Custom agents

Web interface for AI agents.

Open-source knowledge base for people and AI agents. Rich-text editing, hybrid search, GraphRAG, and MCP. Self-host with Docker or use DocsMint Cloud.

一个生成 「影视飓风(Mediastorm)」风格中文口播稿 的 Claude Code / Agent Skill。

An AI agent that applies to jobs for you. It finds openings, tailors your resume, and fills out applications in a real browser on your own machine. Runs on your Claude Code or Codex subscription.

Cross-disciplinary, source-grounded paper deep-reading Agent Skill with vision/text-only routes, domain lenses, and evidence audits.

Connect Claude to image generation with Agent Skills. Three levels: a zero-cost code-based design engine, a Three.js 3D renderer, and a real diffusion model on Cloudflare. Plus an AI Storybook pipeline that turns a plain-English story into an illustrated, narrated HTML book.

Build AI Agents like playing LEGOs. Everything is a Plugin.

众卿 RETINUE - self-hosted task board where humans and AI agents work the same cards. 人和 AI 智能体共用的自托管任务板：对话开卡、审计链、租约围栏、MCP 接入。PolyForm Noncommercial 1.0.0, commercial licensing reserved.

[IEEE TAI] Safe Multi-Agent Reinforcement Learning to Make decisions in Autonomous Driving.

仓库原生 AI Coding Harness —— 把一次性 AI 对话变成可治理、可验证、可沉淀的工程闭环 · spec-first.cn

Open-source control plane for AI agents on your own Kubernetes infrastructure, with per-agent costs, access controls, and audit logs.

The phone is your last API. Give your agent a voice to call any US business - reservations, inquiries, quotes. Verified outcome + transcript. First 250 calls free.

Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.

麦门双预算军师 · 麦当劳中国 MCP 参赛作品 | 钱一个预算、热量一个预算，两个闸门同时过才配餐：88,788 种组合本地穷举，给最划算/最扎实/最均衡三档、券后到手价、全息人设卡。Dual-budget (money + calories) McDonald's China MCP Agent Skill with 3-tier meal plans, coupon math and a holographic persona card.

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

An AI agent command-line interface — multi-model LLM access, streaming terminal UI, tool calling, permission control, and session persistence.

🐚 The AI assistant that just works. One self-hosted app for every model you already pay for: Claude Code, Codex, Copilot, Gemini, Ollama and more. Chat from your desktop, phone or Telegram.

Open-source research assistant and MCP audit toolkit for systematic reviews: cited research reports, PRISMA tracking, evidence and claim checks, and reproducible exports with human oversight.

Open-source AI desktop assistant — run local or remote LLMs with privacy-first design and zero setup required.

Multi-AI orchestration framework for Claude Code — coordinate Claude, Codex, and Gemini with 7 workflow modes, parallel execution, and session unification

给一人公司和小团队用的本地 AI Agent 控制台 把 Claude Code、Codex、Gemini、Qoder 等 Agent 放进同一个看板、消息和审查流程里。

LLM based agents with proactive interactions, long-term memory, external tool integration, and local deployment capabilities.

Django Chatbot with Celery, Channels (WebSocket)

Chatbot with bert chinese model, base on rasa framework（中文聊天机器人，结合bert意图分析，基于rasa框架）

A Webapp that uses Retrieval Augmented Generation (RAG) and Large Language Models to interact with a PDF directly in the browser.

Js/ts library that allows you to set per-time, per-user or per-anything limits for calling Firebase cloud functions

A collection of recent MARL papers

AAAI24(Oral) ProAgent: Building Proactive Cooperative Agents with Large Language Models

AI-powered financial analysis agent for Indian stock markets using AngelOne SmartAPI + Claude

The open-source universal adapter for LLMs. Turn messy real-world data into clean, agent-ready context.

[IEEE TAI] Safe Multi-Agent Reinforcement Learning to Make decisions in Autonomous Driving.

