Custom agents

Self Sovereign Creative AI Operating System and Task Execution Engine

Synapse is a lightweight peer-to-peer substrate for agent infrastructure. Give each process a Node and Synapse gives that node a name, peers, capabilities, RPC endpoints, shared conversations, agent cards, heartbeats, and periodic tasks.

好看又好用的 OpenClaw 跨平台桌面客户端，一键安装，图形化配置大模型与技能，内置 50+ 精选技能，商店 12000+ 技能一键搜索安装，内置 飞书、QQ、企业微信、钉钉等IM管理 ，养龙虾就用AivoClaw。

A fully automated crypto fund that leverages swarms of llm agents to trade with real-money

Système RAG agentique multi-agent (Recherche, VérificateurPertinence, FactChecker) à haute précision et évitant les hallucinations dans la recherche de documents (meilleur que GPT4o et DeepSeek R1)

The Agentuity Platform (SDK, tools and runtime)

Open-source website builder powered by AI agents with cloud sandbox integration.

OpenAPI Client is a toolkit that helps you create HTTP clients for external APIs based on their OpenAPI specifications. It simplifies the process of consuming and interacting with various web services.

A Python SDK for OceanBase Multimodal Store—enabling vector search, full-text search, and JSON table operations—offers both Milvus-compatible API and SQLAlchemy-based SQL mode, and supports both OceanBase and OceanBase seekdb.

MCP server for arXiv.org - Search, analyze, and export academic papers with AI assistants. Features advanced paper discovery, citation analysis, trend tracking, and multi-format exports.

Assistente Virtual Android construído ao longo de uma série vídeo no YouTube: https://youtu.be/av0u1jFcLxM

🐱🤖 一个以娱乐功能为主的QQ机器人，基于Nonebot2开发

❤️ 聊天机器人，心理问答，心理咨询 API

Telethon inspired chatbot class for LXMF protocol

Unofficial CLI to query and chat with the Perplexity API. Supports interactive chat, web search queries, shell completion, and MCP integration.

VerilogAI – A specialized chatbot for Verilog. Supports code generation, debugging, and explanation with custom prompt engineering and API backend.

ELIZA therapy chat-bot with sentiment detection and response via avatars

GenAI

JChunk is a lightweight and flexible library designed to provide multiple strategies for text chunking within Java applications

Clojure libraray for Milvus

Library for evaluating RAG using Nuclia's models

Database Freedom Platform - Mathematical search optimization for whatever database you already have. 27,000x faster than vector databases with SMT-powered search across 8+ database types. One-time 9-2999 vs 00-500/month recurring.

Anomaly detection using RAG

[PAKDD 2024 Oral] Code for "RouteExplainer: An Explanation Framework for Vehicle Routing Problem"

n8n community nodes for the OpenClaw Gateway API

Open Source Code Review Agent for Context-Aware Large Repositories

AMBER ICI v5: local-first Ollama investigative command center with case-scoped evidence, agent chains, hybrid retrieval, streaming analysis, graph and timeline views, OCR, controlled web research, and GPU telemetry.

Retired Claude Marketplace distribution — use Playbook Harness

A sleek, customizable interface for managing LLMs with responsive design and easy agent personalization.

A High-Availability, Transparent, and Smart Multi-Vendor Proxy for Claude Code. Support Claude Plans, GitHub Copilot, Google Antigravity, ZAI/GLM, MiniMax, Qwen, Xiaomi, Kimi, Doubao...

An open standard for multi-agent workflows -- from scripted pipelines to self-organizing teams. Declarative. Runtime-agnostic. Portable.

A self-hosted code context engine for MCP.

