Custom agents

A Multi-Agent AI Tool that creates beautiful presentations with voice-overs 🎦🔥

[NeurIPS 2026 TTCL] Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement

[ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

Jarvis from the marvel universe

FTK Canvas Agent 是强大的多媒体处理自动化工具集，主打音视频处理与智能剪辑。集成多种先进 AI 技术，覆盖全流程，核心功能含 AI 剪辑、AI 特效、智能配音，自带横竖屏分类、场景切片等实用功能，支持零配置即用。其核心是连接 ComfyUI 实现 AI 服务，智能管理工作流，通过对话调用完成任务。

一个基于思维导图的智能思考辅助系统

MedAgentSim: Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions, MICCAI 2025 (oral and early accepted)

PII Masker is an open-source tool for protecting sensitive data by automatically detecting and masking PII using advanced AI, powered by DeBERTa-v3. It provides high-precision detection, scalable performance, and a simple Python API for seamless integration into workflows, ensuring privacy compliance in various industries.

GitHub Copilot: The agent awakens - Building applications with GitHub Copilot Agent Mode

DOI → PDF resolver with 7-source fallback (Unpaywall, S2, arXiv, PMC, bioRxiv, publisher, Sci-Hub). Multi-agent, zero-deps Python.

Ultimate Claude Code skill creator — design, scaffold, build, review, evolve, and publish production-grade AI agent skills

A lightweight embedded database engine that natively fuses vector search, graph, and document-oriented metadata within a single storage kernel — ready to use the moment data is written.

SuperNova is a Windows-first desktop AI Workbench that turns chat into traceable tasks. It combines a Tauri + React Workbench, Rust Product Runtime, typed protocol, and Process Kernel so actions can produce visible artifacts, runtime receipts, replayable evidence, and controlled workspace execution.

AI Agent 复刻精美网页的提示词合集：每个目录一份 prompt.md + 效果图截图，丢给 Claude/Codex/Kimi 即可生成对应网站

C-SSH 0.9.7 · Windows / macOS / Linux / Android · SSH, RDP, concurrent AI, server browsers, monitoring and encrypted sync. Manual updates only. 仅提示与手动下载，不强制更新。

The open-source harness for agentic structural engineering

一个会主动发现任务的智能体

Watchtower | Self-hosted AI security assessment, asset intelligence, and evidence workflows.

Apache Open Source Software Chat BOT

Hermes Agent CN desktop app, Windows-First, built with Tauri, Typescript and Rust. Isolated Hermes Agent core insides.

Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow

The open source AI app collection

Create API agents from OpenAPI Specs

A complete collection of 35 specialized sub-agents for Claude Code that enable end-to-end software development automation

[TMLR] LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects

LaTeX manuscript workflows with five agent skills, project diagnostics, reproducible builds and offline change review.

AIAgentCogNest(AI + Agent + Cognition + Nest)主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识、从零开始的智能体原理及落地实践教程。

An LLM-powered, autonomous coding assistant. Also offers an MCP and ACP mode.

iOS development ClaudeCode plugin for mindful token and context usage. Contains modular MCPs that group various Xcode/IDB tools based on your current workflow. [deprecated]

基于 Hermes Agent 构建的本地多 Agent 团队协作 Web 系统

GTM toolkit for AI agents. Research, intel, outreach, CRM.

真正记得住你、认识你、随你成长的 AI 长效认知记忆引擎 Long-term Cognitive Memory Engine for LLM Agents

Integrating AtomisticSkills into Agentic IDEs (Cursor, Claude Code, Codex, Google Antigravity, Hermes Agent, etc)

A lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.

web UI for Kubernetes clusters

Elixir-native framework for building runtime AI agents

Open-source video pipeline (clipper, script-to-video & more) — scout trends, clip long videos, generate captioned shorts, design motion graphics. Local-first, BYOK. AGPL-3.0.

Local-first Agent Runtime connecting LLMs to controlled tools, Chrome, desktop automation, MCP, context governance, and verifiable memory.

让AI Agent 做真正会思考，有判断的深度调研，而不是会摆信息的汇总报告。一个即插即用的 skill 文件。

Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model, by re-engineering the agent.

An esoteric programming language built to break LLMs and coding agents.

AI Roadmap 2026: a beginner's path through Foundations, LLM Engineering, Agents, Evaluation, and Production, with verified free resources and a mini-project per layer

自媒体运营 Skill（技能包）精选：小红书、抖音、公众号、视频号、B 站、X、YouTube、TikTok、LinkedIn 的选题、写稿、配图、发布和数据，千问、豆包、龙虾 OpenClaw、WorkBuddy、Claude Code、Codex 等智能体可用 | Curated agent skills for social media: Xiaohongshu (RedNote), Douyin, WeChat, X, YouTube, TikTok and LinkedIn

A command line tool for calling Gigabyte's RGB Fusion SDK

Examples of using Pipedream's MCP server in your app or AI agent.

A high-fidelity, general-purpose platform for embodied agent training and testing.

[ICLR 2025] The official implementation of paper "ToolGen: Unified Tool Retrieval and Calling via Generation"

The official Python SDK for the Agentica agent framework from Symbolica

A smaller, lighter-weight version of OpenClaw, natively multi-agent, compiles to Rust, and built on the Swarms framework and Swarms ecosystem. One API, unified messaging across Telegram, Discord, and WhatsApp with optional Claude-powered reasoning.

Open source AI agent for e-commerce

About AI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-agent research.vibe-trading ,trading-agents,ai-trader,ai-trading

An AI Agent that lives in your pocket. Local-first and privacy focused.

