Custom agents

Xueqiu (雪球) stock data CLI for AI agents — 30 commands for A-shares, HK, US stocks & funds

The first browser MCP built for security testing. Give your AI agent a real Firefox browser and let it find vulnerabilities.

自进化量化选股系统 — Kronos K线预测模型 + Hermes Agent 自进化闭环 + A股三池漏斗选股

Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassian for LLM agents. Compact output, lossless XHTML<->Markdown round-trip, Claude Code + Codex + GitHub Copilot integration.

Agentic AI plugin that transforms a dashboard request into a Tableau specification — with interactive HTML mock, implementation blueprint, and experimental .twbx generation. Works with Claude Code, Cursor, and other AI coding tools

用钱学森工程控制论重塑 AI Agent 架构。前馈、积分控制、层级分离、自监控——让 Agent 真正懂你。—— Feedforward, integral control, hierarchical decomposition, and self-monitoring for a self-evolving agent that truly understands you.

Research into AI engineering interview assignments, take-home challenges, and hiring practices from Q4 2025 / Q1 2026

Agentic Testing Harness

Logic-first AI code review via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Catches behavioral bugs, type-contract breaches & async hazards that linters miss. Six skills · Claude Code · Codex CLI · Gemini CLI.

Security-first, self-hosted AI agents - isolation you can prove, not just promise.

A controlled-experiment lab for studying how tool-using LLM agents behave — vary tools, personas, and conversation histories, run repeated trials across models, and measure the effect on safety and tool-call behavior.

The meta-harness that brings real agentic collaboration as a first-class citizen

荒原序列 BarrenOrder — 多Agent飞书群@协作协议。Bot间主从分工+能力匹配+熔断器+消息去重。

Control Kiro CLI from Telegram over the Agent Client Protocol (ACP): switch projects, resume & attach to live coding sessions, streamed responses with diffs, queued follow-ups, and a 24/7 cross-platform background service (Windows/Linux/macOS).

Think first, then code. Where Claude Code and Codex jump straight to writing, this stays review-first: a code reviewer, security scanner, root-cause debugger, and code generator, all in one shell-native loop.

8 AI agents grade your entire repository across 6 dimensions — signed, verifiable A+ to F audit reports in minutes

Open-source runtime security rules engine for MCP servers and AI agents. Detects prompt injection, command injection, jailbreaks, and data exfiltration.

Free WordPress MCP For Connecting AI Coding Agents

Open-source collaborative AI agent platform. Humans and AI agents on different machines work together in shared workspaces — agents run locally on your own daemon, self-hosted, no cloud execution of your code.

An advanced autonomous AI engineering team

One room, three minds: a multi-LLM planning council for your terminal — you, Claude Code, and Codex debate and ship an implementation plan.

What a $500/hour coach would analyze after reading 90 days of your meetings.

A modular framework for building complete AI solutions. It's mostly a Rust framework with a subset of it ported to Deno.

A fast, read-first code inspector for the agent era: watch AI-written changes land live and review every hunk before it ships

A police department for your Claude Code agents — a logging-only hook + CLI that audits the main agent and every subagent and reports rule offenses (permission bypass, out-of-scope & credential access, self-permissioning, disallowed tools, redundant, off-task) with quoted evidence. Catch-and-report, never blocks.

Convert scientific papers into executable, reproducible codebases

A self-hosted, keyboard-driven cockpit for running a whole fleet of Claude Code agents at once. Worktrees, command palette, scheduler, voice — every layer stacks, so you ship far more than hand-juggling terminals. Your machine, your keys, no telemetry.

AI-powered penetration testing with Claude Code agents. RedTeam Barranquilla - Automating security assessments using PTES methodology.

Turn an agent's work: progress, reviews, research, comparisons into a single self-contained, reviewable HTML page (a work canvas). An Agent skill.

Dependency safety gate for Claude Code & Codex CLI — OSV pre-approval, npm lockfile-closure enforcement, and auto-rollback. Local, zero runtime deps.

Agent-first patent-prosecution assistant — open, transparent, and yours. Drafts and redlines in your own Word files, on your own computer.

Bantz won't be a helper; he will be your Host. Your computer will become his studio, and your tasks will give the "entertainment." He won't just execute code; he will "pull strings" behind the scenes with a smile that you can hear through the text.

Headless Matrix WebRTC voice AND video agent — auto-answers calls, bridges audio to any AI agent via PipeWire, optional camera-frame vision for multimodal LLMs

Agentic email + calendar hub on Cloudflare Workers. One Worker owns your domain's email surface: a full self-hosted email client with an AI agent, plus a unified calendar that aggregates Proton / Outlook / iCloud into one busy/free model and writes time blocks back to all three.