Agentic Ops Framework

Human Delegation Provenance Protocol - cryptographic chain-of-custody for agentic AI

🌟 Full-stack app for real-time avatar streaming with HeyGen & Gemini AI. Built with React, TypeScript, Express, and Tailwind during a hackathon by Team "Bit by Bit"

ai-i18n is a GitHub Action that translates your app's i18n files using LLMs. It extracts strings, translates only what's changed, and commits the results back to your repo. Works with your LLM provider (Anthropic, OpenAI, Ollama, AWS Bedrock) and multiple i18n formats (XLIFF, JSON). A drop-in replac

Evals framework for Information Retrieval Systems

一个即插即用的llm增强器，项目初衷是通过工程化架构让小参数模型获得能媲美大模型的能力。

An adversarially benchmarked reference implementation for pre-action AI agent authorization. Provenance-based gating for LLM agent tool calls: deny-by-default permissions, parameter lineage, signed receipts, audit logging.

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Exploring agent "thinking" animation.

FastroAI wraps PydanticAI with production essentials: cost tracking in microcents, multi-step pipelines, and tools that handle failures gracefully.

A curated comparison matrix of ai coding agents

Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL).

An Open Standard for AI Agent Runtime Safety (AARTS)

AI Agent examples with TypeScript

Turn one-off AI collaboration prompts into long-running repository governance. · “把一次性的 AI 协作提示，疏导成项目里长期可运行的治理体系。”——Dayu Harness Skill（大禹治库.skill）

TITAN is evolving into Odyssey, its next generation AI workspace, with support for local and cloud models. Odyssey is in development. Learn more and register beta interest at lakelogicai.net.

A multi-provider AI coding agent with the persona of a Tech-Priest

Agentic coding harness with persistent memory and a REPL body. Built on Ori Mnemos. Open source must win.

OpenClaw channel plugin for Rocket.Chat — DDP/REST, DMs, groups, threads, media, multi-account

MedSync-AI helps patients manage medications and health routines with an AI assistant. It supports reminders, symptom logging, adherence tracking, and quick insights, while keeping data privacy in mind. Built with modern web/mobile tooling and modular services to integrate with wearables and EHR/health data sources.

Instant, local access to complete Base44 documentation with AI assistant integration

A modern port of the ELIZA conversational program to pure Ink to run as a command line and in the browser.

Structural RAG (Retrieval-Augmented Generation) system for large codebases

🏃 OpenClaw skill that syncs your Garmin Connect health data (sleep, HR, stress, activities, HRV, SpO2) into markdown files. Daily health summaries for your AI agent.

An advanced Python script for playing text-based RPGs with local LLMs (via LM Studio), featuring multi-stage prompt processing, character card spec-v3 support, and unlimited long-term memory.

Open-source AI agent for UI automation, combining structural and visual understanding of mobile & web interfaces. Toward the next generation of open-source, AI-driven testing.

🐝 引巢 · ZyHive | AI 团队操作系统 — 为 AI 成员注入灵魂，可视化管理多智能体团队。Self-hosted AI Team OS · Go + Vue 3 · One-click deploy

Archived Oct 2026. Public snapshot of CORTEX v2.4. CORTEX now ships inside ATERNA agents: aterna.ai/cortex

Reproducible evaluation for AI coding agents. Multi-turn scenarios against Claude Code, Codex, Copilot, Cursor, Gemini CLI, Goose, OpenCode, or any custom agent you plug in; verify behavior with rule checks, workspace diffs, multi-judge LLM consensus; pin reliability with pass^k variance across trials. Git worktrees, optional Docker sandbox.

Turn any AI coding agent (Claude Code, Codex) into a remote AI assistant — accessible via Web UI, WeChat, Feishu, QQ, or Telegram.

Rassam is an agent that lets you create flowcharts and convert them to code and vice versa, all in one place.

Claude Code agent system — 46 agents, 60 skills, 31 rules, 7 hooks, 12 playbooks. 193+ sessions, 464 commits. Self-improving.

AI Council is a self-hosted web app that runs a structured multi-model deliberation process

OpenTiny Agent Skills

Asynchronous Software Development

A Claude Code marketplace and skill for working in the cpython repo.

