and keeps a tamper-evident, hash-chained audit log.

Go-To-Market (GTM) & marketing plugin for Claude Code. Recognizes your business type (coaching, B2B SaaS, B2C, e-commerce, local, established) and runs an adaptive pipeline from positioning to measurement. 9 marketing frameworks, 11 commands, local-first.

The desktop app Claude Code deserves — explore, search, replay & understand every session. Local-first, zero-dependency (Python stdlib + SQLite FTS5).

Power Claude Code, Codex CLI, and more with your Copilot subscription.

Open-source Claude Skills + MCP for AI lead capture, lead research, sales follow-up & pipeline management — run Lynqu from Claude, ChatGPT & Cursor.

The open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.

Box — self-hosted Claude Code in your pocket. Run real Claude Code & Codex sessions on your own server, driven from your phone (native chat UI, voice, files, skills, always-on).

CC Commander — Master Claude Code instantly. The Fable Method: 12 enforceable gates so any model delivers Fable-shaped results. 71 plugin skills, 22 specialist agents, 23 lifecycle hooks (39 handlers). Free for now. commanderplugin.com

AI-native commerce platform where customers discover and purchase products through conversation while autonomous agents run the store operations end-to-end, with real-time admin control and seamless integration with external AI systems.

Run Claude Science, Anthropic's AI research workbench, in Docker. One-command setup, persistent data, and reverse-proxy examples for any server.

Turns your daily dev activity into a summarized worklog

Your private AI assistant. BYOK chat (OpenAI, Anthropic, OpenRouter) and schedulable automations connected to Gmail, Drive, Calendar, and Discord. Self-hosted.

Per-project usage & cost tracking for Claude Code — status line + terminal reports

Transparent HTTP proxy that redacts secrets and PII before they reach LLM providers. Works with OpenAI, Anthropic, Gemini, and 25+ providers.

MCP server for WHMCS automation - AI-powered client management and hosting operations

Cinema-grade video production MCP server — 8 tools for recording, editing, effects, captions, TTS, and smart screenshots. Built on ffmpeg + Playwright.

A local-only web app that analyzes your Claude Code conversation logs for per-conversation token usage and cost.

MCP plugin that fires warnings, errors, and alerts on wasteful Claude API token usage. Auto-suppresses logs and ignored history to keep context lean.

Self-hostable web UI and admin console for the Claude Code CLI — multi-user streaming chat with per-agent MCP servers, instructions, and model management.

Watch your AI work — replay any Claude Code session like a movie. Prompts, reasoning, tool calls, file edits & context growth on a scrubbable timeline. Zero deps, 100% local.

Extract and distill knowledge from a folder of PDF books into AI-optimized markdown (Docling + a pluggable LLM CLI; single-pass, map-reduce, and outline-driven per-chapter modes).

AI-powered project handover for Claude Code and Codex: onboarding docs plus privacy-filtered AI memories, verified against current code before import.

Local orchestration for Claude Code — session recovery, scheduling, worktrees, Token Saver, and dashboards via official CLI transport. Independent third-party software.

Instant SEO, performance, and security audits for any URL — an MCP server for AI agents

GCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

🌐 Visualize Claude Code agents, skills, and commands with this interactive tool for easy navigation and understanding of complex relationships.

MCP server for MoySklad — warehouse, inventory, orders, reports (Russia). Part of WWmcp — 114 MCP servers for emerging markets.

Job search utility which leverages public Job Scraper APIs and LLM models to find and evaluate job postings based on user preference and present them in a clean Web UI.

macOS menu bar app showing Claude usage & limits (session/weekly, Codex rate limits, API spend). Multi-account, JP/EN.

Runtime token proxy + intelligence dashboard for LLM tools. Intercepts API calls, strips waste, tracks costs — for individual developers and Fortune 500 teams.

Run Claude Code fully autonomously in an isolated Docker sandbox — cross-platform dev container (macOS / Linux / Windows WSL2) with the neuro-matrix harness, persistent memory, and open egress.

GCF Python implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

NoteMeld 是一个自托管的 AI 知识工作台，用来把网页、视频、文件和对话自动整理成结构化笔记，并持续沉淀为可查询、可溯源的个人知识库。

RAG over 289 of Edward Witten's papers (1976–2026): his arXiv corpus + 44 pre-arXiv recoveries. BGE-large + FAISS + pluggable LLM backend (default Claude, also OpenAI/Ollama) with strict citation grounding.

🧠 Understand AI in minutes: 32 core AI concepts explained with simple visuals + everyday analogies, for technical and non-technical readers alike.

