Custom agents

[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

A meta-skill plugin for Nous Research's Hermes AI agent that watches your workflows and automatically turns them into reusable skills. Every time you work with Hermes and solve something — setting up a project, debugging code, creating a PR — that workflow disappears at the end of the session. You have to explain it again next time.

专业的 LaTeX 简历模板，专为大模型与 Agent 算法工程师设计 | Professional LaTeX resume template for LLM & Agent algorithm engineers

Open Agency is an open-source AI workforce featuring specialized agents for development, growth, research, strategy, and creativity. Each agent is designed to deliver practical results through focused expertise and structured workflows.

Local-first, open-source Claude Science alternative, before Claude Science is a thing. Turn your AI agent into personal DNA expert.

An agent-first decompiler designed to be refined by other agents. Kuna is written in Rust and was originally ported from Ghidra.

A multi-agent travel assistant system built using the **Agent2Agent (A2A)** protocol and **MCP (Model Context Protocol)**

Docker Sandboxes run AI coding agents in isolated environments on your machine or on Docker-managed cloud infrastructure

A fast and minimal framework for building agentic systems

Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry.

Create state-machine-powered LLM agents using XState

The agent skills I actually use to build software with coding agents. The PIV loop, planning, worktrees, and the meta-skills for building your own AI Layer.

Nix-powered agentic reverse engineering environment

A complete bug bounty workspace for HackerOne researchers. Includes scope enforcement, automated recon/vuln pipeline (400+ tools), report templates, CVE/CWE watchlists, and a local VM practice lab. Built for disciplined, ethical hunting.

PGX — Lightweight Postgres for AI agents. Written in Rust. Thousands of isolated databases in one runtime. 🐘

AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models - system prompts, AGENTS.md specs, and Ollama Modelfiles. Built for AI security research and red-team testing.

30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

18 Google Maps tools and 3 Agent Skills for place search, routes, travel planning, and local SEO—via MCP or standalone CLI.

Gemini Live provides multimodal realtime agent capabilities. Build voice agents that can process vision and text in realtime.

Deterministic UI audits for shadcn apps, built for your terminal, your CI, and your AI agent.

pi agent in Golang

Smart job hunting Agent - AI-powered automation from scraping to delivery

DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.

Desktop-native BigFish companion for DeepSeek Harness — real Agent status, always on top on Windows.

Genome viewer for you and your agents.

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

An example of using Google Sheets to create a Viber survey chat bot without a backend server

Agent skill for rendering inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — in agent conversations.

ACP is the Agent Control Plane - a distributed agent scheduler optimized for simplicity, clarity, and control. It is designed for outer-loop agents that run without supervision, and make asynchronous tool calls like requesting human feedback on key operations. Full MCP support.

Power BI CLI - semantic models (.NET TOM) and PBIR reports for token-efficient AI agent usage, built for Claude Code

FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready.

A curated registry of reusable Mercury Agent, Open Claw or Hermes Agent skills designed for real developer workflows, persistent memory, and token-efficient execution.

AgentSkillsHub (agentskillshub.top) — security-graded directory of open-source Claude skills, MCP servers & AI agent tools, refreshed every 8 hours

用于写NSFC本子的Agent Skills

Universal AI Agent using Amazon Bedrock, capable of customize to create/edit files, execute commands, search the web, use knowledge base, use multi-agents, generative images and more.

《AI Quant Trading - From Zero to One》

A skill for AI-coding tools to build and edit Microsoft Copilot Studio agents as YAML — with schema validation, templates, and AI-powered skills. Suited for Claude Code, GitHub Copilot CLI, and more.

Agent skills for drafting, revising, auditing, and resubmitting Nature-style journal manuscripts.

Pi coding agent setup for the lazy

LiteRT and LiteRT-LM sample apps, model recipes, agent skills and utilities.

An agent skill to de-AI your writing

HermesOffice — AI-native office suite forked from GenOffice (Apache-2.0), with native Hermes Agent AI

Turn any goal into a short prompt that makes your agent set a real quality bar, run builder and critic pairs, compare blind, and loop until it wins.

Fully async Rust TUI engine 🦀. For powering AI/LLM coding agents, Cloud/SSH workflows & interactive CLIs: non-blocking readline, inline dialogs, React/Elm-style full-screen TUI, Markdown editor, PTY multiplexing & rust-analyzer MCP server.

The official Agent Skills for ClickHouse and ClickHouse Cloud

Flink Agents is an Agentic AI framework based on Apache Flink

Personal AI assistant for work inside corporate constraints, built on coding agents and the tools, sessions, and permissions you already have.