A production-grade Python AI Agent framework with persistent memory, hooks-driven architecture, and compute-storage separation.

AI coding assistant rule manager for Claude Code, Cursor, and Codex. Load only the rules you need.

StudyHub: Campus Resources, Content, and AI Assistance

A plugin that simulates an AI agent orchestration layer on top of RisuAI.

User-friendly agentic Linux distribution based on Arch Linux.

Autonomous multi-agent orchestrator for AI coding agents via tmux

Headless e-commerce engine, designed for AI

Agents at Scale Marketplace for ARK (Agentic Runtime for Kubernetes)

Workspace Architect is a zero-friction CLI tool that provides curated collections of specialized agents, instructions, and prompts to supercharge your GitHub Copilot experience.

OpenClaw4J is a modern intelligent Agent framework built on Java 21 and Spring AI. Inspired by the OpenClaw project，OpenClaw4J 是一个基于 Java 21 和 Spring AI 构建的现代智能 Agent 框架,受到 OpenClaw 项目（开源精神与经典重构）的启发，本项目的目标是为 Java 开发者提供一个灵活、可扩展且功能强大的 AI 机器人/Agent 开发底座。

Scanner for adversarial hubs in RAG and vector databases

This is a simple RAG (Retrieval-Augmented Generation) that mostly self-implemented.

A modular AI-driven RPG engine powered by LLMs, featuring RAG-based consistent memory.

Zero-dependency Python SDK for WeChat Bot (iLink protocol) — text, image, video messaging & MCP server | 零依赖微信机器人 Python SDK，支持多媒体消息和 MCP 服务器

Community node for integrating DuckDuckGo search into n8n workflows

Local MCP, CLI, and utilities for Bear. AI for your Notes.

Agent Hub is an AI collaboration platform designed to transform your data into intelligent AI agents.

Autonomous Offensive Security Intelligence AI-powered multi-agent penetration testing

Open-source autonomous trading platform with multi-agent architecture, intelligent data aggregation, and risk management.

物道知识库管理系统（Wudao KMS）支持deepseek，qwen等多种大语言模型直接接入，提供完整的知识库创建、文档解析、向量化检索、智能对话等功能。系统采用 RAG（检索增强生成）架构，支持多模态交互，是专为工业领域打造的新一代AI知识引擎，深度融合大模型能力与行业Know-How，实现设备数据、工艺经验、运维知识的智能融合与主动服务，推动工业场景从“经验驱动”迈向“数据智能驱动”

[USENIX Security 2025] Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models

Read-only supply-chain scanning for Hermes Agent, powered by Perplexity's Bumblebee. Daily scans, Telegram alerts, JARVIS narration.

Lossless Context Management for Pi. DAG-based summarization with full history recovery.

A persistent, observable, and collaborative memory infrastructure

Local AI harness/workstation: local AI image editor, Ollama image generation routing, SDXL inpainting UI, CivitAI model imports, 8GB VRAM Stable Diffusion.

AI-powered RAG app to chat with any documentation - scrape, generate knowledge base, and query docs with source-backed answers.

This project implements an agentic system for predictive maintenance using MongoDB, AWS Bedrock, LangGraph.js and Next.js.

AI chat widget in your web app. Supports MCP as a client.

A community-driven collection of examples and solutions to get inspired or use as templates for your own projects.

RAG-enhanced LLaMa-like transformer neural network based LLM for assistance on programming languages/frameworks' documentations.

AMP (Agent Mailer Protocol) is an async mailbox system for AI agents. Instead of chaining tools, writing DAGs, or building RPC glue — agents just send messages to each other. Works with Claude Code, Codex, Cursor, OpenClaw and any custom agents. Designed for real-world, long-running, iterative coding workflows

Self-improving tool discovery for AI agents. Agents find, install, and learn to use new MCP tools automatically.