Custom agents

Open Agent Spec (Agent Spec) is a framework-agnostic declarative language for defining agentic systems. It defines building blocks for standalone agents and structured agentic workflows as well as common ways of composing them into multi-agent systems.

[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

68 plug-and-play, best-practice product management skills for AI agents: 30 Triple Diamond phase + 11 foundation + 12 utility + 15 tool (Foundation Sprint + Design Sprint). Plus 6 sub-agents, workflows, 200+ output samples, guides, and CI-enforced contracts. Apache 2.0.

Skills for Claude Code — deep-research: systematic academic literature review

The agent responsible for conducting the agent evaluation

[NeurIPS 2026] SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perception of web & desktop applications.

V4 Flash 神模式 (opencode-go)：让 opencode-go 的 DeepSeek V4 Flash 从鬼模式切换到神模式的 dsh agent preset

Desktop app for designing parametric 3D models in CadQuery together with the coding agent of your choice

🤖 An AI agent framework built with Rust.

Local-first issue tracking for AI-assisted software work, with an agent-friendly CLI and human-facing TUI

Multi-agent orchestration for Claude Code — decompose tasks, coordinate agents, visualize everything in a rich terminal UI

Self-hosted project management • Customizable boards • Cross-project workload and flow analytics • Calendar/Agenda • Sticky-note wall • Imports/Backups • Email notifications • MCP/Agent automation

A workspace where people and multiple AI agents work together.

Websites, ready for AI. Turn website tasks into verified CLI and MCP actions, with a local dashboard and 20 languages.

Tiny local-first AI harness: any model, MCP and Agent Skills, natural-language CLI. Zero dependencies. MIT.

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

MindSQL: A Python Text-to-SQL RAG Library simplifying database interactions. Seamlessly integrates with PostgreSQL, MySQL, SQLite, Snowflake, and BigQuery. Powered by GPT-4 and Llama 2, it enables natural language queries. Supports ChromaDB and Faiss for context-aware responses.

An example of multi-agent orchestration with llama-index

Multi-agent pipeline coordination: Linear, DAG, and Debate modes for AI agent orchestration

Vault SSH Agent is used to enable one time keys and passwords

Build reliable AI Workflows and Agents with humans in the loop, structured outputs and durable execution.

PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Distributed RL/IL code for Multi-Agent Path Finding (MAPF)

The most agent-ergonomic browser automation

The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, and connect telemetry, services, and business objects in one object graph.

Registry of agents implementing the Agent Client Protocol (ACP)

Daily-updated Top 100 Agent Skills rankings — installs, growth, and social buzz aggregated from skills.sh, ClawHub, Tencent SkillHub, GitHub, X and 10+ communities. Open data (CSV).

Anonymous Multi-Agent Path Finding (MAPF) with Conflict-Based Search and Space-Time A*

A customisable 2D platform for agent-based AI research

It is a medical chatbot that will provide quick answers to FAQs by setting up rule-based keyword chatbots.

📱 ClawApp — OpenClaw AI 智能体手机聊天客户端 | 流式对话 · 图片收发 · 工具调用 · PWA + APK | Mobile chat client for OpenClaw AI Agent

The ADE for AI agents. Automate everything else. Do your true work.

Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.

Build AI agents grounded in a creator's documents, audio, and video.

This repository contains advanced LLM-based chatbots for Q&A using LLM agents, and Retrieval Augmented Generation (RAG) and with different databases. (VectorDB, GraphDB, SQLite, CSV, XLSX, etc.)

Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment

The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it, with all the best practices already in place.

VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.

Compile agent conversations!

Smithers is an agentic workflow framework for defining workflows in simple TypeScript configuration files and executing them quickly, durably, and reliably

Your AI agent army, commanded from Slack/Discord/Telegram/Wechat/Lark. Stream Claude Code, OpenCode, or Codex in real-time — from anywhere.

Clipboard Conqueror is a novel copy and paste copilot alternative designed to bring your very own LLM AI assistant to any text field.

A platform designed for building enterprise-grade, multi-tenant products using Azure, .NET, React, TypeScript, Infrastructure as Code, etc.

RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.

LMS SaaS app featuring user authentication, subscriptions, and payments using Next.js, Supabase, and Stripe — also integrates Vapi AI voice agent for seamless, interactive learning sessions.

Experimental Excel sidebar agent add-in. Multi-model. Powered by Pi.

ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.

Control any coding agent on any device — from your phone.

A cautious, explainable AI-like text risk analyzer for local workflows and coding agents.

100% free, open-source personal agents for your messaging apps, tools, and services

Open, source-backed catalog of computer-use agents: reviewed papers, GUI models, datasets, benchmarks, tools, and reusable JSONL/SQLite data.

