Custom agents

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale.

The open source multi-agent simulation from the Developer Keynote at Google Cloud Next '26. A deployable reference architecture for autonomous AI agents using Gemini and ADK.

🤖 A curated list of AI Agent frameworks, tools, platforms, and resources for 2026 — the year agents went mainstream

A deterministic privacy boundary between your data and AI.

OpenCode goal plugin for Codex-style goal mode, /goal slash commands, persistent objectives, and AI coding agent focus.

Demonstrate once, execute anywhere — secure remote skills for AI agents.

Official code for the paper "Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity"

Open-source, multi-platform harness for AI agents — a native, multi-threaded operator's console (JVM, not Electron) to run Claude Code, Codex, Gemini or OpenCode with a real browser, terminal, editor, secrets & 100+ MCP tools. Built for enterprises, science & research.

Official code for paper "Learning to Use Tools via Cooperative and Interactive Agents"

Local-first AI agent memory — one command, works offline, no account needed. Give your Claude Code, Cursor, Windsurf, OpenClaw agent persistent memory. Markdown storage, hybrid search (FTS5 + embedding), MCP protocol, Web dashboard.

Efficient Large-Scale Fleet Management via Multi-Agent Deep Reinforcement Learning

Deep research agents using MiniMax M2.1 interleaved thinking

WebMCP starter demo — a DoorDash-style food delivery app with 9 AI agent tools (imperative + declarative)

Manage all your terminals and ai coding agents from one unified page.

Tiny MCP server with cryptography tools, sufficient to establish end-to-end encryption between LLM agents

[ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use

A practical library of agents, instructions, and skills designed specifically for QA Automation Engineers, focusing on production-oriented solutions.

The Google Ads MCP Server is an implementation of the Model Context Protocol (MCP) that enables Large Language Models (LLMs), such as Gemini, to interact directly with the Google Ads API.

Call any LLM with a single API. Zero dependencies.

Red Teaming python-framework for testing chatbots and GenAI systems.

Practical setup guides and helpers to connect Burp Suite MCP Server to multiple AI backends (Codex, Gemini, Ollama, ...).

A background agent system for automating end-to-end software engineering tasks, direct from your github repos.

An implementation of a computer use agent (CUA) using LangGraph

vibecoding在AI写作领域的初步尝试，具备function calling，rag，mcp，skills，人在回路等功能，或许能当一个小cursor用？ A preliminary attempt at vibecoding in the field of AI writing, featuring capabilities such as function calling, RAG, MCP, skills, and human-in-the-loop. Maybe it could serve as a lightweight alternative to Cursor?

AI trading research engine for Claude Code. Analyze stocks (technical, fundamental, sentiment, risk, thesis), options strategies, sector rotation, portfolio analysis, and PDF reports. 16 skills, 5 parallel agents. Research tool only — not financial advice.

MCP server for the Live Tennis API — give Claude, Cursor and other LLM agents real-time tennis scores, odds and model win-probability

Personal Corp OS — управление личной компанией через AI-агентов: задачи вне головы, отделы вместо памяти, недельное ретро. Открытые скиллы для Claude Code и Codex

Generate images by Stable-Diffusion-webui Based on Python | 使用Python的基于 SD-webui 的画图机器人（支持中文、Novelai和Naifu）

Caspian is a control room for running multiple AI coding agents in parallel

Lightweight multi-agent gridworld Gym environment

A multimodal, function calling powered LLM webui.

Um template para criar um FAQ chatbot usando Rasa, Rocket.chat, elastic search

K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI systems to assist with cluster management, troubleshooting, and deployments

AI-powered whale trade surveillance for Polymarket — real-time monitoring of 700+ markets, 14 autonomous research tools, 7-step deep analysis with information asymmetry scoring.

A fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other desktop applications just like humans. Based on E2B oss code.

Low-code/no-code python library that transforms plain English instructions into fully configured multi-agent AI teams

Browser extension for AnythingLLM Docker & Desktop application

使用skill让 AI Agent 像安全分析师一样分析恶意样本 | AI Agent skill for automated malware analysis using IDA Pro

Vue 3 terminal UI toolkit for browser DOM and CLI stdout: components, ANSI rendering, markdown transcripts, log views, and agent consoles.

Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent handoffs (−53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.

Connect any code. Call as dependency. The official repository for Graftcode: the integration-free development layer that lets you call methods across languages and runtimes on remote services as if they were local. Eliminate integration layer code entirely.

This is a MULTILINGUAL bot designed to provide emotional support and assistance to individuals struggling with mental health issues. It can help individuals access mental health resources, offer guidance and support. With the integration of Language translation, this chatbot will be very efficient as it will be able to break the language barriers

这个仓库主要是收集CoW(chatgpt-on-wechat)与DoW(dify-on-wechat)的插件，欢迎补充加入看到、用过或新开发的插件。

Simple AI Agent to answer questions for specific domains based on website docs

Switchboard plugin for VS Code, enables subscription-based AI agent teams

Level-based Foraging (LBF): A multi-agent environment for RL

TreeSearch: Search your codebase like a human — not like a vector database. No embeddings. No chunking. Just millisecond search over structured documents and large codebases. 无需 embedding，无需切分文档，在结构化文档和大型代码库中实现毫秒级检索。

Agent Graph is a Multi-Agent System built on the principles of Context Engineering

Beautifully designed components for building AI Agents 🌎

Kiro Best Practices Boilerplate

AI-powered advertising strategy engine for Claude Code. Build complete ad strategies, generate platform-specific copy (Google, Meta, LinkedIn, TikTok, YouTube, Pinterest), design campaign funnels, allocate budgets, and produce professional PDF reports. 15 skills, 5 parallel agents.

