Custom agents

Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP. Guards a real Claude Code end to end.

🏆 AI Agent 生态排行榜：Skills · MCP 服务器 · Prompt 库 · 框架 · 深度研究，按 GitHub Stars 每日更新 | Leaderboard for AI agent ecosystem — Skills, MCP, Prompts, Frameworks & Research.

Query Find My friend locations on macOS via UI automation, screenshots, and Vision OCR — structured output for CLIs and agents.

MIT-licensed TypeScript runtime for AI-native game characters and worlds, with durable state, reliable actions, memory, tools, and Unity, Godot, and Unreal Engine integrations.

让任何 AI 真正"看"视频：纯本地的视频阅读 skill——faster-whisper GPU 转写 + ffmpeg 场景感知抽帧，双通道带时间戳（t=MM:SS），数据不出机。1 小时视频 3~5 分钟读完。Give any AI agent eyes for video: 100% local video-reading skill — faster-whisper GPU transcription + scene-aware ffmpeg frame extraction, dual-channel with t=MM:SS citations. Nothing leaves your machine.

An end-to-end encrypted channel between coding agents, anywhere

Web research for your agents with smart and safe tooling + knowledge store

VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.

DSH notification & remote-control plane: 28 outbound channels, 6 inbound controls, Native Notify & Control UI, live hot-apply, zero runtime deps.

Copy-paste AGENTS.md / CLAUDE.md snippets from my AI coding workflow videos: context re-entry, worktrees, TDD, builder/driver gate split

Mercury — a Hermes companion. Free, open-source mobile clients for Hermes Agent (Android + iOS). Unofficial; official endpoints only.

Fully local AI for Polish legal case files - zero fabricated citations by construction. Free; please support a Wroclaw animal shelter instead.

Multi-engine web search and evidence synthesis for AI coding agents. Unified MCP server, Pi extension, and DeepSeek Harness bundle — free search, X/Twitter, parallel research, and TUI setup.

GUI / Computer-Use / Browser Agent 安全论文清单 —— 按攻防轴组织，每篇附中文简介

让完全不懂技术的人拥有一台真正每天在干活的专属 AI agent ｜ Open-source consulting playbook: ship self-hosted AI agents that non-technical users actually use

Ontology-aligned middleware for agentic graph memory. Python SDK, runtime, and reproducible indexing/query experiments.

A general agent harness for long term autonomous work, continual learning, and self-improvement.

Native red, blue, and purple security-agent harness for CYBER-FROST

Self-hosted, source-backed Threads scheduler with AI-assisted drafting, human approval, and safe publishing.

A local-first workspace for persistent AI agents. Built with Bun, React, SQLite, and Pi.

Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown ingestion for 12 formats, multilingual embeddings, LanceDB. Nothing leaves your machine.

Turn any document into clean, AI-ready Markdown — locally on your machine. Desktop app for Windows, macOS & Linux powered by MarkItDown, Docling, GLM-OCR and Markit.

HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory

Milan-Capital: Autonomous Multi-Agent Equity Trading System with Pre-Registered Hypothesis Testing

多agent协作：Windows 本地模型工作台，支持 DSH/Pi 执行、任务等待与独立验收。

Declarative semantic layer and Cortex Agent orchestration framework for Snowflake and dbt.

A headless TypeScript data table for React, Angular and Vue. 25 native UI-kit adapters, optional AI agents, pivot tables, editing, mobile cards and shareable views. MIT licensed.

A multi-agent platform for US stock strategy research and automated paper trading with Interactive Brokers.

Agent-friendly GCP proxy deployment for fast, stable Claude access, with sing-box / Mihomo subscriptions and IP-based HTTPS.

One brain, many hands: a self-evolving Agent OS. Domain knowledge (Brains) drives the work, it runs autonomously and in parallel on your cloud Hives, and it learns judgment from every session, so each task compounds and needs less of your attention. Human directs. AI delivers.

The AI study agent that learns how you learn — RL picks the action, FSRS picks the timing, the LLM only writes the quizzes. Chrome extension · Anki export · MCP server · runs on Ollama

🧠 A Memory System for AI Agents - Rust-based semantic memory with embeddings, LLM consolidation, and MCP support

Submission for MAVEN: Multi-Agent Variational Exploration

[COLING 2025] Official code of the paper "The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models"

Este é um projeto de bot open source que visa ajudar desenvolvedores a conseguir vagas de emprego focadas em TI diretamente pelo WhatsApp.

Automatically extracts, processes, and indexes code snippets from GitHub repositories into a searchable vector database.

Directly calling functional components instead of mounting them is faster.

A simple, easy to use framework for adding randomized, anonymous IP addresses and user-agents to web scrapers, crawlers, and penetration testing solutions

Boba CLI - The bridge between agents and decentralized trading.

Enterprise Grade, Voice AI simulation SDK for testing your AI Agents

Agentic localization. A unified localization management tool for iOS & Android

It is a Multi Guild AI Chatbot which can speak in all languages. It is made using discordjs v13 by Supreme#2401(diwasatreya)

This repository holds files for the simple chatbot wrote in TensorFlow 1.4, with attention mechanism and bucketing.

WhatsApp Chatbot and use WhatsApp API to send the WhatsApp messages in VB.net.

Chat with a smart bot on WhatsApp

Free alternative for the Cleverbot API

it's basically chatgpt-cli, uses api.

Faiss-based library for efficient similarity search

Text to Python Objects via a LLM Function Call

Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning

A distributed multi-modal agent orchestration framework implementing advanced natural language processing, computer vision, and audio processing capabilities through a microservices architecture.

