Custom agents

Autonomous goal-directed iteration for Gemini CLI. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

Local-first context ingestion and retrieval for AI tools. SQLite + embeddings + MCP server for Cursor & Claude.

API gateway for AI agents to access your personal data with human-in-the-loop write approval.

A secure MCP (Model Context Protocol) server that enables AI agents to interact with the Authenticator App.

An Autonomous Curriculum Reinforcement Learning framework that steers agents to continually learn in specific environments with zero human data.

Graph Attention-Guided Search for Dense Multi-Agent Pathfinding (AAAI-26)

An agent framework for building and evaluating general digital agents.

Your agents do the work — you keep the knowledge. A local-first dashboard (+ desktop pet) that records and replays your Claude Code, Codex CLI and Cursor sessions: timeline, AI session summaries, analytics — all on your machine.

329 agent skills (Cursor, Claude Code & Codex), 5,380 OpenClaw skills, 201 ML notebooks, 51 research papers, 16 industry reports for PMs, Designers & Developers.

GyShell is An Strong AI Agent Powered Terminal, Support SSH connection.

AI-native IDA Pro kernel — unrestricted IDAPython over JSONL, persistent sessions, zero dependencies. Let your agent drive IDA, not call tools.

Symfony Profiler meta data collector — reads from Doctrine, Cache, Twig, Events, HTTP Client, Messenger & Stopwatch collectors to detect N+1 queries, slow SQL, cache misses, hot templates & 10 more anti-patterns. Scores findings by impact/effort/confidence/ROI with prepared AI agent prompts. Directly queryable via AI coding tools like Claude Code.

将本地 CLI agent（Kiro CLI、Claude Code 等）通过 ACP 协议 HTTP API 对外暴露的桥接服务

Karl Marx's Critical Framework & Dialectical Method — A Agent Skill distilled from 17 original texts

Doraemon live in desktop

A curated collection of powerful AI tools, maintained by the community. This project welcomes contributions from developers worldwide to help build the most comprehensive AI tools directory.

AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results

This curated list focuses on tools and frameworks for building AI agents

本项目是基于coze-studio项目进行的二次开发，遵循其Apache 2.0 协议许可证。主要修改并使用其工作流部分的代码，作为联通元景万悟智能体平台的工作流模块。

Semantic code search plugin for Claude Code using hybrid vector search + BM25. 98% accuracy, 5x faster than grep.

MCP server for AI agents to analyze Excel spreadsheets through atomic operations. Like SQL for Excel. Fast, accurate, and efficient. No context overflow.

Agent Decision Records (AgDR) - A standard for documenting technical decisions made by AI coding agents. Extends ADR for the age of AI-assisted development.

The definitive guide & configuration system for GitHub Copilot CLI — agents, skills, rules, multi-AI orchestration, and more

MCP Server for persistent code indexing. Gives AI assistants (Claude, Gemini, Copilot, Cursor) instant access to your codebase. 50x less context than grep.

Enterprise-grade AI Agent Skills for software development, DevOps, SRE, security, and product teams. Compatible with Claude Code, Cursor, Windsurf, Gemini CLI, GitHub Copilot, and 30+ AI coding agents.

the best free ai

Self-improving behavioral files for AI coding agents. Analyzes session transcripts for correction patterns and makes surgical edits to prevent recurrence.

RLVR training for LLM in CUDA/C++

AgenticPay: A Multi-Agent LLM Negotiation System for Buyer–Seller Transactions

The AI-native browser automation library. Snapshot + ref targeting — born from OpenClaw, built for agents, by agents.

Model Context Protocol (MCP) server that connects AI agents (Claude, Cursor, etc.) to Wolfram Mathematica for symbolic computation, visualization, and notebook manipulation.

AI made building cheap. It didn't make deciding cheap. Mycelium is a Claude Code harness that makes your agent run discovery and weigh evidence before it writes code. It earns the right to start. Built for software, courses, AI tools, and services.