CLI built for AI agents to help navigate codebases better. An alternative to grep/find/glob

A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summaries and suggestions based on user queries. Features data ingestion with Airflow, real-time monitoring with Grafana, and a Streamlit interface.

A RAG agent using Google's ADK & Vertex AI that lets set up semantic search across documents in under 2 minutes. Features GCS integration and natural language querying

Run Claude Code, Codex, Kimi, OpenCode, Hermes and one of the 26 other coding agents using MCP , CLI or TUI , WebUI.

The NVIDIA NeMo Agent Toolkit UI streamlines interacting with NeMo Agent Toolkit workflows in an easy-to-use web application.

RepairAgent is an autonomous LLM-based agent for software repair.

A Rust based terminal workspace for multiple AI coding CLIs in parallel (windows supported)

Google ADK Training Hub: Build Production-Ready Google AI Agents in Days, Not Months 🚀 The only comprehensive Google ADK training with 34 hands-on tutorials, working code examples, and production deployment patterns. Learn skills that directly impact your projects and career. 💼

智能答题助手 - Android平台AI答题应用，通过截图识别和AI分析为各类题目提供答案解析

CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework

Like “oh-my-opencode”, but for Cursor IDE. Multi-agent orchestration, natively, using nothing but a few config files.

🚀 Grounded AI development for Dynamics 365 Finance & Operations. Indexes 580K+ X++ symbols (standard, ISV, custom) and exposes 26 MCP tools that prove every method, field, label and form pattern against your real metadata before the AI writes code. Works with GitHub Copilot, Claude Code, Cursor & Visual Studio.

The KCORES Agent benchmarking project is designed to evaluate the tool-call capabilities of single-modal/multi-modal models.

The universal MCP server for Claude Code and other MCP-compatible clients. One installation gives AI access to 10,000+ PowerShell modules and any CLI tool. You and AI collaborate in the same console with full transparency. Supports Windows, Linux, and macOS.

CrawlLama 🦙 is an local AI agent that answers questions via Ollama and integrates web- and RAG-based research.

Pi coding agent extension that routes LLM calls through the Claude Code CLI

Codex IDE integration for Emacs

An open-source trading framework where users describe strategies in natural language and AI agents generate, backtest, and deploy executable code across exchanges.

Scalable, Composable Reinforcement Learning for Real-World Agents with Bedrock AgentCore.

ZoneMinder client for iOS, Android, Windows, macOS, Linux and web. Live camera view, event review, montage, timeline, push notifications. Rewrite of zmNinja.

Awesome-Prompt-Engineering - This repository includes resources for prompt engineering. 🌟 Star if you like it!

ComPDF Skills are AI-agent-ready PDF processing skills for Claude Code, Cursor, Copilot, OpenCode, and 39+ coding agents to convert, edit, split, insert, compare, compress PDFs, and more.

可移植的逆向分析 SKILL 技能，驱动 IDA + WPeGPT 插件，对 PE/ELF 进行三种模式的自动化分析（轻量/全量/漏洞），输出分析报告。支持 SKILL 技能机制的 AI Agent 均可加载使用。

🚀 One-command requirement development flow for Claude Code - Complete workflow system with sub-agents, quality gates, and intelligent automation

An experimental playground for open-source, all-in-one office AI for universities: code, docs, spreadsheets, slides, browser – all are the AI's workspace. Local-first, event-driven, auditable, with both TypeScript and Python implementations.

15-minute AI-agent positioning session for startups: forced choices, a sub-30-word statement, co-founder compile, and a 90-day proof plan. Claude Code / Cowork / Codex.

A block-based content engine and bilingual blog backend for Laravel Gutenberg-style editor, media library, post templates, roles, and an AI writing assistant, with zero host coupling.

A lightweight Godot framework + agent skills for building and shipping games

A stateful AI operating system for serious, long-horizon work.

智能微信聊天机器人（基于 KouriChat 修改，兼容微信 4.1.12+，底层使用 wechatauto-replica） - WeChatBot_WXAUTO_SE

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

Local-first service attribution, stale development server detection, AI runtime health monitoring, and open-weight model capacity planning.

