Custom agents

This is the repo for the paper Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining.

Official implementation of the Neurocomputing paper "Multi-Vehicle Trajectory Prediction and Control at Intersections using State and Intention Information"

The Starcraft Multi-Agent challenge lite

Agent-based model of the UK housing market.

The next evolution of Agents

Sliver agents for Mythic

Code Hacker - VS Code Custom Agent + Web + TUI

Faraday Agent Dispatcher launches any security tools and send results to Faradaysec Platform.

Zero-human, cold-start construction of long-chain agents in professional domains

Tablestore for Agent Memory

🤖 Home Assistant custom integration for using webhook-based systems (e.g. n8n) as conversation agents and voice assistants.

Agent-to-Sim Learning Interactive Behavior from Casual Videos.

Agen is a minimalist language for agent loops and state machines.

Function Calling Mistral 7B. Learn how to make functions call for open source LLMs.

The purpose of the "Meta Agent with More Agents" project is to dynamically solve complex queries by breaking them down into smaller tasks and assigning each to specialized AI agents. The Meta Agent coordinates the process, leveraging a ReAct Agent for tool-based tasks and a Chain of Thought Agent for reasoning-based tasks. The system's flexibility.

Real-time Slack ingest and MCP server to power your agentic Slack bots

Source code for the IBM Granite AI Model Workshop

Implementation of Evo-Memory style learning for LLM agents. Agents learn from outcomes, refine strategies, and get smarter with every task. 🚀 Features: Experience-driven memory architecture Semantic search + context synthesis Self-improving agents

A simple PolicyKit authentication agent for XFCE

这是一个用于claw.cloud部署 Hysteria2 + Nezha Agent 的轻量级 Docker 镜像。

基于 Go 的加密货币量化交易 Agent(模仿 nof1 策略，偏长期交易)｜Go-based cryptocurrency quantitative trading agent (imitating the nof1 strategy, leaning towards long-term trading)

A curated list of open-source projects at the intersection of Agent and RL

[ACL 2026] LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark

Survival analysis in health economic evaluation Contains a suite of functions to systematise the workflow involving survival analysis in health economic evaluation. survHE can fit a large range of survival models using both a frequentist approach (by calling the R package flexsurv) and a Bayesian perspective.

📝 md2wechat MCP Server | 让 Claude Code & AI Agent 一键排版发布到微信公众号

A remote, phone-first console for your tmux — agent-agnostic, no database. Spawn and watch coding agents in parallel worktrees, or anything else you run.

The Generative AI Toolkit is a lightweight library for building, testing and evaluating AI agents in Python, using any of the LLMs supported by the Amazon Bedrock Converse API.

The Open Source Voice Agent Platform. Orchestrate ultra-low latency AI pipelines for real-time conversations over WebRTC.

深度优化多Agent自主执行编码 Harness 框架，支持从自然语言任务出发，完成任务规划、代码生成、自动验证与迭代修复闭环，并成功接入 Terminal-Bench 2.0 评测体系，任务完成率约 40%，榜单排名约 70。

[ICLR'26] Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

Examples of agent apps built with different tools — powered by Google's Agent Development Kit (ADK) and Nebius Token Factory.

Benchmarking Language Agents Under Controllable and Extreme Context Growth

Browse & Inspect CLI agents : Claude Code, Codex, Gemini CLI code & conversation history

Sharepoint to text: A python-libraries which extracts the plain text from legacy and modern office documents and PDF. An enabling library for the agentic age which is driven more by Sharepoint content that you would think ...

A suite of open-ended, non-imitative tasks involving generalizable skills for large language model chatbots and agents to enable bootstrapped recursive self-improvement and an unambiguous AGI.

CLI for AI-assisted manual code review

Prediction market harness for AI agents — skills, MCP server, and Python SDK

Local browser toolkit for AI agents: deep research and browser use automation with local Chrome (CDP) + Playwright. Flexible, extensible scripts for web navigation, extraction and workflow automatization - built for reproducible research and agent-driven browsing.

DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context providing a deeper understanding of your codebase.

Multi agent system for drug discovery tasks

Centralized AI agent skills for Obsidian plugin and theme development.

AI Agent leveraging symbolic reasoning and other auxiliary tools to boost its capabilities on various logic and reasoning benchmarks. This project aims to develop a robust and flexible AI system that can tackle complex problems in areas such as decision-making, mathematics, and programming.

Autonomous Agents on the Web (WebAgents) Community Group

MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning

Reusable Claude Code resources for Drupal development - skills, agents, and commands

[NeurIPS 2025 𝐒𝐩𝐨𝐭𝐥𝐢𝐠𝐡𝐭] AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling

Install agent skills and MCPs with one API

AI agent that implements your specs, opens PRs, and reviews code overnight. Queue GitHub issues or PRDs, wake up to pull requests.

Terminal Kanban for AI Code Agents

Skills and plugins to accelerate security workflows with the Orca Cloud Platform

Skills for AI agents.

CLI for Beeper Desktop API - unified messaging from your terminal. Give your AI agents the power to chat across all your messaging platforms.

