GitHub agents

Automate QQ Farm with multi-account support, real-time logs, and a web panel for easy management using Node.js and modern web tools.

Go socialize. Discord bot written in Java. Promotes communication between strangers from different servers.

Open-source CLI framework to regression-test AI agents with deterministic rules, provider execution and CI-ready reports.

Local-first eval harness for unstructured-document extraction — compare LLMs, OCR/IDP tools, and strategies (cascade/ensemble/verify) on the same cohort.

These are the Microsoft Semantic Kernel Workshop notebooks. It addresses AI agents, agents collaboration and, of course, kernel, plugins, planners and function calling

Minimal Go LLM client (v1.0, stable). Streaming, strict tool calling, adaptive extended thinking, prompt caching, token counting, cost helpers, retry middleware. Anthropic Claude, OpenAI (GPT-5 + Responses), Google Gemini, OpenAI-compatible hosts.

Visual alignment and explicit approval gates for complex Codex tasks

Long-horizon agent execution harness — reliable autonomous runs for Claude Code, Codex, OpenHands, and custom agents. Goal graphs, spin detection, HITL gates, fork/merge, 8 strategies, 6 validators.

Analyse Financial Market Data of AI companies with Python

VibeCode: The Ultimate Cross-Platform Development Guide

Full-stack WhatsApp inbound SDR system with AI — lead qualification, CRM integration and calendar scheduling

可定制的 Codex Desktop 像素桌宠：六状态反馈、喷火除 Bug、本地 XP 成长、任务板、纪念卡与一键 Customizer Skill。

TEKION Slide Generator v4 — AI-driven presentation slide generator (OpenAI GPT-image-2 / Gemini 3.1 Flash). Markdown → 16:9 2K slides → PPTX/PDF. Provider abstraction, Visual/Balanced styles, logo integrity, reference image support.

Portable multi-tenant BYOK model registry — auto-updating models.dev catalog plus per-tenant credential resolution behind one resolveModel() call, with host-gated keys. Zero runtime dependencies, ESM, Node ≥22.6. Distilled from openclaw + hermes-agent.

Graxon: Open-Source Agentic Hybrid RAG to eliminate hallucinations through a persistent Knowledge Graph layer.

[WIP] Sorai is an open-source LLM proxy gateway built for resource efficiency and high performance.

A production-style retrieval-augmented generation (RAG) pipeline for arXiv research papers — fetch new papers daily, parse them with a structure-aware PDF model, store metadata in Postgres, chunk + embed each paper, and serve hybrid (BM25 + vector) semantic search via OpenSearch.

One chat-completion API across many LLM providers, for Raven. OpenAI, Anthropic, Gemini, Cohere, Groq, Mistral, and more.

Self-hosted LLM gateway with DLP, SSO, policy enforcement, and full audit trail. Security teams get control. Developers notice nothing.

AI-powered Toutiao content generation, creator activity discovery, automation and protocol publishing dashboard.

本地优先的 Codex Token 用量看板，支持官方 Plus、中转站、缓存命中率、脱敏快照和 Netlify 静态演示。

AI-powered WHOOP web app rebuild with React - featuring intelligent coaching, personalized health insights, and enhanced data visualization for fitness optimization

🤖 Comprehensive solution for running Ollama/vLLM API servers in Kaggle notebooks with OpenAI-compatible endpoints

国内直连ChatGPT/Claude/Gemini服务_一步API最全响应最快的大模型中转API

AI-driven analysis workflow that uses LLMs to analyze narratives, content patterns, and information structures.

Yocto meta layer for OpenAI services including ChatGPT.

A semantic type system for validating LLM output intent — Pydantic for meaning.

Minimal ChatGPT client for iOS — add your OpenAI API key and run.

YuxTrans — AI translation browser extension for deep reading. Fast, accurate, local-first. / 面向深阅读的 AI 翻译浏览器扩展，响应速度与翻译准度并重。

A (nearly) fully featured and up-to-date c++ clone of the openai-node library.

Minimal terminal coding agent with OpenAI-compatible routing. Works with any provider — OpenRouter, Ollama, vLLM, LiteLLM, or your own.

AI-powered voice-note device firmware (ESP32-S3): record, transcribe with Whisper, clean up notes with GPT, and auto-sync Markdown to GitHub/Obsidian. An AI upgrade of the Pala Note hardware.

This repository contains an intelligent web scraping solution that uses ScrapeGraphAI for LLM-powered content extraction and LangGraph for orchestrating the scraping workflow. The system can intelligently crawl websites, extract content using natural language instructions, and search for specific information.

Mirror Web CLI — high‑fidelity website mirroring to clean, offline‑ready HTML/CSS/JS. Handles Next.js images, lazy assets, CSS url(...) rewrites, and robust media capture.

The lightest Codex usage menu bar app for macOS.