An autonomous AI coding agent with novel innovations in tool state management and code editing, running in a Docker sandbox with a persistent shell, parallel tools, and a VNC desktop.

给 AI agent（Claude Code / openclaw / Codex）用的 VPS SSH 管理技能：统一密钥、别名管理、一键下发公钥、安全关闭密码登录、批量探活

IRIS Mini ⚡ — The agentic CLI heartbeat. Scaffolds code 🏗️, commands the local filesystem 📂, and automates your developer workflow directly from the terminal 🚀. Pure execution, zero friction, local-first intelligence 🧠💻.

A lightweight, text-based UI wireframing schema optimized for AI coding agents and Spec-Driven Development (SDD).

A curated list of the best AgentOps tools for 2026 — observability, tracing, evaluation, cost monitoring, and guardrails for LLM agents. Covering open-source and SaaS tools with feature benchmarks and architecture guidance.

Design UI changes from real source code — verify data, iterate faithful HTML mockups, then delegate. A Claude Code plugin & Codex skill by nlook.me

Record a browser workflow once, get a deterministic MCP tool your AI agent can call. Zero tokens at runtime. Postman for AI agents.

Local-first memory, recall, and skill evolution plugin for Codex agents.

Local-first desktop workspace for AI agents: browser, terminal, memory, plugins, runtimes, and durable loops.

Single-file Tor/.onion access layer for AI agents — 18 search engines, Robin OSINT pipeline, 4 LLM modes, MCP server

Installable AI workflow plugin that routes complex software tasks through focused specialist skills for architecture, UI/UX, docs, diagrams, databases, QA, security, and resilience review.

Self-hosted, browser-based AI dungeon RPG, fully local on an AMD Strix Halo APU: narrator + per-character agents on one local LLM (Gemma 4 26B MoE via llama.cpp/Vulkan), local images (FLUX.2 klein/ComfyUI), expressive voice (Maya1 TTS). FastAPI brain, SQLite, vanilla JS, docker-compose with guided setup (CLI wizard or double-click HTML).

Uma IA VTuber que mora no seu PC. Fala, escuta, lembra — e nada sai da sua máquina.

Local-first AI knowledge base for PDFs, Office docs, web clips and Markdown notes — ask your whole library and get citations that jump back to the source. Vectorless RAG, wikilinks, local Codex/Claude agents.

Gaia is a living, open registry of every AI agent skill — structured as a leveling skill graph. Live site: https://gaiaskilltree.com/

Agent-agnostic Markdown skill for Xiaohongshu topic planning, trend matching, scoring, and risk review. No code dependencies.

面向 Codex、Claude Code 与 AI Agent 的考研择校导航 Skill：联网调研复试线、统考名额、推免和拟录取数据，生成避坑提示与冲稳保建议。

Плагин для Cursor-автоматизации блога: SEO/GEO пайплайн на субагентах, визуалы, QA, llms.txt и SSH WordPress publish

Official Porkbun MCP server — exposes the Porkbun v3 API as 30 native tools for Claude Desktop, Cursor, and other AI agents. Idempotency-safe writes, full domain lifecycle.

Brief-to-PR harness for GitHub Actions — draft PRs from arXiv papers, search queries, or your own design docs.

AgensFlow is an open-source framework that treats multi-agent coordination as an online policy-learning problem under partial observability, enabling learned routing to improve coordination-heavy workflows over static approaches.

文 Veyllo Agentic Framework

The self-hosted, multi-tenant AI app builder for teams. Sandboxed, audit-logged, MIT-licensed. The open-source alternative to Multi-Tenant Saas buiders.

Find AI/LLM security vulnerabilities in your code before attackers do — covers prompt injection, MCP tool poisoning, RAG data poisoning, and more

用于立创硬件开源广场项目介绍的AI技能。AI skills for introducing the OSHWLab project

Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully yours.

Kalshi CLI — Go command-line client for Kalshi Trade API v2 with versioned, schema-validated JSON output.

Biomimetic autonomous cognitive AI brain — never forgets, self-learning, hallucination-resistant, desktop-controllable

A portable AI skill that turns MR Dang's value-investing framework into executable stock-analysis workflows.

Claude Code plugin for intelligent GitHub Pull Request reviews that continuously learns your project's conventions and team feedback.

