Custom agents

The most minimal AI coding agent, now in neovim

Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)

From PyTorch model to end-to-end TensorRT inference experience in two commands—AI-native, cross-platform, and built for the best possible user experience.

Compact DeepSeek Harness desktop host with a native SwiftUI iPhone Remote source preview.

WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.

The universal skill manager for AI coding agents.

A high-energy developer challenge that brings an e-sports twist to agentic AI with live AI Battles, asynchronous community challenges, GitHub-based submissions and more!

Semantic code navigation for AI agents

Youtu-RAG: Next-Generation Agentic Intelligent Retrieval-Augmented Generation System

从零走向AGI之路！！！旨在深入了解通用人工智能（AGI）的发展路径，从最基础的概念起，逐步构建完整的知识体系。涵盖AI Agent、RAG、MCP、具身智能、大语言模型、多模态、数字人、AI绘画、AI视频等！！

AI-Powered Game Development Team in Your Terminal

Telegram ↔ tmux/herdr/agterm bridge for Claude Code, Codex CLI, and Pi Agent. Monitor output, respond to prompts, manage parallel sessions. Control AI coding agents from your phone.

AI-powered advertising strategy engine for Claude Code. Build complete ad strategies, generate platform-specific copy (Google, Meta, LinkedIn, TikTok, YouTube, Pinterest), design campaign funnels, allocate budgets, and produce professional PDF reports. 15 skills, 5 parallel agents.

Multi-agent deep research for Claude Code — 7-phase pipeline with source triangulation and quality ratings

Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.

Let your AI agents use your Chrome, signed in as you, in background tabs. By Alexey Indeev · blog: read.aindeev.com · X: @AlexeyIndeev

Open-source B2C and B2B commerce for developers and AI agents. Spurtcommerce is built with TypeScript, Node.js and MySQL.

Agent copilot for onchain systematic trading, from monitor to trade analysis.

An extension for oobabooga/text-generation-webui that enables the LLM to search the web

ai app for slidev

Multi-Agents AI LLM Crypto Financial Trading Framework. 开源多代理加密货币交易决策框架。

Harness-agnostic orchestration package for multi-agent consensus workflows

MCP server for Mikrotik

Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.

A curated guide to the Herdr ecosystem: tools, workflows, configs, clients, skills, and integrations.

AI Agent Memory

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

Long-term memory for any AI agent. One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Self-host free or use Uteke Cloud.

Claude Code plugins for the work that keeps coming back: repo maps, conditional rules, ticketed parallel work, extra subscription models, local usage metrics, and guided setup.

企业级桌面 AI Agent 工作台，让技能、知识与任务在同一处协作。

Dotted, honestly-3D loading indicators for AI and agent interfaces in SwiftUI. Nine hand-tuned designs, two tuned sizes.

CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.

Your friendly and safe CLI Copilot

A simple Python program to implement the search-extract-summarize flow.

Agentic AI platform that harnesses Visual Agents Chaining to build proactive digital assistants

use claude code's agent teams orchestraction with any harness

台灣第三方金流 Skills for AI Agents - 藍新金流、綠界科技 ECPay、統一金流 PAYUNi

Zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/MLX on Apple Silicon. Automates env setup, LoRA training (SFT, DPO, GRPO, vision), post-hoc GRPO log diagnostics, evaluation, and export end-to-end. Part of the Gaslamp AI platform.

Agentic LaTeX Writer - Local-first editor for AI-assisted academic writing

Extract structured strategy specifications from quantitative finance research papers — Agent Skill for GitHub Copilot & Claude Code

OpenCode Mobile — open-source Android client for the OpenCode AI coding agent. Run AI coding sessions from your phone against your self-hosted server over Tailscale. Available on F-Droid.

Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.

AI assistant in Telegram that remembers everything and helps you run your life. Self-hosted in one command.

Compose a full-stack TypeScript stack and get a cutting-edge, verified project made for AI coding agents, with type safety, lint, and tests built in. | 自由组合全栈 TypeScript 技术栈，得到一个前沿、经过验证、为 AI 编码智能体打造的项目，内置类型安全、lint 与测试。

Multi-agent end-to-end application - General-purpose artificial intelligence agent for multimodal agent collaboration

All-in-one Web Agent framework for post-training. Start building with a few clicks!

MinimalChat is a lightweight, open-source chat application that allows you to interact with various large language models.

Safestclaw is the alternative to openclaw.. You can naturally chat with it via text and voice, and you can choose not to use a language model., By default it picks up on intent and semantics.. No prompt injection while you get over ninety percent of what openclaw does plus tts and voice to text

Benchmarking library for RAG

A Git worktree workflow tool for AI coding agents. Enables parallel development with isolated environments.

pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers into code that runs in secure sandboxes for token-efficient workflows.

🚀 K8s Agent Orchestration System: Managing the KAOS in your large-scale distributed multi-agent systems

[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models

🔥 Open-source multi-agent orchestration system for OpenClaw, enabling swarm intelligence via unified group chat.

Self-hosted search + markdown harvester for AI agents. SearXNG (100+ engines) + FastAPI + trafilatura. Tavily-compatible /search plus /extract with size presets and pagination. One-command Docker Compose.

A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides intelligent fact extraction and deduplication, with an artifact store for detailed content.