OpenCode AI Coding Agent 学习与实践教程：从 Agents、Skills、MCP、Context Engineering 到 AI Coding Workflow。

Local-first native macOS terminal with Vietnamese IME support and coding-agent observability

AI 求职助手 Skill：简历解析 → JD 硬性条件核对 → A/B/C 匹配评分 → 生成投递包（开场白、HR模拟、简历优化建议）。保留人工确认环节，不进行无人值守批量投递。

Open-source AI CLI and local MCP server connecting 25 clients—Claude Code, Cursor, Codex, ChatGPT, Hermes, and OpenClaw—to 2,000+ models/APIs, with OAuth and rollback.

This repository provides comprehensive resources for learning Agentic AI, including blogs, tutorials, and projects that will help you master generative AI and develop industry-grade applications.

Code, prompts, and resources for Gemini CLI: Code & Create with an Open-Source Agent

Simple Chit-Chat based on KoGPT2

DeepPavlov Dream is a free, open-source Multiskill AI Assistant Platform built using DeepPavlov Conversational AI Stack. It is built on top of DeepPavlov Agent running as container in Docker. It runs on x86_64 machines, and prefers having NVIDIA GPUs on the machine.

A collection of the the best ML and AI news every week (research, news, resources)

A real-time Agent framework for audio and video.

Terminal-first AI assistant for software engineering tasks (inspired by Claude Code v2.0.67)

C++ Agent toolkit - Pre-built binaries, visit: https://github.com/mtconnect/cppagent/releases Docker images available at https://hub.docker.com/repositories/mtconnect

An opinionated, Agentic Engineering toolbox powered by LLM Agents to solve problems autonomously.

A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.

Agent Framework Examples for Java and Kotlin Developers

BioAgents: An AI scientist framework for autonomous deep research in biological sciences. Multi-agent system combining literature analysis agents with data scientist agents to enable deep research automation through user feedback integration and iterative scientific discovery. Inspired by advances in Edison Kosmos, Sakana AI, K-Dense and others.

一个基于LLM的多Agent全流程漏洞挖掘项目，支持PHP、Java、Python、Go、Node.js等多种语言项目环境搭建、漏洞分析、漏洞验证、报告产出。支持多Agent并发高效率沟通完成漏洞挖掘任务。

Token-efficient browser MCP server — structured web pages for AI agents, not raw accessibility dumps

Agentic web-scanning engine with a terminal workspace, specialist tools, browser validation, reports, REST and MCP.

📝 Glyph is a private desktop workspace for notes, documents, and ideas, with Markdown editing and built-in AI tools.

SkillLens: a framework for studying model-generated agent skills across the full raw experience generation → skill extraction → skill consumption lifecycle.

Local guardrails for AI coding agents. Check proposed file changes and shell commands, block risky patterns, and return actionable feedback. Works with Claude Code, Codex, Cursor, Gemini CLI, and more

The middle manager for your agents

Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints autonomously

How to turn your Second Brain into a living research memory that your agents maintain. Workshop with slides, video and code.

A curated collection of offensive, defensive and AI/LLM security tools.

Connect your agent to the apps you already use - with or without Zapier.

Next-gen AI-native server ops panel with an in-workspace SRE agent. Crash self-healing, safe rollbacks, Docker/game servers, and local Ollama support.

Codex CLI and Claude Code CLI on your phones. No computers required.

Open-source MCP server that gives AI agents web search (SearXNG) and clean Markdown crawling of pages, whole sites and logged-in areas. Self-hosted, no API key. Firecrawl-compatible API planned.

Free, open-source anti-detect browser profile manager: per-profile fingerprint, cookies and proxy, Camoufox and Chrome engines, desktop app, REST API and MCP server for AI agents. Self-hosted alternative to GoLogin / MoreLogin.

Make your AI agents work as a team. Orchestrate jobs across Claude, Codex, Cursor, Devin, Pi, local models and more, or run a Software Factory: long plans, proven steps, safe merges. Carries your setup, tracks every cost.

WPS 笔记官方 AI Agent Skills 生态库：提供 30+ 场景化 Skill，通过 wpsnote-cli 与 MCP Server 让 DeepSeek Harness、灵犀、WorkBuddy、Claude Code、Codex、Cursor 直接驱动你的笔记知识库（读写、搜索、导入、排版与学习）。

Ralph Desktop - Start vague. Ralph Loop until perfect. A visual controller for AI coding agents that helps you brainstorm requirements and execute tasks through persistent iteration.

Still struggling with the high threshold or looking for the appropriate baseline? Come here and new starters can also play with your own multi-agents!

Multi-Agent Robotics Simulator

CRISPSR-GPT LLM Agent Public Welcome Page

Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP needed.

[ICLR 2026] VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.

Give your AI assistant eyes and hands in the Godot editor: scene editing, input injection, deterministic playtesting, and live game state for agents

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, model routing, edge inference, RAG, memory, multi-agent orchestration, security, and observability. 14 runnable proof-of-concept phases.

The harness for your harness. Local hooks, taste enforcement, and developer observability for AI coding agents (Claude Code, Codex, Cursor, Copilot CLI).

Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.

Official codebase for Spotter: Let the Embodied Model Lead, and the VLM Reflect for It

Desktop-first, open-source (MIT) application for running parallel agents, and multi-step custom workflows triggered by schedules, webhooks or events from tools like Linear and Sentry, across your already-used providers.

CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.