Custom agents

Native opencode for Android / Termux (Bionic aarch64). Stable, beta and dev channels, built and published automatically.

AI Business OS: multi-agent platform with RAG, OCR, speech & workflow automation. FastAPI + LangGraph + Celery + Flutter. Production-grade, Dockerized

controls the entropy of the codebase by enforcing code module boundaries.

Aixle Flow — orchestrate coding agents through durable, inspectable workflows.

Self-hosted AI architecture for 2026 running on a k3s Kubernetes cluster, providing local Qwen3 model inference, vector RAG pipelines, AI agent frameworks, and hardware-accelerated image generation driven by GitOps workflows.

Open-source MCP server for discovering fast-growing internet conversations with Bubble Agent

Give any AI agent its own disposable Linux machine. Firecracker microVM sandboxing with millisecond boot times, full network access, and native MCP support.

A Rust implementation of LangGraph's state machine framework for building LLM agent applications.

Argus is a desktop app that helps find and fix wasted agent work. Local, free and open source. Focuses on business tasks, not code. Works with Claude Cowork / Chat / Code, ChatGPT Work and Codex.

An open-source Coding Harness Platform for long-horizon, multi-agent software delivery.

Jandal AI — Local-first Android AI assistant with on-device LLM inference, semantic memory, and extensible skill framework

Tools you can actually install and use with your coding agent — skills, MCP servers, harnesses, CLIs. Curated from a weekly agent-tooling radar.

Apple-grade design skill family for Claude Code & Codex — 9 confidence-labeled skills (HIG, Liquid Glass, motion, scrollytelling, OS surfaces, delivery, a11y) with a restraint × surface discipline. One installer links into both ~/.claude/skills and ~/.agents/skills.

OpenCode vision support: automatically saves pasted images and guides non-vision models to recognize them via tool calling. Supports single & multiple images.

Baseline-aware modern CSS Agent Skill: small SKILL.md router + on-demand references. Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode, Pi, Kiro, Pythinker Code, Aider + 70 more agents.

A runnable reference implementation of multi-agent constraint propagation using Caura. 5 specialists share memory via MCP so decisions made upstream automatically govern downstream agents.

Claude Code: The Definitive Guide to Agentic Development — a technical book written in one weekend by AI, free EPUB/PDF for e-ink readers. Includes the assignment file so you can write your own.

Model Context Protocol server for Couchbase - connect AI agents and LLMs like Claude, Cursor, and Copilot to Couchbase/Capella

This project is a fully automated AI blogging platform built with LangGraph and Groq’s LLM. It generates and publishes technical blog posts automatically to a modern, responsive website. The system dynamically renders Markdown content without requiring complex build setups.

Uncensor Qwen 3.8 27B with a pre-baked system pack for Ollama, plus GGUF download links.

Model Context Protocol (MCP) servers that give AI agents local access to macOS apps: Mail, Calendar, Reminders, Messages, Contacts, Notes, Shortcuts, Files, System, and Maps. Unified server plus focused single-app servers.

Safe to explore. Free to build. Koder by aixplain is an AI coding harness for desktop and terminal, with permission checks, reviewable changes, and hosted or local models.

A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.

Skill Marketplace is the first open-source marketplace purpose-built for AI agent skills — the reusable, composable building blocks that power coding agents like Claude Code, Kiro, Cursor, Windsurf, GitHub Copilot, Cline, and more.

Playwright E2E test generation and QA automation pipeline for Claude Code — workflow docs, multi-user flows, mobile audits, and 6 specialized QA agents

Free local dashboard for running Claude Code, Codex, Gemini CLI, and Pi.dev as a coordinated coding team.

Operational tooling & discipline for multi-agent AI engineering fleets — mutation-proven guards, a Textual terminal monitor, generalized skills, and specs. Every check ships with proof it can fail.

An Emacs-native LLM agent harness featuring isolated sandboxing, asynchronous sub-agent orchestration, and fail-fast sync file merging.

Namaste AI — Free handwritten notes and study material covering AI concepts from the Namaste AI course. Explore the history of AI, neural networks, deep learning, transformers, LLMs, prompt engineering, RAG, AI agents, and more. An open-source learning resource by Chetan Nada.

Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every line dated. One memory per client, session handoffs, promotion into knowledge and rules on your yes, plus orchestration and QA layers.