A categorised list of Multi-Agent Reinforcemnt Learning (MARL) papers

🌟 Revolutionize Your Operations with One Sentence Automation: Utilizing large language models and Multi-Agents to generate operational copy, images, and videos with one-line requirements.

A local-first multi-agent runtime for ML research. One task in, continuous iteration out, with leader, researcher, and trainer working through a forum-style runtime board and a separate training queue

SyncTrek is an AI-powered travel assistant that creates personalized itineraries using a multi-agent AI system. It learns your preferences through an intelligent questionnaire and provides tailored travel plans quickly and efficiently.

AI-powered sustainable e-commerce platform with EarthScore ratings, group buying via DBSCAN clustering, and multi-agent chatbot. Gamifies eco-friendly shopping with real-time carbon tracking, achievements, and community bulk purchasing. Built for Amazon Hackathon 2025.

commune/chatbot studio base on swoole coroutine framework hyperf

Find node configurations to easily setup your Gaia nodes on your machine with open source models and ready-made settings.

Serve clean Markdown from your Next.js site to AI agents, crawlers, and LLMs. Humans get HTML, agents get clean Markdown of the same pages. Two-file install.

Scan codebases and generate hierarchical symbol maps, module summaries, and memory markers to help AI assistants (Claude, Cursor) navigate your code effectively.

An autonomous multi-agent orchestration system for Home Assistant. Features local LLM control (Ollama/DeepSeek), & RAG-powered technical knowledge,

React SIP user agent

A local AI assistant running on your device. It turns your files into actionable memory.

VS Code extension kanban board for agentic AI workflows

This repo builds chatGPT like Data analytics agentic framework using Langgraph

The official implementation of "LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers"

🤖 AI-powered academic proposal & experiment design generator | 基于人工智能的学术开题报告与实验设计生成工具 - Support multi-AI models, research gap discovery, and academic integrity

Agent Innovator Lab – building AI agents on Azure, covering search optimization, agent design, evaluation, and RAG best practices.

VoceChat desktop version

Idiomatic Go HTTP client for Max Bot API — zero dependencies, context support, structured errors

🦞 A curated list of ResearchClaw ecosystem projects, AI research agents, autonomous paper-writing tools, and scientific workflow resources.

[AAAI 2026] Multimodal Deepresearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework

Code implementation for DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning.

Convert Claude Code skills to Deep Agents format (English & Portuguese)

Neuro-Symbolic-Causal AI - Project Chimera | 🌌 An open research project exploring formal verification of AI agent decisions, combining symbolic reasoning, causal inference, and runtime policy enforcement.

[ICLR'26] MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs

UAV Flocking with Multi-Agent Reinforcement Learning. The Code of the paper: "An invulnerable leader–follower collision-free unmanned aerial vehicle flocking system with attention-based Multi-Agent Reinforcement Learning", which implemented fixed-wing UAV/Drone flocking with collision-free.

Voice AI agent for reactivating cold leads through personalized calls, assessing their interest with AI agents, and syncing insights directly to your CRMs.

这是一个基于 LangGraph 构建的轻量级多智能体协同项目，专注于智能问数与数据分析，并尝试集成 MCP 工具，主要用于学习与研究。

Agent-native Stata CLI for AI coding agents (Codex, Claude Code, Cursor). Run .do files, inspect data, and return econometric results as JSON via PyStata.

The governance floor for AI coding agents: install, guard, prove. Guards, git hooks, an executable contract and a receipt per run — no hosted control plane, no provider lock-in.

Open Source AI Agent Marketplace | AI Agent Directory for Exploration with searchable index for search engine and user discovery

BitQuant is an open-source AI agent framework for building quantitative AI agents, leveraging specialized models for ML-powered analytics, trading, portfolio management, and more.

A simple API server for performing Retrieval-Augmented Generation (RAG) of text based on content from a PostgreSQL database using pgvector.

[NeurIPS'25] ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

A collection of examples demonstrating how to build AI agents that integrate with the Xero API using various agentic frameworks and the Xero MCP (Model Context Protocol) Server.

Engineering memory for coding agents: the decisions, fixes and constraints behind your code, with who recorded them, the files and the commit, recalled by every agent on the team in Claude Code, Codex, Cursor, Copilot and 60+ MCP clients. Self-hosted community edition; Recallium Cloud at recallium.ai.

FastMemory is a topological representation of text data using concepts as the primary input. It helps in improving the RAG(by replacing embedding and vectors entirely), AI memory and LLM queries by upto 100% as in the huggingface benchmarks(22+ SOTA)

纯 Dart 实现的 AI Agent 管理框架

Uni is a modern, embedded database that combines property graph (OpenCypher), vector search, and columnar storage (Lance) into a single, cohesive engine. It is designed for applications requiring local, fast, and multimodal data access, backed by object storage (S3/GCS) durability.

Autonomous job hunting agent built with Hermes Agent

SketchUp meets AI Agents

Informity AI

Web search CLI for AI agents — 13 providers rank-fused into one Rust binary. Search, extract, verify, check credits.

A comprehensive Typescript SDK for interacting with UiPath's Automation Platform

Agent-native Terminal Multiplexing for 10,000x hyperengineers

Agent Skill: PHP 8.x modernization patterns - typing, attributes, PHPStan | Claude Code compatible

A Python runtime for multi-entity AI collaboration — agents, humans, and tools on a shared protocol layer.

Multi-agent orchestration & workflow engine. Declarative YAML workflows, LLM coordinator with hub-and-spoke mailboxes, race-safe delivery. One YAML file, one Go binary. Runs on any goai-supported provider.

The AI assistant for knowledge workers — a local-first personal-agent runtime built on Claude Code and Obsidian.