Custom agents

ChatOps Engine for Slack, written in Go, inspired by Hubot and Jenkins

A RiveScript interpreter for Go. RiveScript is a scripting language for chatterbots.

Lightweight AI coding agent SDK. Same power, 97% less complexity. Build custom AI coding agents in 1 minutes

This repository provides pre-configured rules that teach AI coding agents how to effectively use Nia.

Pengunuity is an experimental open-source autonomous AI Agent that aims to replicate the structure of human memory.

code implementation for 'Bi-level Actor-Critic for Multi-agent Coordination'(AAAI2020)

Asynchronous Spatial Allocation Protocol for Heterogeneous Multi-Agent Trajectory Planning

Projeto de GenAI usando LLAMA V2 Local estilo ChatPDF

Data Agent is an intelligent data analysis system that automatically completes complex data analysis tasks through multi-agent collaboration.

A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical guides on defining and collecting rewards to build more intelligent and aligned AI agents.

Build an embeddable RAG Chatbot for your website using Cloudflare Workers.

offical code of paper 'SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding'

AI agent platform enhanced with Agent OS architecture inspired by Claude Code, built on DeerFlow

MachineAuth provides authentication and permission infrastructure that allows AI agents to securely access APIs, tools, and services.

Benchmarking the gap between AI agent hype and architecture. Three agent archetypes, 73-point performance spread, stress testing, network resilience, and ensemble coordination analysis with statistical validation.

React-flow chatbot

Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.

Codes for Paper "Delay-Aware Multi-Agent Reinforcement Learning".

Multi-agent simulation library in Python

My version of the Stanford experiment "Generative Agents: Interactive Simulacra of Human Behavior" in Python using a local LLM.

Production-ready multi-agent orchestration. Revolutionary architecture for enterprise development automation.

PenGym: Pentesting Training Framework for Reinforcement Learning Agents

A hybrid programming language combining Lean4's formal verification with blazing-fast compilation, actor-based agent orchestration, AI-driven optimization, and vector-backed agent memory.

Your personal AI knowledge system. Self-hosted, agent-driven, and always private.

[CVPR 2025] Official PyTorch code of "Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation".

Policy Synth is a TypeScript class library designed to streamline and enhance decision-making processes through multi-scale AI agent logic flow.

EvoSynth is a SOTA automated LLM red-teaming framework that evolves executable, code-level jailbreak attack methods using multi-agent synthesis, evolutionary search, and self-correction.

MCE: Clone Human Souls with LLM Native Agent Skills | 基于 LLM Agent Skills 的心智克隆工程 | Agent Skills | Mind Skills | Mind Clone

RAG-powered AI agent that translates natural language into SQL for live database querying.

LLM & IDA 主导的逆向分析平台

Better context. Better code.

The app framework built for AI coding agents. Own every line. Your AI already knows how to build on it.

🐍 Асинхронный Python-фреймворк для разработки ботов MAX Bot API (max.ru)

Agent skills that give AI agents live web data — search, scrape, and extract structured data with Extraction Templates and Web Search Agents, plus one-command business intelligence workflows. Plugin and MCP server for Claude Code, Cursor, Codex, and Grok.

AI agent toolkit (skills+MCP server) for Lightning Network payments. Run nodes, pay for APIs (L402), host paid endpoints, and manage credentials.

Comprehensive course on building production AI agents. From Transformer fundamentals to multi-agent orchestration, RLHF, and deployment.

Terrarium: Multi-turn data engine for evaluating and optimizing LLM agents in living environments.

🤖 Your Intelligent Copilot for Data Exploration and Processing Pipeline

🤖 Cortex AI: #1 智能量化交易系统 — 全自动加密货币套利引擎 v3.4。支持 Solana、TON、Binance (币安) 和 Bybit。2026年最佳高频量化交易机器人。

Red Team AI Benchmark: Evaluating Uncensored LLMs for Offensive Security

Command-line tool for the Chrome DevTools Protocol (CDP): debug targets, console, traces, heap snapshots, and JavaScript CPU profiling for Chrome, Node.js, and React Native.

A lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.

Can LLMs beat classical HPO? A benchmark comparing classical, LLM-based, and hybrid methods on Karpathy's autoresearch.

Chat copilot plugin for Paperclip — interactive AI assistant for managing tasks, agents, and workspaces

An Arduino AI Assistant. (4A! Yay!). This plugin integrates Claude, ChatGPT, Gemini, LM Studio and more directly into the Arduino IDE.

Agents, skills and templates for structured AI-assisted development with OpenCode, Codex and Claude Code

Đây là bộ SKILL, RULES, COMMANDS do Anh Tester xây dựng dành riêng cho cộng đồng Tester để thiết lập AI Agent trên Claude Code hỗ trợ kiểm thử phần mềm.

Grabs all your Perplexity conversations data, spits it out into a nice file folder structure and allows you to find your old conversations again.

HTML output skill for Claude agents — 4 levels (Static Doc / Visual Artifact / Two-Way Interactive / Throwaway Tool). Based on Thariq Shihipar's framework.

Lightweight Linux sandbox for AI agents. Kernel-native isolation (namespaces, cgroups, seccomp, Landlock) with REST API, MCP bridge, and web dashboard. Single Rust binary.

Your local-first AI ad ops crew. Works with Claude Code, Cursor, Codex & Gemini.

