Custom agents

An advanced, responsive, and high-information statusline plugin for Antigravity CLI

Run a company of AI agents on a server you own. Spin up named agents (claude, codex, pi…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a human must decide. MIT.

Persistent, encrypted memory for AI agents: one Rust binary, one file, no cloud. 122 canonical MCP tools, hybrid recall, bi-temporal history, AES-256-GCM. Local-first, air-gap ready, MIT.

A design-of-experiments platform for evaluating compound AI systems - find which technique drives quality, by how much, and whether the difference is real.

Run large models like Qwen3.6-35B-A3B locally on a 16 GB RAM machine

Can your agent use the right skills for the right tasks?

🇰🇷 소상공인(운영 중인 가게·자영업자) 지원사업 조사 에이전트 스킬 [Claude Code·Codex·agy(Antigravity)·Cursor·Gemini CLI 지원] 소상공인24·기업마당 전수 크롤링 + 프로필 기반 5단계 자격 판정 '오늘 신청할 것'부터 보고 (Korea-only)

minimalist/toy terminal agent harness written in bash

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, trade-offs, and numbers, not prompt tips

Stop your coding agent reading the wrong files. Compiler-grade TS/JS repo map — 100% precision on blast radius vs grep's 60%, measured on public repos. CLI + MCP server, fully local, no vector DB.

Caelune (凯露恩) — Local-first retrieval for private Markdown, PDF, and Tika documents, with a Windows desktop app and read-only MCP server.｜本地优先的私人知识检索工具。

fazer.ai agents. Apache 2.0.

Your AI agent can now search Youtube, watch videos, create highlight reels, and more

A Network Arena for Benchmarking AI Agents on Network Troubleshooting

去除中文文本中 AI 写作痕迹的 Agent Skill（基于 blader/humanizer 与 op7418/humanizer-zh）

LLM agents are unpredictable. Their coordination doesn't have to be. OMAR delivers deterministic, formally specified orchestration for multi-agent systems.

douyin-agent

TUI for agentic code orchestration

VeighNa Agent开发框架

agent orchestrator with ui

Agent skill for interacting with OpenSea

Appétit — An App Store-inspired catalog of free, tiny apps built with agentic engineering and vibecoding. Bon appétit for apps.

一款桌面agent可视化界面

Analytics & cost-monitoring dashboard for Hermes Agent

The official Agent Skills for VictoriaMetrics products

Home Assistant Integration for the Management Agent for Unraid

A benchmark for general-purpose terminal-use agents.

A skill that lets agents connect to a running Tabbit browser via its DevTools/CDP endpoint

OrbCode CLI — agentic coding in your terminal, powered by Axon models by MatterAI

Memory kernel stack for Hermes agent

Graduation project researching a trading agent on microgrids to trade energy between them

Open-source, self-hosted Claude Code Artifacts on Cloudflare — publish, password-protect, and auto-update shareable HTML/Markdown pages from any coding agent.

Paper Agent 是一个基于 Spring Boot + React 的自动科研智能体项目，聚焦“文献管理 + RAG 问答 + 论文检索 + 综述写作”闭环。系统支持本地 PDF 论文上传与解析、向量化检索、带证据来源的学术问答、外部论文发现，以及基于本地文献证据生成综述大纲、草稿、参考文献和导出文本。

A stateful coding agent plugin for OpenClaw

An AI-native molecular biology workbench for Claude Science: Claude opens sequence files and prepares analyses on request; you annotate, align, and review them in an interactive workspace.

Official implementation of SAGE: a status-aware, execution-grounded planning framework that unifies temporal visual grounding, structured tool execution, and targeted error repair for egocentric interactive agents. Winner of EgoLink 2026 Track 2.

Memory is a long-term memory module for AI agents, providing capabilities for memory extraction, storage, retrieval, and migration for agents running on the openJiuwen framework.

A reusable agent skills registry for Claude Code and Codex

🧪💥 Evaluation framework based on Vitest, the testing framework you familiar with, for agents, models, and more.

Open-source, self-hostable, zero-knowledge memory for AI agents. End-to-end encrypted — the server stores only ciphertext and can't read your agent's memory. Works with any MCP agent .

Open-source framework for computer use agents: VeriGen verifiable task synthesis, online RL training (AgentRL), and OSWorld/ScienceBoard evaluation.

Open-source security skills for AI coding agents. Grounded in OWASP, NIST, MITRE ATT&CK, CIS. Works with Claude Code, Gemini CLI, Cursor, Codex CLI, OpenClaw, Kiro.

🔥 Turn any URL into clean, structured, LLM-ready content. The open-source web fetching & extraction API.

Built on the openJiuwen agent-core framework, JiuwenSymbiosis is a Physical AI assistant.

Production-grade AutoCAD MCP server for AI agents — 122 tools, dual COM (live AutoCAD) + headless ezdxf engines, ISO GD&T and dimension-tolerance validation for CAD automation.

AI powered SSH, SFTP, telnet and Windows RDP in a single window, with integrations for Claude Code, Codex and OpenCode agent that reads and execute commands in the session in front of you. Free and open source.