The official codes for "M^3Builder: A Multi-Agent System for Automated Machine Learning in Medical Imaging"

Coordination protocol for agent-first teams. No UI. No sprints. No Jira. Just state sync.

开源多Agent智能体协作框架MetaGPT核心概念介绍及相关案例测试

[ACL 2026 Main] Official repository for paper: OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents

arifOS — Constitutional MCP kernel for governed AI execution. AAA trinity: AGI (Mind) · ASI (Heart) · APEX (Judge). Built for the sovereign agentic era.

Schedule AI agents to run automatically on your desktop — like cron, but with Claude & Gemini built in. Free, open source, local-first.

Imagine a personal assistant in your pocket 📱 that handles your emails 📧, schedule 📅, and to-do lists ✅—all through Telegram. That's what this Telegram AI agent does! 🤖✨

A CLI tool for running AI agents inside microVM sandboxes

A collection of Agent Skills designed to help AI coding agents build and maintain Swift applications targeting WebAssembly.

Dev tools in Emacs MCP for agentic Elisp development with LLMs

An autonomous claude code development team orchestrated by a hook-driven deterministic code workflow. An example repo to inspire your own workflow

Durable Cloudflare computers for agents: run repos, steer live workspaces, verify results, and return receipts.

Open Studio is an open-source AI ecosystem powering research and automation with specialized agents like ChatHub for AI conversations and OpenStudio Tube for YouTube creators. More niche AI tools on the way—powerful, open, and built for impact!

Bring your own AI environment to Obsidian. For note/doc creation, refinement, search, organization, management, you name it!

Official Code for MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training (In ACL 2026 Main)

Goal-Driven agent for long-running tasks, docker-isolated workers, intelligent task decomposition, and autonomous execution

Local-first AI agent bootstrap: Playwright Browser MCP + ContextDB for Codex CLI, Claude Code, Gemini CLI, and OpenCode.

AI-powered company knowledge MCP. Unified place for internal policies, values, documentation, and governance. Agents can search, cite, and answer questions using real company docs.

A library for Hnefatafl (Viking Chess, or Tafl) that is used for move generation/validation, piece placement/movement, and game over detection. You can use it to simulate games between AI agents - although you need to write the agents yourself :)

Unofficial Ruby SDK for Claude Agent

Governed infrastructure for internal tools and AI agents

Live2D + ASR + LLM + TTS → Real-time communication + Offline Deployment/Cloud Inference 实时沟通 本地部署/云端推理

A JetBrains IDE plugin that integrates OpenCode — the open-source AI coding agent — directly into your development workflow.

适用于 AI Agent 全自动为 Minecraft 服务器插件、mod自动化测试

Open-source statement-level Playwright tracer, purpose-built for AI agents. Analyzes test runs with increased accuracy.

The Ultimate Claude Code Workflow - Memory Bank, 14 Agents, 18 Commands, 10 Critical Gap Solutions

Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking

Official codebase for the paper "Auditing Agent Harness Safety"

Claude Code skill for handling long-context tasks through recursive decomposition

AI Assistant for interviews & exams - helps capture questions and generate quick, smart answers.

A Context Harness for every coding agent. Run Claude Code, Codex, Gemini, Cursor and more in parallel, each in its own worktree, and steer them by capturing, organizing and injecting context. Web, desktop, terminal and phone.

Agent Decision Records (AgDR) - A standard for documenting technical decisions made by AI coding agents. Extends ADR for the age of AI-assisted development.

Open source multi agent toolkit for Claude Code and GitHub Copilot CLI: 30 agents, plan to ship workflows, review and security gates, plugin marketplace.

Build AI agents with Google's Agent Development Kit (ADK). 20 modules from basics to advanced topics.

Curated legal skills built by lawyers at Skala.io

Generate App Store & Google Play preview videos and screenshots from a simple TypeScript config. Built on Remotion + React + Tailwind. Ships with AI agent skills for Claude Code — scan your app, direct the creative, render to MP4.

SochDB is a high-performance embedded, ACID-compliant vector database purpose-built for AI agents and memory

90+ production-safe OpenStack tools for AI agents via MCP. Project-scoped & read-only by default. Works with Claude, Open WebUI & any MCP client. FastMCP + OpenStack SDK. Available on PyPI, Docker Hub & Smithery.

🔘 Full-Stack Development Framework for AI Agents. Build custom ERP, CRM & Business Tools in days not months. Start with 80% of the job done.

🔥 构建高质量的大型语言模型Prompt，让AI替你打工。Building a rich, high-quality prompt for an Large Language Model (LLM)

EFF-Monitoring是一款面向安全运营场景的告警协作与 AI 研判平台。平台围绕安全事件全生命周期，提供AI研判、处置流转、经验沉淀、插件接入等能力，通过证据驱动的分析与协同机制，帮助安全团队快速看懂告警、定位风险、联动上下游并提升处置效率。

《Skill 蓝皮书 2026》· 基于 61,776 条 Skill 数据的原生研究 · AgentSkillsHub 出品 · 54% 0 star · 基尼系数 0.983