Local-first marketing operations control center for CRM, outreach, content, analytics, approvals, automations, and agent workflows.

MCP server for AutoCAD LT v3.1: freehand AutoLISP execution, 8 consolidated tools, File IPC + ezdxf backends, focus-free dispatch, undo/redo, P&ID symbols, and robust IPC with ESC prefix and UTF-8 fallback. Companion agent skill: puran-water/autocad-drafting

Terminal pixel-art office for AI coding agents

A curated list of MLSecOps tools and resources for securing machine learning and AI systems - adversarial ML defense, LLM security, AI red teaming, model scanning, supply-chain protection, and MLOps pipeline security.

An AI Agent that interacts with Windows OS at GUI level.

MOMO CODE — AI coding agent that evolves with you

Local AI PR workbench — Claude/Codex review in isolated git worktrees, human-gated GitHub comments

The Language Virtual Machine for Agent Skills

Search Airbnb using your AI Agent

WeChat iLink Bot SDK for Node.js and Python — zero-config agent integration

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

Open source code for ICLR 2026 Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

Build an AI Telephony Agent for Inbound and Outbound Calls

Open-source template for a durable personal AI agent — web chat, Slack, Linear, and long-term memory with user-approved saves. Eve, Nuxt, Better Auth, Vercel Connect.

README-first research reproduction skills with bounded execution, auditable evidence, and byte-preserving README annotations.

Portable AI-agent skill: capture YouTube transcripts as Obsidian-ready Markdown with metadata, linked timestamps, language selection, and subtitle exports

《推荐系统：工业架构与核心算法》开源书稿

You can outsource your thinking, but not your understanding. A hook for agent-assisted development that quizzes you on the changes before you push to prod.

inference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agents

Interactive subagents for pi — spawn, orchestrate, and manage sub-agent sessions in cmux terminals

Docfork - Up-to-date docs for AI Coding Agents.

A powerful all-in-one bot for Twitch streamers

Open-source abilities for OpenHome agents.

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

🧬 Extend EvoScientist with Installable Skill & Knowledge Packs

AI said it finished. Flyto2 shows the proof.

Dragonclaw: Maybe the best openclaw client. Built with Electron+SQLite, it doesn't touch OpenClaw's code but adds multi‑agent, high‑concurrency, DAG workflows. No prompt tuning needed (pre‑optimized). One‑click install with built‑in cloud service (replaceable).

Agency Agents is a small, native app for browsing, installing, and tracking the agent personas from msitarzewski/agency-agents across the AI coding tools you actually use.

The best way to work with coding agents. Run fifty in parallel, let them spawn each other, review everything in one place.

A local-first desktop workspace for running, organizing, and resuming multiple coding agents and shells with real PTYs, split panes, persistent layouts, and local session history.

iMessage personal assistant + password vault

Agentic Android launcher: build your own apps and widgets with AI agents, Omarchy themes, Arch Linux without root

mahilo: Multi-Agent Human-in-the-Loop Framework is a flexible framework for creating multi-agent systems that can each interact with humans while sharing relevant context internally.

RunAgent simplifies serverless deployment of your AI agents. With a powerful CLI, multi-language SDK support, built-in agent invocation & streaming suppprt.

Leverage a legitimate WFP callout driver to prevent EDR agents from sending telemetry

The open-source agent-serving project

Automated web vulnerability scanning with LLM agents

TokenRoll LLMDoc for Coding Agent

Native macOS SwiftUI app for managing multiple AI code agent skills

An open source AI-native agentic SOC platform

Create polished product demo videos with AI coding agents and Remotion. The UI is code, not a screen recording.

The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery

Hrm人事系统：Flowable审批流 + RAG知识库 + 智能问答

MCP Playbooks for AI agents

AWM: Agent Workflow Memory

A large-scale benchmark for evaluating vision-language-action models, embodied agents, and vision-language models

LoongFlow is an expert-grade Agent framework for Loop Engineering. Through a Plan-Execute-Summary loop and structured experiential memory, it enables AI to continuously think, execute, reflect, and evolve across complex software engineering, mathematical, and machine learning tasks.

More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs, configs, memory & rules across every AI coding agent. 🌟 Star if you like it!

AI agent framework, written from scratch (not based on openclaw), focused on stripping it down to the bare necessities, optimizing token count, reducing security risks. modular so you can enable only exactly what you need.

A Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Self-Evolving Agents.

Stealth Chromium engine that stops scrapers and browser agents from getting blocked, with one line of code change.