Large Language Models for All, 🦙 Cult and More, Stay in touch !

AI Powered Search and Chat for Orgs - Think ChatGPT meets Google Search but powered by your data.

Your new Telegram buddy powered by transformers

Ultra-lightweight AI Agent

Keep your secrets hidden from AI agents.

一个通用桌宠 Agent 框架，能导入自定义角色包，并让角色感知屏幕内容与系统事件，根据用户当前场景主动做出自然反应。

A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository.

A tiny macOS app that turns Caps Lock into a physical keep-awake switch for closed-lid MacBook work.

A local-first personal knowledge layer for AI agents. Build evolving knowledge spaces with LLM Wiki, knowledge graphs, and agent workflows.

Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning

AI Agent Orchestration Platform

A Unicode canvas for humans and AI. Draw diagrams, interfaces, and slides as editable text.

Operant Beta：以多模型分工、按需通信、分层审批和经验复用为核心设计，在本机组织可追溯的 Agent 协作，并通过模块化架构扩展能力。

客服机器人，Chinese Retreival chatbot（中文检索式机器人）用到的一些QA模型，基于tf-idf，lsa，cnn，transformer，bert等

HF CLI extension to run local coding agent powered by llmfit and llama.cpp

Measuring and evolving with the frontier of agent work

Universal mobile devtool for Agents & Humans - control iOS Simulators, Android Emulators, and real devices from a single dashboard and CLI

Run parallel research agents with any model

Bops: a team of AI bots that run your business ops, each with its own computer, email and phone number. bops.bot

one line code, satisfied all your ChatGPT imagination✨✨✨

TUI / CLI config manager for agentic harnesses (Amp, Claude Code, Opencode, Goose, Copilot CLI, Crush, Droid)

potato: the portable annotation tool

从零开始的Agent学习之路

Natural language → ComfyUI workflow JSON. 34 built-in templates, 360+ node definitions, auto model download. Supports txt2img, img2img, txt2vid, img2vid, audio, 3D generation across SD1.5/SDXL/SD3/FLUX/Wan2.2/HunyuanVideo/LTXV/Mochi/Cosmos + LLM integration. Works as a skill for Claude Code, Cursor, and other AI coding agents.

pool is Poolside’s coding agent that runs in your terminal or integrates with any ACP-compatible editor

This repo contains different Soul.md files each file is different and allow your agents to behave in unique interesting personality.

面向长程购物 Agent 的可复现后训练

Monitor and drive your herdr agents from menu bar, phone, or Telegram. Zero config locally. Free tunnel for remote. No Tailscale needed.

Animated 3D robot heads for React: TV-headed bots with LED faces that show what your agent is doing.

Native Quiet Home launcher, reversible cleanup tools, and an agent-readable guide for the Samsung U8000F running Tizen 9.

This project accepts excel files as input which contains the description of a Knowledge Graph (Vertexes and Edges) and convert it into an in-memory Graph Store. This project implements APIs to search/filter/get nodes and relations from the in-memory Knowledge Graph. This project also provides a dialog management framework and enable a chatbot based on its knowledge graph.

An auto-scaling cluster of build agents running in your own AWS VPC

ChatGPTやCopilotなど各種生成AI用の「日本語]の Prompt のサンプル

OpenClaw Managed Agents — the open alternative to Claude Managed Agents & ChatGPT Workspace Agents. Any model, any cloud, open source.

An intuitive interface to create, orchestrate, and monitor Claude-based code agents for automated development workflows.

Official Code Release of SAGE: Scalable Agentic 3D Scene Generation for Embodied AI

Give your Hermes agent the web as real sources, never a made-up answer — multi-provider search and extraction with an optional local, key-free DonSeTch option.

Synchronized multi-client state for AI agent sessions

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

Persistent, searchable engineering memory for AI coding agents. Saves ~50% tokens and ~30% time while planning

An LLM-powered multi-agent framework for simulating interactive, evolving story worlds.

Open Instinct: an open-source Instinct. A personal agent you text on iMessage, with its own computer and a trusted network of other agents. Built on Pi, Inkbox, Maritime and Composio.

Google AntiGravity IDE for Vibe Coding

🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!

🗿 FableCodex is a Codex-style coding agent workflow that plans like Fable.

Give Claude Code's ultracode mode to ANY model you already pay for. A tiny local proxy + one config.json. Point your AI at AGENTS.md and it sets itself up.

Your agent reads the rules. This checks whether it followed them.

Metis is a coding agent that boosts AI/LLM coding performance by 50% QQ群: 801193315