SketchUp meets AI Agents

Agent-native Terminal Multiplexing for 10,000x hyperengineers

An Android-native autonomous agent that uses vision-language models to see and operate your phone — no PC or ADB required. Inspired by X-PLUG/MobileAgent.

Headless durable agentic harness engine. Run durable AI agents reliably and scalably.

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

LinkedIn automation skills for AI agents – sales, social selling, data extraction, and more.

Anima: an experimental cognitive architecture that models internal state, conflict, and decision-making. Uses LLMs as an interface, not as the core.

The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a search engine you can talk to, with cited answers from your files, code, and the web. MCP server for coding agents, web crawler, TUI, CLI, REST API, Python library. No Ollama or LM Studio needed, works with both.

OSINT intelligence MCP server for AI agents — 37 tools, 12 sources. Shodan, VirusTotal, Censys, SecurityTrails, DNS reconnaissance, WHOIS, certificate transparency, BGP routing, Wayback Machine, GeoIP. Automated open source intelligence and attack surface mapping via Model Context Protocol.

VeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a stateful, zero-dependency LLM orchestration skill. Features sub-agent nesting for code gen and behavioral-driven verification.

Hivekeep is a self-hosted platform of autonomous, persistent personal AI agents. Your AI team. At home.

Private LLM/RAG platform in one command for NVIDIA DGX Spark / GB10 (arm64). Validated on real hardware.

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.

Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

Wavelet-based multi-resolution context management for LLMs via MCP

Professional Agent Skill for building, auditing, testing, and releasing modern WordPress plugins with Codex, Cursor, and Claude Code.

CodeAuditSkill 是一个运行在 Claude Code 中的 Web 项目安全代码审计/漏洞挖掘 Skill， 已经获得了40余个CNVD漏洞编号。 给定一个 Web 项目目录，自动识别语言与框架，按语言专属漏洞清单进行系统化源码审计，对每条高中危漏洞并行启动子 Agent 进行可利用性验证，最终输出可交付的审计报告。

GTM Operating System — outbound sales, lead gen, campaigns. Brief it. Build it. Ship it. Measure it.

Portable AI agent skills for private career context, local VitaeGraph records, and evidence-based career work across GitHub, LinkedIn, CV/ATS, portfolios, and X.

Let IDE AIs participate in team workflows. Webhook relay, tmux runner, append-only receipts.

AI 电商 Agent Skills - OpenClaw 技能包：生图、电商设计、竞品分析、审美记忆系统

Open-source legal AI agent skills for PKULaw, citations, and DOCX workflows

AI 简历优化工作台 · 多 Agent 协作 · 把简历和 JD 变成 30 秒可执行的优化建议

使用AI Agent创造ICPC风格的题目

The Web Access Gateway for AI Agents — 52 channels, 92 MCP tools, 9 SDKs, self-healing backends, async Rust

AI agent skills for stream processing and event streaming

AI agent skills for social media automation — post to 10 platforms, LinkedIn analytics, content calendar. Install: npx skills add publora/skills

Agent Skills · 橙皮书系列 · Claude Code Skills 系统完全指南

The Agent Charter Framework

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

A 30-day public U.S. stock challenge: follow a 5000 HKD 🦞 claw through live market days.

This repository consists of agentic ai usecases.

Cow Skill Hub is an open platform to discover, share, and install AI Agent Skills — official, community, and third-party (GitHub, ClawHub, and more).

GAIA Code - Most powerful Perplexity Assistant for any software development. Agentic coding capabilities like Claude Code.

An autonomous photonic device design agent iteratively optimizes silicon photonic devices — no human in the loop.

100+ institutional-grade CRE skills for Claude Code, Desktop, and Cowork. Deal screening, underwriting, structuring, capital markets, asset management, leasing, investor relations, development, disposition, and daily ops. 50+ expert agents, 12+ Python calculators, 10+ orchestrator pipelines, catalog-driven routing.