Agentic QA boilerplate built on Playwright + KATA + TypeScript. Multi-agent skills following the agentskills.io spec, orchestrating the full QA lifecycle: shift-left planning, in-sprint testing, TMS documentation with ROI scoring, KATA automation, and regression with GO/NO-GO. Works across Claude Code, Opencode, etc.

Claude Code Growth Operating System (OS): Sales, Marketing, Product and Retention as one Revenue system

Core engine behind Calibrate, a framework for evaluating AI agents: speech-to-text, text-to-speech, LLM evaluation, end-to-end simulations

My daily AI agent skills for Claude Code, Codex, frontend QA, reviews, and workflow automation.

Plugin de skills e agentes para Claude Code workflows de engenharia reais, do PRD ao PR

Guardrails for AI coding agents — block catastrophic tool calls before they run. Semantic, agent-neutral, near-zero false positives.

Artemis IDE — A free, open-source AI-powered development environment built with Electron & React. Features autonomous AI agents, Monaco editor, integrated terminal, MCP marketplace, 16 themes, Discord RPC, token tracking, and more. No subscriptions, no cloud lock-in. Just code.

The robustness engine for AI coding agents. A local Rust code graph gives an agent repo-wide understanding, a validation gate that runs before an edit lands, and safe symbol-aware edits. Deep on TypeScript, useful on Rust, local and deterministic.

Self-hosted visual crypto trading platform built with FastAPI, React, and Redis. Features genetic backtesting and AI strategy generation.

Nine eval-built agent workflows for planning, implementation, copy, and repository work.

Embedded long-term memory database for AI agents & LLM apps. Six-layer cognitive architecture, knowledge graph, hybrid BM25 + vector search, sleep-time memory consolidation. One .meh file, zero infrastructure, pure Go.

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.

Desktop & phone notifications for AI coding agents (Claude Code, Codex, Gemini CLI, Cursor). Native VS Code support. Toast + ntfy push. Zero dependencies.

A terminal dashboard for managing multiple AI agent sessions in tmux

Multiplayer admin and orchestrator platform for heterogeneous agent runtimes — Hermes (container-per-agent) and Letta (memory-first agents on a shared server) in one control plane, with multi-tenant security, group approval, and audit.

会读空气的本地 AI 伴侣核心模块——硅基感知 / 漫想模式 / 工具调用调度器(分批开源中)

面向中文研究生与科研工作者的学术辅导 skill 套件（支持 Claude Code / Codex 等编程智能体）：选题 → 检索 → 成文 → 评审 → 投稿全链路 25 个命令，引用核验以真实 API 响应为准、不凭模型记忆编造，AI 管效率、人管研究决策——辅导不代笔

Static AI Agent Risk Analyzer for AI applications. Detects capabilities, prompt risks, tool permissions, MCP integrations, governance gaps, and autonomy before deployment. Generate JSON, HTML and SARIF reports for CI/CD.

高性能，低门槛的通用终端 AI 代理工具 / General-purpose terminal AI agent

Cross-disciplinary, source-grounded paper deep-reading Agent Skill with vision/text-only routes, domain lenses, and evidence audits.

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit prompts.

The guide for AI meta harnesses

Agentic Memory System for Long-Term AI

Multi-account email MCP server for SMTP sending, IMAP search, replies, attachments, and inbox organization

MCP server for Rockwell/Allen-Bradley Studio 5000 — parse L5X project exports and give AI agents structured access to PLC tags, UDTs, routines, and programs.

Claude Code skill: distill a book or video series into one interactive single-file HTML · 书籍/视频深度蒸馏

Files you own. Memory your agents can trust. Also: your AI won't gaslight you about what's in your own notes anymore.

Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.

A multi-agent system that generates and evaluates business ideas

AI agent system designed to help solo founders build and ship products efficiently

Facebook Pages marketing skills for Claude Code and Codex: high-share posts, hooks, engagement replies, and a weekly plan. Publish via Publora. Open source, MIT. Content engineering by Creative Content Crafts.

Manage, review, and migrate cloud AI agents with Git and YAML. The open-source IaC control plane for managed AI agents.

Workspace-first orchestration for long-horizon Lean 4 formalization agents.

Saraswati Agent 是一个本地长篇角色扮演agent，通过 LangGraph 编排模型、工具、分层记忆、剧情状态和生成后审计，动态演化来实现更长期的更沉浸的角色扮演体验。

Multiplayer admin and orchestrator platform for heterogeneous agent runtimes — Hermes (container-per-agent) and Letta (memory-first agents on a shared server) in one control plane, with multi-tenant security, group approval, and audit.

夕小瑶 × DeepSeek Harness Web 皮肤合集、安装器与社区创作工具链