GitHub agents

🔍 Detect API model dilution and fingerprint which LLM is actually running behind any OpenAI-compatible or Anthropic endpoint

Comprehensive cost & token usage analyzer for Claude Code with detailed breakdowns by model and token type. Uses ccusage CLI tool and LiteLLM pricing data. The raw token usage data is available in ${HOME}/.claude/projects/<project-name>/<conversation-id>.jsonl files.

Paste any URL. AI scrapes the website, cross-references reviews & funding data, then roasts their marketing BS — out loud. 🔥

Open-source Claude Skill + MCP integration for job search and interview prep. Live job data, role-specific interview intel, voice mock interviews on four-leaf.ai.

Model Context Protocol server for generating QR codes

Codex-pet-compatible companion overlay for Claude Code

MCP server for Yandex Direct — PPC campaigns, ads, keywords, stats (Russia). Part of WWmcp — 114 MCP servers for emerging markets.

🔥 Open-source AI Agent Builder — Create, share, and run AI agents with MCP, tool-calling, and any AI provider (OpenAI, Anthropic, Gemini, Ollama)

Track your Claude usage and the March 2026 2x promotion — right from your menu bar

A Claude skill that turns Claude into a rigorous reasoning and sparring partner — honest engagement, calibrated pushback, current sources, reuse before reinvention.

Multi-model Telegram bot (aiogram v3) with OpenRouter model picker (Llama, DeepSeek, Claude, Grok). FSM, async processing, HTML rendering, anti-flood.

🔍 Extract and analyze your Claude Code conversation history to discover usage patterns, generate insights, and create custom slash commands from your prompting style.

📱 Remote control for Claude Code CLI from your mobile device. Monitor and send inputs to terminal sessions in real-time via iOS & Android.

A framework for LLM-orchestrated research and audits. Multi-prompt, multi-session, context-disciplined.

Transparent proxy that taps LLM API traffic to extract token usage metrics. ~0.1ms overhead.

The definitive guide to using Claude Code for analytics. Production-ready skills, agents, hooks, and workflows for data analysts, analytics engineers, and data scientists.

Claude Code plugin for premium, keynote-style UI — dark, minimal, cinematic reveals with disciplined motion. Portable across Claude Code, Cursor, Codex, Gemini CLI, and Copilot CLI.

Claude Code skill for 1Password secrets management — store, read, and inject API keys and credentials using the op CLI

Stop juggling six AI CLIs. Conclave is your universal remote for LLMs - query any model with one syntax, or unleash them all in parallel and let a judge synthesize the chaos into a verdict. Why trust one robot when you can have a whole council argue about your code?

WCAG 2.1 accessibility agent built on Anthropic API. Audits, evaluates and fixes digital products for UX, UI and development teams. Includes an installable Skill for Claude.ai and a full CLI with PDF/DOCX export.

Chrome DevTools Network-tab-style waterfall visualizer for Claude Code agent workflows. Zero config, zero cloud.

Token Optimization for Context Engineers. 4.8 KB WASM. Sub-millisecond. Zero dependencies.

Hooplytics turns NBA box-score data into player intelligence through machine learning, interactive analytics, and visual workflows for exploring trends, projections, and performance signals.

AI-powered natural language database assistant for Laravel — chat widget with ReAct agent, native tool calling, and multi-layer security

Loop Claude Code through builder/reviewer/test cycles until a completion signal fires. Cost-capped, resumable, scriptable.

Agentic Proposal Generator: Multi-agent AI system using Claude Agent SDK that converts B2B discovery call transcripts into business proposals.

AI-assisted KiCad PCB design using Model Context Protocol and Claude

A bank account for AI agents. Give your AI agent its own wallet with spending controls — no credit card required. Built with Claude Code for the Cerebral Valley 'Built with Opus 4.6' hackathon.

Fuzzy-search every Claude Code session on your machine and resume the one you pick.

Chrome extension showing Claude Pro/Max usage limits (Windows/Linux/macOS)

Multi-Layer AI Quality Assurance for Content Generation. Multiple LLMs evaluate, score, and approve every output before delivery.