WorkWit: a self-hosted, open-source (MIT) enterprise AI Agent platform for office automation — built-in contract review & resume screening, 40+ skills, MCP connectors, multi-tenant RBAC. Deploy with one Docker Compose.

Make your AI agent write documents like Notion — Codex & Claude Code skill that locks document structure & Notion visual style

AI agent operating system for Blender 5.2: bpy knowledge base, AGENT_OK execution contract, 3D-print production gate, worked keyboard and desktop-robot builds.

Run your AI models at home in one binary: chat, persistent memory, web access, browser control, MCP tools, encryption at rest and end-to-end encrypted remote access. Linux, macOS, Windows. FR/EN docs.

An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.

Tell your coding agent which dependencies changed after its training cutoff. Diffs types and changelogs, writes a short block into AGENTS.md / CLAUDE.md.

LearnGo, a ios versatile learning tool with RAG and Prompting under LLM like GPT-4o-mini, enabling subject Q&A, smart note generation from uploaded materials, offline photo(or AR) object recognition with translations, and multilingual voice input (Cantonese, English, Mandarin). It also features customizable themes for a personalized experience

The open, machine-readable standard for the Somali language — orthography, grammar, terminology, translation, and AI/benchmark resources, as a versioned, citable RFC-style catalog.

dsh-go — DeepSeek Harness 装进口袋：手机本机运行，也能遥控你的电脑。Android · Unofficial.

Agent skill that orchestrates Codex, Claude Code, Antigravity, Kimi and custom CLI workers with playbooks that save context and quota, and reports what each run did and cost.

Keeps AI coding agents such as Claude Code, Codex, GitHub Copilot, Gemini CLI and Cursor to the least code that does the job and still works.

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

chatbot, an aiml interpreter for PHP

Agentic abstraction layer for building high precision vertical AI agents written in python for Model Context Protocol.

Rank LLMs, RAG systems, and prompts using automated head-to-head evaluation

Locally hosted AI code completion server. Like Github Copilot but 100% free and 100% private.

FlowLens is an open-source MCP server that gives your coding agent (Claude Code, Cursor, Copilot, Codex) full browser context for in-depth debugging and regression testing.

Academic Personal AI Infrastructure

jadx ai analysis plug-in

[CVPR2024] This is the official implement of MP5

[ACL 2024] PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain

An MCP server that provides safe, read-only access to SQLite databases through Model Context Protocol (MCP). This server is built with the FastMCP framework, which enables LLMs to explore and query SQLite databases with built-in safety features and query validation.

[CVPR 2023] Official repository for FJMP: Factorized Joint Multi-Agent Motion Prediction

Erotic conversations scraped from public resources on the internet

An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

AutoSTAT is a user-friendly agent framework for end-to-end data analysis and interactive optimization.

PI（π）—— When The Art of War Meets Cognitive Science for Ai

Open-source voice agent orchestration framework - build production voice AI pipelines without vendor lock-in

This is a Whomrx GPT which is related to the worm GPT and the natural enemy of the chat GPT {UPDATE 2025}

A fully autonomous (no human-in-loop) agentic based project design and coding machine

🤖 Autonomous AI-powered ethical hacking agent powered by Llama 3.1 70B on NVIDIA NIM

Multi-Agent AI System for Company Research

Turn any model into an agent. Model-agnostic, framework agnostic agent harness.

AGNTCY Identity allows to onboard, create and verify identities for Agents, Model Context Protocol (MCP) Servers and Multi-Agent Systems (MASs).

PasLLM - LLM inference engine in Object Pascal (synced from my private work repository)

TradingAgents-A Share Edition` is a derivative open-source implementation based on [TradingAgents](https://github.com/TauricResearch/TradingAgents?tab=readme-ov-file), focused on China A-share research context and multi-agent collaborative decision workflows.

The UI5 MCP server improves the developer experience when working with agentic AI and the UI5 framework.