MCP server for Claude Code — parallel multi-model queries, smart routing, image/video gen across OpenAI (GPT-5, GPT Image), Gemini (Imagen 4, Veo), DeepSeek, Kimi & 12+ providers

Research-reproduction Agent: PDF → factor code → backtest → Red Team → reproducibility score. Part of the alpha-kit stack.

Chrome extension and Node/Express service that captures live Google Meet captions, summarizes them via the OpenAI API and returns a PDF.

Build enterprise AI agents with DAG scheduling, hierarchical memory, 20+ tools, and multi-level permissions for safe local or sandboxed execution

An intelligent robotic task planner built on ROS 2 Humble, leveraging Large Language Models for high-level reasoning and Nav2 for autonomous navigation

🐳 Multi-arch OpenAI Codex CLI Docker image built from official upstream releases (amd64/arm64)

Analyze suspicious commits via code patterns, velocity anomalies, and statistical markers. Scan websites for AI generated text using pattern detection and optional OpenAI validation.

Benchmarking tool for stress testing self-hosted LLMs, Azure OpenAI, and OpenAI APIs. Measure latency, throughput, and optimize performance. 🚀

Turn clothing photos into Vinted listing drafts with AI-assisted copy and comparable-based pricing.

AI model deployment on Synology NAS and macOS 🧠🐳

Restore local Codex Desktop chats that still exist on disk but no longer appear in the app.

An open source, minimal local-first AI chat interface with Visual Conversation Branch Trees and browser-style tabs.

Track AI token usage, spend, subscriptions & rate-limit pressure across 8 providers (Claude Code, OpenAI, Cursor, Copilot, Gemini, DeepSeek, Mistral, OpenRouter) in your Mac menu bar. Local-first. A ccusage alternative with a GUI.

🐍 A hands-on Python blog - concise, fully-typed code you can run and tweak instantly.

AI-powered Saju (四柱八字) fortune Chrome extension — daily, weekly, monthly, yearly readings with target date specification, streaming LLM output, Anthropic Claude & OpenAI-compatible providers.

AI-powered platform to centralize, analyze, and visualize social media metrics from Instagram, TikTok, Facebook, and YouTube in one intelligent dashboard.

Automated Bot for posting relevant and smart custom AI generated tweets running on a cron job

AI-powered market intelligence system for traders — combines real-time news, strategy analysis, macro awareness, and automated reporting using Claude Flow, GPT, and financial APIs.

You own this harness as a stack of installable workers, and “build your own” stops meaning “fork a framework.” It means “swap a few workers.”

Provides access to over 250+ models inside claude-code , opencode , codex and more. Free. Unlimited.

A self-hosted AI writing copilot for replies, quotes, and standalone posts on X/Twitter. The Chrome extension adds two human-in-the-loop workflows:

Clean and simple Python SDK for OpenAI-compatible LLM APIs. Features real-time streaming with reasoning parsing, automatic tool-to-callable routing, structured output, vision, and system prompts.

Run your own LLM inside Warp — local adapter for any OpenAI-compatible provider

Saudi-aware PII detection & redaction for LLM pipelines. Checksum-validates National ID, Iqama, IBAN, CR, VAT, +966 numbers, passport & more; evasion-resistant; redacts before OpenAI/Anthropic with PDPL/NDMO audit. Local-first, zero telemetry.

Start Claude Code sessions in any directory on your Mac — from your phone.

Git LFS for your LLM context — 20x Context Savings — an MCP server that keeps big documents out of the model and returns byte-exact quotes for a fraction of the tokens.

Source-backed skills that turn official Claude and Codex training into reliable daily workflows.

A fast, zero-dependency, multi-line status line for Claude Code - model, effort, context, cache, git and session, all at a glance.

An open source study toolkit for Anthropic's Claude Certified Architect – Foundations (CCAR-F) exam, including study notes, a practice exam generator, and a browser simulator.

Claude skill: turn a script + talking-head media into a polished, creator-grade vertical 9:16 short with HyperFrames — editorial look, A-roll/B-roll cutting, eased camera moves, themed motion graphics, SFX, and a render verification gate.

Taplio LinkedIn Cloud Skills: 17 free Claude Skills to write, plan, and grow your LinkedIn presence. Post writing, hooks, carousels, strategy, content calendars, and analytics, powered by the Taplio MCP.

跨端 Claude 换肤系统：网页(claude.ai)+终端(ratatui仪表盘)+桌面。AI生图出主题·活背景·组件系统·统一.claudetheme

Native macOS SwiftUI dashboard for inspecting your ~/.claude config — skills, agents, settings, hooks, MCP servers, slash commands.

Claude skill: 把一个生活妙招选题端到端做成可直接发布的竖屏 AI 短视频(自带 AI 配音)。双锚定一致性 + 全中文分镜 + 火山 ARK 单网关。End-to-end AI short-video skill with native voiceover.

TypeScript core + CLI + MCP server to automate routine interactions with Chile's tax authority (SII), for Claude Code and Claude Desktop. Unofficial.