Fetch, share, and sync Claude skills between GitHub and your Cowork sessions

🥷 MCP Playground: Fullstack AI agent template. Claude + microservices = modular superpowers. Enable weather, DB, files tools from UI gallery. Built for hackers who ship to production 🚀🔥

This repository presents a project focused on developing a high-precision legal expert LLM application called Contract Advisor RAG. The project's goal is to create a Retrieval Augmented Generation (RAG) system for Contract Q&A, enabling users to interact with contracts by asking questions and receiving accurate, context-rich responses.

Hands-on LLM evaluation learning repo — local models via Ollama, no paid APIs, no maths. Covers deterministic eval, LLM-as-a-Judge, hallucination testing, prompt injection, RAG evaluation, and agent trajectory scoring.

AI decision workflows that turn enterprise documents into traceable decisions, executive artifacts and operational handoffs.

面向小说创作场景的半自动化辅助系统

Your private document brain. PDFs in, RAG out. Self-hosted. Plug everywhere.

🧠 Transform documentation chaos into a structured memory system with Mnemos, your self-hosted, multi-context knowledge server for developers.

Navigation index for the 131 S-class problems forming the backbone of the WFGY tension reasoning engine.

Agent skill that teaches AI agents how to manage Zilliz Cloud vector databases through zilliz-cli

Simple local RAG sample using Spring-AI, Ollama LLMs and Vespa-AI

Turn your PDF collection into clean text your AI can actually read. Mac app.

微信公众号文章总结器 | AI-powered WeChat article summarizer with RAG, GraphRAG, MCP, and multi-platform export

Semantic search over your Gmail, from inside Claude Code. Embeds your full inbox with zembed-1 and reranks with zerank-2 — finds emails by meaning, not keywords.

Hybrid RAG system for translating Ancient Egyptian transliterations using the TLA dataset.

Wiii is an open-source durable AI workbench for conversations, local and cloud agents, files, tools, memory, artifacts, and permission-aware integrations.

AI RAG chat bot that know your domain.

An intelligent local AI agent powered by open-source LLMs, featuring free web search, hybrid memory, and context-aware query rewriting for real-time, grounded answers.

A lightweight wrapper around AI SDK that intelligently indexes and retrieves MCP tools using graph-based vector search.

Build, configure, and chat with your own Retrieval-Augmented Generation bots.

Distributed document RAG system with intelligent GPU/CPU orchestration. Auto-discovers heterogeneous nodes, routes workloads adaptively, and achieves 60x+ speedups through VRAM-aware load balancing. Privacy-first architecture with 4 interfaces (CLI, API, MCP, Web UI). Real distributed systems engineering, not just an API wrapper.

Smart AI Based Food RAG is an intelligent food search system that utilizes cutting-edge technologies to provide users with efficient and intuitive text and image search capabilities. The system combines the power of Retrieval Augmented Generation (RAG) techniques, computer vision.

A high-performance, private Markdown search engine with Hybrid Search (BM25 + Vector) and MCP support. Built in Rust.

一个基于 Spring Boot + Vue 3 的现代博客系统，支持 AI 辅助写作、内容总结和 RAG 知识库系统

LLM powered Mental Health Support

A standalone Edge-RAG Memory Daemon for autonomous AI agents. High-performance Rust core (SurrealDB/RocksDB + Axum) with Bayesian Math Retrieval, multi-language AST indexing, and enterprise Semantic Redaction.

A Genshin Impact Question Answer Project supported by Qwen1.5-14B-Chat

The industry's first "Open Source OCR Arena," a free, no-login utility for one-click benchmarking of 7 top-tier models (Marker, MinerU, MonkeyOCR, Docling, Dolphin, OCRFlux, PP-StructureV3) on your PDF/image files, specializing in PDF-to-Markdown conversion.

Automatic slide deck generator using the power of Postgres as an AI control plane for RAG and MCP

[ICMR 2026] Official Repository for The Paper, Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach

Question-answering system for Zotero libraries with a 3-stage RAG pipeline: FAISS retrieval → CrossEncoder reranking → extractive QA. Features GROBID parsing, question expansion, multi-color PDF highlighting, and Streamlit interface. Ask questions, get answers with sources.