让 AI 助手轻松获取抖音、TikTok、B 站、小红书等 21 个主流平台的数据｜Enable AI assistants to easily access data from 21 mainstream platforms including Douyin, TikTok, Bilibili, Xiaohongshu｜AI アシスタントが抖音・TikTok・Bilibili・小紅書など 21 の主流プラットフォームのデータを簡単に取得｜AI 어시스턴트가 도우인, 틱톡, 빌리빌리, 샤오홍슈 등 21개 주류 플랫폼 데이터를 간편하게 확보

3-level security toolkit for AI agents: regex patterns, heuristic rules, ML classification. Claude Code hooks, git pre-commit, CI/CD scanner.

具备认知记忆架构的 AI Agent，让 AI 记住你的偏好，越用越懂你 核心特性：四类型记忆系统、跨会话记忆共享、Claude Code 架构、15+ 大模型支持

Telegram bot yang bridge ke Tempo MPP — panggil GPT-4o, DeepSeek, dan Exa Search langsung dari chat Telegram.

A decentralized micro-settlement protocol enabling autonomous AI agents to pay publishers for premium content via Circle Programmable Wallets and x402 nanopayments.

A tool to convert GitHub issue/discussion into Markdown.

AI Skill Hub — a cross-platform desktop app to discover, dedupe, organize, and sync AI agent skills across Claude Code, Codex, and a shared pool. Ships an MCP server so your agent can run the whole library — install, align, organize, clean up — every write gated and reversible.

Python toolkit for on-chain AI agents on BNB Chain.

A fully-local, multi-model AI agent framework with Mixture-of-Agents (MoA) orchestration. Run a high-performance agentic stack on consumer GPUs (RTX 4080/5080) using Hermes + Ollama, with zero cloud dependencies.

Agentic Software Engineering (ASE)

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

Local cockpit for Claude Code usage — rate limits, activity chart, one-click skill buttons.

Prompting tests for evaluating LLMs, coding agents, and agentic models

Keep changing the app you built with AI, and see that each change works. Your own coding agent makes the edit; VibeRaven shows the steps, your checks, the running app and the diff, with Undo. For Vercel + Supabase apps from Lovable, Bolt, Cursor or Claude Code.

Benchmark suite for evaluating agent and LLM memory systems

The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.5.1 Stable.

An 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

A hands-on course for learning PydanticAI - the Python agent framework built on Pydantic

AI agent (Claude Code + Codex) & system monitor for the Thermalright 9.16 LCD — native macOS

RunComfy AI media skills for Claude agents — incremental publish test

面向 AI Agent / LLM 工程面试的智能诊断 Agent，也能模拟面试、改简历

The open-source control plane for your personal AI workforce. Run your own AI agents. Your infrastructure. Your models. Your rules.

The local-first control plane for long-horizon coding agents: cross-session project memory (ContextDB), adaptive workflow routing, multi-agent teams, resumable overnight runs, and verifiable evidence — on top of Codex CLI, Claude Code, Gemini CLI, OpenCode, Hermes, Grok, WorkBuddy, Pi, ZCode, and Qoder.

A collection of free AI coding tools! :copilot:

The NestJS-native runtime for governed AI agents

Multi-agent memory governance demo using Caura + OpenClaw. Three agents (Sales, Legal, Admin) share one memory backend with hard fleet boundaries enforced at the query layer. Shows scoped writes, blocked recall, cross-fleet synthesis, and conflict detection.

simple, type safe, elegant command line framework. the CLI framework for agents

28 OSINT Agent Skills that turn Cursor, Claude & AI coding agents into a full open-source intelligence platform — reconnaissance, attribution, GEOINT, breach checks & due diligence. Ethical, sourced, passive-first.

🎯 CenterOS — The Lightweight AI Operating System! A simple, cloneable framework that turns your AI into a personalized system for automating your business, life, and everything else.

A Rust-native, multi-agent development cockpit for macOS — spawn isolated worktrees, run CLI coding agents in parallel, and review every change through a GitLens-grade Git UX.

A security-hardened container environment for running the OpenCode CLI in complete isolation.

browser-based PI agent: The Reasoning Engine of AI Employees

dshcloud：部署并托管 DeepSeek Harness (dsh) 实例的多租户平台，支持自托管或云端部署。Deploy and host DeepSeek Harness (dsh) instances — self-hosted on your own server or cloud-hosted: a multi-tenant platform with isolated Docker containers, persistent workspaces and resource quotas.

A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents

Agent skills from Xcode 27, packaged as a Claude Code plugin

Teaches AI coding agents to make clear, honest charts, and checks each one before you see it. For Claude Code, Codex, Cursor, and more.

Open-source, self-hostable, always-on personal agent with its own computer. Runs on Cloudflare Workers or Node.

先进且稳定的企业级智能分析平台；面向企业问数、洞察分析的Data Agent，基于数据分析方法论打造可审计、可治理、可复现workflow

A GUI workbench for Claude Code and other CLI agents · Claude Code 的可视化工作台（网页 + 桌面），也能驱动 Codex / Gemini CLI / Qwen / OpenCode 等 CLI agent

Eden (Nintendo Switch emulator) port for Xbox Series X|S with its own Direct3D 12 renderer, developed almost entirely by an autonomous AI agent (Claude). Experimental. Ships no games, keys or firmware.

Pre-deployment governance, identity auditing, and data-leakage scanner for Microsoft Foundry Toolboxes and autonomous AI agents.

Community GitHub Action for DeepSeek Harness — AI Code Review · CI Diagnosis · Auto Fix · Issue → PR

Battle-tested operating system for shipping product with LLM coding agents. 17-stage wave loop, two-reviewer gate, dual-document agent memory, full template library. Everything you need to turn agentic coding from vibes into a repeatable process.

Grapheteria: A structured framework bringing uniformity to agent orchestration!

Not recommended. Too simple for the AI Coding Agents