Hermes Agent plugin: rewrites your prompts before they hit the LLM — across CLI, TUI, Discord, Telegram. Quality scoring + analytics + arrow-key interactive overlays.

A hands-on course for building an AI agent harness from scratch — grows one project from a single LLM call to tool calling, memory management, planning, guardrails, tracing, and multi-agent orchestration. No frameworks.

A wallet of AI agents that use real tools and ask each other when a question isn't theirs. Runs on your computer; the model is your choice, local or not.

FDE 中文成长手册：24 周 Forward Deployed Engineer 教程，贯通商业决策、一线问题发现、RAG/MCP 工程交付与运营交接。

Elbi gives your data agent a verified fact store.

Human escalation for Solari browser agents — hand off the live session, solve the blocker, resume in the same session.

Live Knowledge Base of LLM Agents for Science

Monorepo of creative engineering builds: computer vision HCI, WebGL 3D experiments, autonomous AI agents, and browser bots.

AI-powered end-to-end YouTube content automation: trend detection, multi-agent editorial system, AI video generation (Veo), and scheduled publishing. Zero external dependencies.

基于 React、Vite 和 Three.js 的 3D 分镜导演台

Autonomous Penetration Testing Agent Framework with External State Memory & Anti-False-Falsification Guardrails.

Multi-agent reinforcement learning in a macroeconomic environment, with V-learning and bootstrap confidence intervals for government policy parameters.

Your senior Microsoft 365, Intune, and Entra admin, installed in the AI client you already use. Agent Skills plus MCP servers for Claude Code, Cursor, Codex, Gemini, and GitHub Copilot, with a human approval gate on every tenant write.

A lightweight, modular post-exploitation framework for Linux and Windows. Manages interactive reverse/bind shell sessions over TCP/TLS/mTLS and provides plugins for enumeration, execution, pivoting, and operational tasks without deploying a separate agent or dropping enumeration binaries on target.

AI restaurant marketing & operations engine for Claude Code. Multi-platform review analysis, menu engineering, local SEO, social content calendars, ad copy & PDF reports. 14 skills, 5 parallel agents. Restaurant marketing agencies charge $3-$10K/mo for what this does in minutes.

PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents

The Bun-first fullstack TypeScript framework. Laravel-style conventions, end-to-end types, built for coding agents. Deploys to Bun, AWS Lambda, Vercel and Cloudflare Workers.

Multi-agent orchestration for AI coding assistants

Identity broker for AI agents with OAuth2 delegation and consent management

Give your agent eyes: any video link in, one typed JSON out. A Claude skill + API.

make your ai track the progress of your project without drifting off

AGENTS.md contract for AI coding agents + zero-dependency linter + SessionStart hook. Works with Claude Code, Codex, Cursor, Copilot.

Claude Code and Codex in one workspace, with agents that keep their memory and skills across projects. Open source, runs on your machine.

Official Chatway Live Chat MCP server. Connect ChatGPT, Claude, and other AI agents to manage customer support conversations. Chatway offers an AI chatbot, website live chat, WhatsApp, Messenger, Instagram integrations, team inboxes, automation, and iOS & Android mobile apps.

Official implementation of “Harness Optimization for Agentic Multi-Reference Image Generation”

An inference-time framework for long-horizon LLM agents with explicit belief states, consistency validation, and trapping-aware recovery.

Native AI assistant for macOS, built with SwiftUI and llama.cpp. Run local LLMs offline, work with PDFs, and create custom AI assistants. Optional NIKA cloud integration.

基于 Derpyu520/qq-bridge（https://github.com/Derpyu520/qq-bridge）的衍生增强版，特别鸣谢原作者｜QQ ↔ DeepSeek Harness 桥接：跨会话共享记忆、记忆快照与回滚、卡忙自愈看门狗、按会话模型管理、贴吧只读浏览、受限图片发送、群聊唤醒优化及 DSH 0.2.1 兼容适配。

知几 Presight：基金实时估值、持仓跟踪与 AI 市场研究，结合实时行情、热点新闻、Skills 和个人知识库（RAG）。在线体验：https://presight.cloud

Code for AAAI2026 paper "Multi-agent Undercover Gaming: Hallucination Removal through Counterfactual Test for Multimodal Reasoning"

A self-hosted Telegram bot for downloading music from streaming services

An Adversarial Co-Evolution Framework for LLM Agent Safety

AI agent toolkit for 1C:Enterprise 8.3 (BSL): rules, skills and MCP servers so the agent works from your real code, plus byte-perfect metadata editing verified in a test base. Docs in Russian.