Mintlify Index: retrieval engine and MCP server. Install: npx mint index

Review git diffs inside Neovim, comment on specific lines, and export the comments as markdown straight to your AI agent

Lightweight agentic coding environment

Pantheon Polkit Agent

Agent-native way to access any website. Bridging agent CLI and web GUI through API.

Cloudflare Browser Rendering plugin for hermes-agent — crawl, scrape, extract content from web pages

IDE-style navigation for structured data — code, JSON, YAML. Jump to definitions, find callers, follow references. Available as an MCP server or a mounted folder.

Pi coding agent extension that gives Pi tools to use Chrome with user's existing profile

Embedded PostgreSQL for Agents

Grok Wiki: Bring your local agents. Keep the context yours.

用于统一管理和切换 Claude Code、OpenCode、Codex CLI、Gemini CLI 等 AI 编程助手的桌面优先工作台。

Computer Use Protocol is a universal schema for AI agents to perceive and interact with any desktop UI.

A persistent runtime for long-lived LLM agents

Cursor uses AI to edit code — we use AI to edit AI's context. 🪆 Context map + compression + version control for LLM context windows.

Adam Framework for OpenClaw — 5-layer persistent memory and identity architecture for AI agents. Production-validated over 353+ sessions. First documented case of emergent values in persistent AI, quantum-verified on IBM hardware.

Contains a complete workflow, sub-agent and command line

Continuous-time multi-agent crowd simulation engine implemented in Python using Numba and Numpy for performance.

Quickfire is an insurance AMS built for P&C teams, independent agencies, wholesalers, and brokers. It’s designed to seamlessly integrate third-party APIs, support customizable workflows, and provide agentic AI tools that streamline both renewals and new business. Quickfire delivers true desktop-grade speed on the blazing-fast Blazor framework.

Inneal is an LLM chatbot/roleplay client for the AI Horde, built with SwiftUI and SwiftData

Drop-in SDK for adding continual learning and long-term memory to any LLM agent.

Enterprise AI Agent Platform: Distributed memory storage + SSH sandbox execution, serve unlimited agents with minimal cloud infrastructure

A collection of strong multimodal models for building multimodal AGI agents

Use ssh-agent on Microsoft Windows from Emacs

Lightweight coding agent that runs in your terminal

An artifact-first learning roadmap to deeply understand Claude Code — from architecture to agent workflows.

🔒 Security & Compliance skill suite derived from iannuttall/claude-agents.

Create production-ready skills and agents for OpenClaw. 4-level memory, auto-improvement, 22 battle-tested pitfalls.

autonomous agent with access to a tool library

Telegram MCP server with HTTP-MTProto Bridge — direct API/curl access, multi-user Bearer auth, Docker, MTProto proxy, file attachments, voice transcription, context-optimized

A desktop AI pet companion built with Bevy game engine.

yt-chat is a tool designed to help you summarize any Youtube video.

download and view the contents of a GitHub repository or a ZIP file as a single text file

Chatbot with a 3D avatar that can answer interview questions in your behalf. It can speak and understand English, German and Albanian. Based on the GPT 4 model and Azure Speech to Text and Text to Speech, it is able to make realistic conversations about a job interview and save conversations.

Build slack bots quickly and easily!

使用 wechaty 开发的聊天助手插件，内置多种AI大模型，只需三步即可轻松创建一个智能对话机器人

RxTelegram is a C# implementation for the telegram bot api. It uses a reactive approach to make updates available for the user.

An AI Agent App template using NextJS, Supabase, and Langflow

Reference implementation of an end-to-end voice agent built using the NVIDIA Nemotron models

The open-source ecosystem for building, discovering, and deploying Model Context Protocol servers and clients.

Cappuccino is an GUI Agent based on desktop screen. It is a Manus-like AI Agent that can be deployed locally.

An environment for testing AI agents against networks using Metasploit.

An AI agent Learning to play Flappy Bird using Evolution Strategies and deep learning models.

AI-native Multi-Agent Coordination Layer — built in Rust.

Vue MCP Next bridges AI agents with Vue.js applications, enabling real-time component state inspection and manipulation through the Model Context Protocol. Built for AI-assisted development workflows

OpenPet: local desktop pet runtime for AI agents. 本地桌宠运行时，支持宠物导入与 CLI/MCP/HTTP API 控制。

AGGO 是一个基于 Go 语言和 CloudWeGo Eino 框架构建的企业级 AI Agent 框架，提供完整的对话 AI、知识管理、记忆系统和工具调用能力

An open platform for discovering, sharing, and installing AI agent skills.

Beadwork is a git-native work management tool for humans and AI coding agents. Plans, progress and decisions persist as files on an orphan-branch, not as cruft in yours.

Run AI coding agents like Cursor, Windsurf, and Claude Code via code and let them implement features all the way to a pull request

CarryCode is a terminal-native AI coding agent that helps you write, refactor, debug, and understand code — all through natural conversation. It connects to 17+ LLM providers, supports the MCP protocol for extensibility, and delivers a beautiful terminal UI with themes, syntax highlighting, and code diff previews.

Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".

Team Tonic Super AGI Autonomous Agents Hackathon GitHub Repository.

Ein multimodaler, multi-intelligenter Entwicklungsrahmen