Local dashboards and physical controls for AI coding agents — native 3D aquariums, Stream Deck, Apple/Android apps, e-ink, ESP32 and LED displays.

Agent-native investment research workspace for evidence-tracked, refreshable investment theses across equities, earnings, macro, and portfolio review.

Unofficial KakaoTalk CLI and native MCP server for macOS — read, watch, and send messages via Accessibility automation.

The first book dedicated to enterprise Agent platform engineering, from data intelligence foundations to production-ready AI-native business systems.

Ivory is home for your database clusters — deploy, watch and fix them from one place, be it your browser, your phone or your AI agent. Open source, self-hosted, one Docker container and nothing to install on your hosts.

An opinionated, curated list of tools for enforcing software development standards: one recommended tool per job, with limits.

A showcase of diverse AI agents, fostering innovation and collaboration across domains.

Metorial MCP Index - An ever growing list of open source MCP servers 📁 🎉

WARC + AI - Experimental Retrieval Augmented Generation Pipeline for Web Archive Collections.

Transform Claude Code into a complete development studio with 40+ specialized AI agents, MCP integrations, and enterprise-grade workflows

OpenLens AI: A Fully Autonomous Multimodal Research Agent｜ OpenLens AI：全自主多模态科研智能体

Build AI that feels. Open-source persona engine — personality emerges from neural drives, not prompts. Inspired by Her.

[New Update](Added Agentic-Mode, Dark-GODMode)The Real BlackHat GPT - ai can do your illegal stuffs without saying anything. Use At Your Own Risk!

Sleek, Fast and Token Efficient AI Coding Agent

一个基于 Spring AI 的多智能体金融分析系统。全部基于最新行情数据、实时新闻，拒绝幻觉。多个 AI 专家分工协作、对抗辩论，产出可执行的投研决策；系统每日自动复盘持仓、反思决策对错，把经验教训沉淀到向量记忆，让下一次分析更聪明。

ReactBench is an evaluation for coding agents on realistic React work

Pilot Harness — a CodePilot-inspired desktop client and plugin suite for DeepSeek Harness on macOS, Windows, and Linux.

为 Trae IDE 打造的全流程标准化 AI 开发技能库，内置调度分发与多角色研发技能，一键导入规范 AI 编码工作流 🚀

An evaluation harness for medical/health AI agents — reproduce and cover multiple benchmarks under one scoring discipline

Spot it. Save it. Free, local-first Chrome extension for images, videos and prompts. Explore 2,000+ curated cases and connect your library to AI Agents via MCP. 提示词导演

Octogen is an Open-Source Code Interpreter Agent Framework

Official Code Repository for the paper "Distilling LLM Agent into Small Models with Retrieval and Code Tools"

飞书逆向，飞书apis，飞书AI Agent

The first self-evolving AI agent. Rewrites its own source code in real-time. 6 AST mutation strategies. Absorbs GitHub repos autonomously. 7 autonomic drives. Standalone CLI. Works anywhere.

[ICML 2026] Autonomous AI agent for end-to-end spatial proteomics analysis, with SP-Bench for agentic multiplexed-imaging workflows.

Email inbox API for AI agents. Give every agent its own real email address, receive mail as structured webhooks, and reply in-thread over REST. A complete multi-tenant mail server in Rust: inbound and outbound, DKIM/SPF/DMARC/ARC, MTA-STS, DANE, three-tier anti-spam.

Opencode Plugin for AI-Agent Orchestration

AI编程工具中文提示词合集，包含Cursor、Antigravity、VSCode Agent等多种AI编程工具的提示词，为中文开发者提供AI辅助编程参考资源。持续更新中文编程Rules和最新AI编程提示词。

Spectrum sharing in vehicular networks based on multi-agent reinforcement learning, IEEE Journal on Selected Areas in Communications

Learning to Use Medical Tools with Multi-modal Agent

platform engineering framework for the agentic age

OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.

Main Kagenti repo - installer, UI and docs

Knowledge architecture for a 10,000-note Obsidian vault — 5 system files + 7 shared rules + 8 slash commands, shared openly with humans and AI agents. Live: https://system.cmdspace.work

An extension suite that turns Pi into a multi-agent orchestration platform

这是一个专门接入Agnes免费模型API的skill，帮助新手排查和修复问题，也能直接在Agent工具中使用生图生视频，支持Claude code、Openclaw、Codex、Hermes等工具部署接入，所有信息基于最新的官方文档和说明。

SwarmZero's SDK for building AI agents, swarms of agents and much more.

Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.

Towards Large Multimodal Models as Visual Foundation Agents

A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors OpenSearch/Elasticsearch data, builds RAG-based behavioral memory, and validates real-time anomalies using LLMs.

Pixel-perfect clones of any webpage. Paste a URL, get a measured Vite + React replica.

A visible workspace for AI agents to collaborate as a single team.

[ACL 2026 Main, SAC Highlight] FinSight: Towards Real-World Financial Deep Research. 🎯One ticker, one click, one publication-ready report.

Drive a real, stock iPhone (and any macOS app) from any MCP client via iPhone Mirroring — no Developer Mode, no Xcode, no WebDriverAgent. Tap, swipe, type, OCR, plus replayable AI-authored test skills.