Native agent-graph runtime written in C++20

Everyone is building AI second-brains. Some are self-hostable, some are cloud-based. But, which one is actually worth your time & costs?

Production-ready Enterprise RAG system for grounded Q&A. Powered by Gemini 3.1 & FAISS, featuring recursive semantic chunking and citation-backed retrieval.

Multi-agent LangGraph RAG for financial Q&A — 72.7% on FinanceBench under κ=0.932 calibrated judge. RBAC at the vector layer, multi-party HITL on high-stakes answers, self-hosted LLM observability. pip install financebench-rag-agent

PMM Sherpa MCP. Senior product marketing advisor across Claude.ai, Claude Code, ChatGPT, Codex, Gemini CLI, Antigravity. Four tools backed by a 38K-chunk corpus.

PBX Market Estimation & VoIP Trend Forecasting

Let data insights, emerge naturally in any scenario.Intelligently extract insights from massive data, giving every manager their exclusive data advisor.

RAG chatbot for Portuguese IRS questions. Answers with citations to official AT documents (CIRS 2025, EBF 2025). Built with pgvector + BM25 hybrid retrieval, Groq (llama-3.3-70b), and Streamlit.

a powerful Markdown chunking tool that understands document structure. Unlike naive token splitters, it protects atomic elements (code, math, tables), merges by semantic affinity, and scores chunk quality — ready for RAG and fine-tuning workflows.

Chat with any folder of documents using a local LLM — no API keys, no cloud.

Fast, local, hackable graph RAG engine in Go: hybrid dense+lexical retrieval, PageRank over a chunk+entity graph, community summaries for global queries, multimodal, single binary, local Ollama.

This platform handles the entire lifecycle of an industrial anomaly detection system

Model-facing macroeconomic knowledge canon for AI/RAG use: money, liquidity, credit, regimes, instability, and institutional macro strategy.

About Curated RAG knowledge base infrastructure for Odin game development - built with MiniMax-M3 via Kilo Code

🤖 Build AI systems to enhance education with a Virtual Teaching Assistant and voice agents that ensure secure and accurate support for students and faculty.

Full-stack AI chatbot with Spring Boot 3.4, Spring AI, React, real-time streaming, RAG, and JWT auth

基于“永生.skill”的数字生命模拟系统。通过双系统认知架构与长时记忆RAG、常饪生命代谢，让AI（爱）替代因各种原因无法陪伴在身边的人。支持QQ机器人通电、主动反向查岗与情绪状态机，将未完的陪伴以数字生命形式永存。

🚀 企业级私有化 RAG 知识库系统 | 💯 纯离线部署、无需联网 | 🔐 支持 LDAP/AD 统一认证与 RBAC 部门级权限隔离 | ⚡️ 基于 LlamaIndex + Ollama + BGE-M3/Rerank | 📝 支持多格式文档解析、上下文对话记忆及精准的 PDF 原文溯源高亮 | 📊 内置数据可视化仪表盘🚀 Enterprise RAG Knowledge Base. 💯 Fully offline/air-gapped deployment. 🔐 Features LDAP/AD integration, RBAC & Department Isolation. ⚡️ Powered by LlamaIndex, Ollama, and Local Re

MedGEM brings Google's MedGemma and MedASR to offline Android devices for private, multimodal clinical support anywhere.

Annotate Markdown and PDF files in Obsidian with overlay highlights and sticky notes that remain external to your original documents.

Shellless and rust only llm agent

Generated Vuetify 4 documentation as an installable agent skill for Claude Code, GitHub Copilot, and OpenAI Responses.

Live index of LLM evaluation tools and benchmarks, refreshed every 15 minutes from GitHub

Claude Code TUI dashboard: live monitor for parallel sessions and sub-agents, with LLM-generated daily/weekly digest

Shovs LLM OS is a local-first research runtime for studying agents that plan, use tools, remember, verify, and explain what happened.

An AI agent that manages your server from Telegram — text it to run tasks or fix problems, and it watches the box 24/7 and pings you when something breaks.

Apply realistic sensor noise, analog artifacts, and camera metadata to AI-generated images using this custom ComfyUI node suite for research and photorealism.

Bodhi AI — a local-first desktop AI agent that does the work, not just chats. This monorepo ties together the Rust runtime (Bamboo), React UI (Lotus), Tauri shell, Go backend & docs, with a coordinated release train.

基于 LLM Agent 的智能接口测试平台：RAG 文档问答 / 用例自动生成与评审 / LangGraph 多Agent工作流 / 失败归因分析 / pytest 回归脚本沉淀，支持多模型切换与多被测系统零代码接入