Vendor-neutral UI/UX agent skill system with Codex, Claude, Gemini, Qwen, Copilot, GLM, Kimi adapters

Pull-based C2 framework with ten native transports, concurrent multi-profile handlers, and end-to-end ECDSA-signed tasking. Single Go binary agent with every property baked in at build time. Multi-operator team server with RBAC, audit chain, and a Qt/CLI console. Linux + Windows, amd64 + arm64.

中国金融 AI 工具全景图：Market Data MCP / 量化框架 / 券商 Skills / 金融 CLI / Python 金融库。覆盖 A股 港股 基金 期货 行情数据 量化回测 因子挖掘 舆情分析 投研。支持 OpenClaw / Claude / Cursor / Coze 等 AI Agent 平台。每周自动巡检更新。

[KDD 2026] Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation

21st.dev agent skill: search, install and publish React/shadcn components, themes and templates from the terminal. Install with: npx skills add 21st-dev/skill

Official repository for BrickWright, a framework that enables LLM agents to create physically feasible LEGO® builds from text or image prompts.

Redefining development through cognitive automation and collaborative agent systems.

Give your agents a soul. Soulgent turns every Claude Code, Codex and WorkBuddy session on your Mac into a character you can see: who is working, who is done, who is waiting for you. Native macOS app + Soulgent App, a phone web app to reply from your iPhone.

An Agent Name Service (ANS) registry, based on https://datatracker.ietf.org/doc/html/draft-narajala-ans-00

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.

AgentSentry v0.5.0-beta — Standalone Agent Management Framework for AI agent oversight.

Context Limiter & Output Vetter for context bloat. It is a highly specialized, structure-aware JSON built specifically to intercept and compress MCP responses before they annihilate your LLM's context window.

AI powered twitter Bio Generator built Using Next.js and Groq | Shadcn | Llama 3

Front end for Agent-LLM.

Codex + Claude → DeepSeek or other llm 本地代理 | Agent Protocol Translation Proxy

Complete observability platform for AI agents and MCP servers. Improve your AI deployment outcomes, identify inference inefficiencies, and gain insights into real agent usage patterns.

用最简单的代码带你实现基于大模型的本地知识库问答系统

GPT-2 based neural conversational model with TensorFlow.

Python 3 ChatBot / Botnet

Study for Natural Language Processing & Deep Learning Framework

This repository helps you evaluate your models on the FreshStack benchmark!

A ChatGPT powered chatbot for the AWS Well-Architected Framework

可视化网页工作台 + 本机连接器：把 PDF、Word、PPT、URL 一键整理成本地 AI 助手可接手的 PPT 项目包，输出可编辑 PPTX 或杂志风网页演示

Retrieval Augmented Generation for youtube videos with a BRAD agent

ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning. BCB '24: Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics.

Open-science computational astronomy built to be reproduced. We pursue discovery-oriented research on modern spectroscopic surveys and publish the entire research lab, infrastructure included, as code.

Use tensorflow to achieve some NLP project, eg: classification chatbot ner attention QAetc.

Instruction/chat prompts creation library for text generation LLMs. It supports local and Hugging Face models.

Collection of Project Tutorials / blogs in python, web applications, machine learning, data science, deep learning

A bot for iMessage ([email protected]), Telegram (@ImSueBot), and Discord. Now in Elixir!

A pytorch implementation for the MMI-anti model

A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following

kbqa task-oriented qa seq2seq ir neo4j jena seq2seq tf chatbot chat

Bard is a powerful language model chat-bot developed by Google AI. It is based on PaLM 2, one of the most advanced language models in the world. This repository contains an APK that uses a WebView to bring the Bard website to your Android device. 🤖

The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model reranking, and 77.7% LoCoMo accuracy. MCP native, REST API, self-hosted.

This repository `II-Commons` contains tools for managing text and image datasets, including loading, fetching, and embedding large datasets.

Multi-agent stock analysis framework using LangGraph — specialized agents for technical analysis, news sentiment, and synthesized investment recommendations.