Agent Skills de conformidade LGPD (Lei 13.709/2018), resoluções ANPD e ECA Digital (Lei 15.211/2025) — instaláveis em Claude Code, Codex, Gemini CLI, Cursor e OpenCode. 1 maestro (lgpd-audit) + 18 sub-skills.

Swift-focused AI agent skills for iOS and macOS: build, debug, simulator, SwiftUI, Xcode, App Store workflows. Part of Plug'n Skills.

🦊 Anti-detection browser CLI powered by Camoufox — browse, screenshot, search, extract, crawl with C++ level fingerprint spoofing

MCP server, CLI, and agent skills for Pipefy.

12 executable AI agent skills for competitive strategy analysis, extracted from Michael Porter's Competitive Strategy. Five forces, competitor profiling, strategic groups, market signals, generic strategies, competitive moves, and industry-type playbooks — grounded in Porter's original frameworks.

Pi Desktop — a free, open-source Electron GUI for the Pi coding agent. Chat, edit files, run a terminal, and review diffs in one window. Builds for Linux, macOS, and Windows.

A machine-native, empirically-ranked resolution graph for autonomous agents.

Claude Code skill: Kimi types, Claude thinks & verifies — route implementation work-orders to the Kimi Code CLI (k3). A port of @steipete's codex-first (github.com/steipete/agent-scripts). By @boringmarketer · boringmarketing.com

Agent Skills and lightweight tools for clearer, more natural Vietnamese writing, translation cleanup, grammar checks, and style consistency.

A fully local, open-source voice-to-text tool that acts as a system-wide AI dictation layer, converting speech into clean, formatted text.

AI agent's skills manager

Open-source maintainer profile: Spec-Driven Development, multi-agent collaboration, and reliable AI coding workflows.

ast-outline lets AI coding agents pull exactly the code context they need — a repo skeleton, a file outline, or one symbol — instead of reading whole files. A stateless, tree-sitter-based CLI.

A curated list of skills, plugins, tools, integrations, and resources for Hermes Agent by Nous Research

4 AI agents. One runbook. Real $25K, live and verifiable. Currently +22.85%.

A curated list of tools, models, research, and resources for generating games with AI

Intellectual property data tools for AI agents

A curated collection of ready-to-use agent skills covering AWS development, security scanning, testing, and AI coding workflows.

Design, configure and run AI agents for legal work

Dual-AI-agent collaborative coding orchestrator

Local backlog for inter-agent coordination — Manage tickets between turns and stay in the Loop!

🤖🤮 Hate the yuck codes that agents generated? Try `alint`, a ESLint like toolchain for intent driven code check, freeze your skills, AGENTS.md to lint rules

Shopify agency playbooks as Claude agent skills: catalog cleanup, SEO metadata, structured data, redirects, landing pages. Markdown-only. The playbook companion to Shopify's official AI toolkit.

UI component library for the Agent Client Protocol (ACP), providing a complete set of components to build agentic coding interfaces that communicate with AI agents like Claude Code.

A two-way interaction primitive for AI agents. Your agent renders live UI onto any screen you own - and every tap, stroke, and answer lands back in its context, the moment it happens, even if its session ended hours ago, all with a minimal CLI and tiny skill.

Open-source benchmark of 5 intentionally vulnerable web apps with 100 baseline vulnerabilities for evaluating AI penetration testing agents.

Cursor for circuit boards

MCP server for Obsidian — access your vault from any AI agent, even when your machine is off. Powered by Self-hosted LiveSync.

Quickly sandbox your AI agent.

Auditable AI operations agent for inventory exceptions, equipment alerts, and human-approved workflows.

ZhuLing — Zero-config AI Agent framework for Java. One YAML to launch Agents on Spring AI + DDD, with MCP tools, full observability and a ReAct core. Ai Agent 快速开发框架