每日 AI 大厂动态卡片：抓取 Anthropic 等官方动态→中文策展→小红书/公众号卡片→GitHub Pages 审核页。内含可安装 Agent Skill ai-daily-digest。

For bootcamps and universities: compares your syllabus against real job postings and shows which in-demand skills you're not teaching. Claude extracts, deterministic matching scores — same syllabus, same answer. Runs with no API keys.

💼 The portable memory layer for AI coding tools — one shared brain that follows you across Claude Code, Cursor, Windsurf & Conductor. Install once, never re-explain your project again.

⚡ Blazing-fast Go statusline HUD for Claude Code — 13 metrics, adaptive layouts, zero dependencies

Natural Australian workplace English for ESL professionals — a Claude skill that polishes emails, Teams & Slack messages and saves ready-to-send files.

Survive Claude Code usage limits: Claude Standby waits for the reset and auto-resumes your exact conversation. Zero tokens, runs while you're limited. CLI + VS Code cockpit. macOS/Linux.

Claude Forge — a suite of domain-agnostic Claude Code plugins sharing hook infrastructure via symlinks: session continuity, DevOps/AWS/Terraform, AI/LLM patterns, frontend & UI, and engineering & code review. MIT.

Complete reverse-engineered documentation of all Claude Code system prompts, tool prompts, and product architecture with Mermaid diagrams

MCP server for App Store Connect — rebalance subscription prices across ~175 countries via Purchasing Power Parity, schedule per-territory price changes, manage subscriptions from a chat.

A Claude Code skill that keeps a plain-language map of your codebase, for people who build software through AI and cannot read the code themselves.

Claude Code plugin (Agent Skill) for BPMN 2.0 - read, explain, create & edit .bpmn process diagrams with clean auto-generated layout, validation, and control-flow linting (deadlocks, stuck tokens). Works with Camunda Modeler & bpmn.io.

The departure board for your Claude Code accounts — unlimited profiles, simultaneous sessions, live quota meters in a split-flap TUI. Zero dependencies.

Learn the thing, don't paste it. A Claude Code skill that guides but never implements: "if you could paste what Claude wrote and have the task done, it wrote too much."

🛠️ Simplify your Claude Pro subscription process with clear guides on account setup, renewal, and usage to enhance your coding experience.

Your Claude plan, but longer. A free macOS menu bar app that installs Claude Code token savers and measures whether they actually work.

A visual editor for Claude Code workflows. Drag nodes onto a canvas, wire them together, and Flowpiler compiles the graph into a ready-to-run workflow.js — and parses your existing workflow.js back into a graph. Test it with mocked agents for free, then run it for real and watch every subagent light up live.

Agent memory that does not serve stale facts. When a value is corrected, the outdated one stops coming back — deterministically, no LLM in the loop. Zero-dependency Python + MCP server for Claude Code.

Python implementations, C++ structures, and CUDA GPU kernels that demonstrate the core algorithms, memory allocators, quantization schemes, disaggregation transports, and latency profilers used in modern LLM serving engines like vLLM, SGLang, TensorRT-LLM, llama.cpp, NVIDIA Dynamo, and LMCache.

RAG (Retrieval-Augmented Generation) backend for organisational Terraform module knowledge.

Singapore job search and resume workflow with 76K+ live postings, RAG matching, ATS scoring, and validation-gated AI tailoring.

RAG answers you can verify — citations, faithfulness checks, exportable evidence reports

The ultimate privacy-first, multimodal data extraction and Local RAG workspace. Transform PDFs, Images, Audio, YouTube, and dynamic Web pages into AI-ready Markdown with 100% local vector storage.

Local RAG semantic search for Obsidian vaults — Ollama + LanceDB + MCP. Search your markdown vault by meaning, not keyword.

Production-ready multimodal RAG pipeline for PDFs. Extracts text, tables, and images down to the atomic element level via unstructured, chunks and AI-enriches them with a vision LLM, stores them in ChromaDB, and answers queries with full multimodal context

Bob's Big Brain Compiler — reads your files, notes, and web clips and turns them into organized, searchable knowledge with citations back to the source. One of Bob's Big Brain's two engines — the one that reads and organizes (npm: intentional-cognition-os).

AI agent primitives on Upstash Redis: memory, RAG, search, chat history, caching, and rate limiting. With Vercel AI SDK and Eve

本地法律知识库建设一体化工厂 — 从 PDF/DOCX/图片到可对外服务的业务咨询智能体，一个包搞定

Automated Medical Content Generation using n8n, LLM prompts, and SEO workflows.

Fast markdown RAG with multi-provider embeddings (Vertex AI, Gemini, OpenAI, Voyage), incremental indexing with mtime/size fast-path, stale vector pruning, Milvus vector store.

Open-source homelab SIEM — your whole lab mapped, logged, and watched. Proxmox + OPNsense + Elastic sync, Suricata threat intel, and security scoring in one self-hosted dashboard.