A deterministic, high-performance memory engine. Built in Rust.

Helix: AI-powered CLI with RAG intelligence that converts natural language to commands using 450+ system commands. Features local AI, cross-platform package management, Git workflows, syntax highlighting, and multi-layer safety with directory sandboxing.

Turn your voice into intelligent, linked notes inside Obsidian

RAG-less document QA that loads an entire document into the LLM KV cache once, saves it to disk, and restores it before every query. No embeddings, no vector DB, no chunking. Drastic latency cut on static corpora.

RAG document intelligence with .NET AI building blocks (Microsoft.Extensions.AI, VectorData, Agents) and Aspire

Vex - Vector Exchange - Built by Vektor Memory - A Cross-standard Vector memory DB migration tool - Open Source

A multimodal RAG application using Qwen 2.5 VL, ColPali, and QdrantDB for text and image-based retrieval.

Fast hybrid (BM25 + semantic) local code search for AI agents - pure Rust, persistent index, MCP/gRPC servers, tree-sitter symbols

Partition API used by Agentset

Agentic AI Platform for intelligent database interaction

Local-first context engine for coding agents: project skeleton, symbols, references, graph, retrieval, confidence, MCP, CLI, and HTTP API.

一个为 Dify Workflow “量身定做”的 Telegram 群聊机器人。

High-performance RAG system for intelligent document Q&A with hybrid retrieval, GPU acceleration, and citation-backed answers. Upload docs, ask questions, get precise responses.

Musubi (結び) — Ai Agent shared memory and thought layer. The braiding of threads between presences.

ZIM-based retrieval augmented proxy for OpenAI-compatible AI

Cognitive Memory Architecture for Agents

A Columbia University capstone project focused on mitigating hallucinations in Medical Question Answering systems using Retrieval-Augmented Generation (RAG), ElasticSearch, and LLM-based validation.

A fully functional conversational AI system for restaurant phone ordering using Twilio, Whisper, LLM, and RAG

Full Stack Developer | AI & RAG Expert | Open Source Contributor. Bridging the gap between robust engineering and cutting-edge AI.

Spring AI RAG demo with PGVector, conversation memory, tool calling, and Open WebUI integration

A Self-Evolving Research OS for AI Researchers

This MCP server enables LLMs to retrieve and process web scraping requests using ScraperAPI.

Official GitScrum MCP Server: Full Agile & CRM context for AI Agents in Cursor, VS Code and Claude.

An LLM Cost Calculator for all the major services

AI-CLI 时代的 data lens:把 Claude Code 的 jsonl 实时镜像成可读 HTML,带跨 session 搜索 / 知识图谱 / 自动周报。零 token,单文件 Python。

Hyperliquid trading intelligence for AI agents — 99 MCP tools: builder analytics (revenue, retention, audience overlap), cohort analytics, liquidation heatmaps, trader profiling, and real-time market data across 1.3M+ wallets.

Local-first MCP gateway for federating stdio and HTTP servers through one endpoint

A PowerShell tool for Windows that recursively scans a directory, captures its structure, and concatenates file contents. Perfect for creating detailed context for Large Language Models (LLMs) from your codebase.

Pi coding agent extension for native Ollama — fixes tool calling under streaming

This will be used as the repository for the demo with x402 and fastset

Curated OpenClaw/Codex skills collection for Apollo Toolkit.

Your Gemini web app as a service — turn the free Gemini web interface into a programmable HTTP API for image and video generation

the canonical design language for AI coding harnesses. 52 skills, 19 commands, 89 detector rules, 15 harnesses.

AI HR Agent is first free and open-source AI chatbot for HCM System

Reverse-engineered source code architecture of Claude Code CLI — 4,756 TypeScript files reconstructed from cli.js.map. Deep analysis of QueryEngine, Tools, Bridge, MCP integration, Ink UI, and more.

Claude agent for use with the Mangrove Developer API & MCP Server.

BYOLLM. AI coding assistant for VS Code that runs on your machine — agentic, private, zero friction.