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation, and anti-slop quality gates. Packaged as a Kiro Power.

It understands your voice commands, searches news and knowledge sources, and summarizes and reads out content to you.

An AI framework for building cool things.

:smiling_imp: An extensible chat bot framework. sactive-bot is an evolution of the open source hubot project. - https://www.shipengqi.top/sactive-bot .

Autonomous Qwen3-VL training-code research on the official DocVQA benchmark. main: NVIDIA multi-GPU, mlx: Apple Silicon/MPS.

Official Implementation of Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization

Desktop app for running multiple AI agents in parallel. Each agent gets its own terminal, editor, and git worktree, all in one window.

[DEPRECATED] Superseded by systempromptio/systemprompt-template and systempromptio/systemprompt-core. Multi-modal MCP client for voice-powered agentic workflows.

M2I is a simple but effective joint motion prediction framework through marginal and conditional predictions by exploiting the factorized relations between interacting agents.

Automating prompt engineering using AI Agents.

File cache with diff tracking for AI coding agents. Drop-in MCP server that cuts token usage by 26%.

Using AI to generate 3D models

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider, OpenHands, DeerFlow. Companion to Designing AI Agents (Manning) by Jia Huang.

Self-Improving Agents -- A Progression Four levels of self-improving code agents, from the simplest loop to a full adversarial arena with self-modifying agents. Each level adds one key idea.

Automated AI news aggregation that feeds directly into your Obsidian vault. Stay current on the latest LLM research, trending repos, and breakthroughs — curated daily

Public Claude Code skills for Personal Corp, product work, AI operations, and agent-assisted development

Create agentic front-end experiences for the web in VanillaJS™️. Lightweight, extensible, and WebMCP-native.

A curated list of AI copilots and assistants that enhance productivity across various domains, with a focus on coding and software development tools.

Self-hosted AI RAG + MCP Platform

Examples of AI Multi-Agent Solutions

Runtime Security for tool-using AI agents, with local policies, pre-action enforcement, and forensic audit trails.

🎯 Read research papers faster with AI. Resophy is an HTML-based AI paper reader with: 🤖 AI Translation & Analysis — instantly understand structure, contributions, and results 🚀 Daily arXiv Recommendations — discover relevant papers with less noise 🛠️ Vibe Coding Oriented — agent-friendly and easy to customize

An efficient solver for lifelong Multi-Agent Path Finding

Practical OpenClaw tips for memory, reliability, cost, automation, and multi-agent workflows.

Fully managed RAG solution implemented using Knowledge Bases for Amazon Bedrock

The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.

LambChat — Enterprise Agent Infra for governed AI agents. Skills + MCP powered, Loop Agent ready, multi-tenant by design.

Open multilingual construction cost database for AI Agents - 55K+ work items, 27K+ resources, 30 regions. Semantic search via Qdrant vector DB

A native macOS terminal for agent-driven development, built on Ghostty.

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in Claude Code, Codex, Cursor, Aider, OpenHands.

A privacy-first AI agent that sanitizes your prompts locally with a local LLM before forwarding to remote LLM APIs.

Local-first macOS gateway that turns one WeChat chat into a command center for AI assistants, Routes, and local tools.

Amazon Sumerian Hosts (Hosts) is an experimental open source project that aims to make it easy to create interactive animated 3D characters for Babylon.js, three.js, and other web 3D frameworks. It leverages AWS services including Amazon Polly (text-to-speech) and Amazon Lex (chatbot).

Local-first memory layer for OpenClaw, Codex App, and Codex CLI: capture, recall, dedupe, and native sync.

A curated, comprehensive collection of open-source AI tools, frameworks, datasets, courses, and seminal papers.

Your custom 24/7 AI trading agent. Inspired by nof1.ai

An environment for testing AI pentesting agents against a simulated network.

This is a repository for the course "Agentic AI Engineering" by Towards AI.

AI Agents with Bedrock

Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery

AI agents platform that gives you a workspace with an integrated team of personal assistants that can work behind the scenes to handle daily monotonous tasks.

A collection of original system prompts and tool data used for AI chatbots. Explore how companies such as ChatGPT prompt their AIs!

Multi-agent AI coding orchestration system designed to drive successful coding outcomes with a high level of transparency (think more light-factory than dark-factory).

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat pipeline.

Knowledge Manager Agent for Claude Code - Extract and organize content from web, PDF, social media to Obsidian/Notion

SuperNova is a Windows-first desktop AI Workbench that turns chat into traceable tasks. It combines a Tauri + React Workbench, Rust Product Runtime, typed protocol, and Process Kernel so actions can produce visible artifacts, runtime receipts, replayable evidence, and controlled workspace execution.