Custom agents

A beautifully crafted desktop client for running and managing local LLMs via llama.cpp.

Your coding agent writes the code — CodeFRAME proves it works, and keeps proving it. Every bug you capture becomes a permanent, scoped obligation that blocks the merge until real evidence satisfies it. Works with Claude Code, Codex, OpenCode and Kilocode.

Google Search Console CLI and skills for AI agents (and humans)

Agent-native design skill: ordinary prompts -> verified HTML-first prototypes, decks, dashboards, motion demos, and export-ready visuals.

Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.

Unofficial Node.js client for gemini.google.com.

C# local LLM chat completions library using ONNX Runtime, compatible with Microsoft.Extensions.AI

Enterprise-grade RAG and document search system for extracting reliable insights from real-world data.

Your AI value investing agent. Analyze stocks like Graham & Buffett. Built on MCP.

Enterprise-grade AI Agent system for code generation, analysis, and orchestration

Real-time global intelligence dashboard 54-country CII, AI Agent (Ollama/Groq/OpenRouter), 35+ data layers, Tauri desktop (Win/macOS/Linux)

A web-based map marking and itinerary planning tool with AI assistance.

Навыки для KodaCode

Claude Code edits your videos with triple lane on-device pre-processing, then exports to Adobe Premiere. NO CLOUD MICROSERVICES REQUIRED! Plug in hours of footage, wait 30 min and get an edited video back!

A persistent, searchable filesystem for AI agents.

Claude / AI-agent skill for solving engineering contradictions with Altshuller's TRIZ — full 39×39 matrix, 40 principles, Su-Field analysis with 76 Standard Solutions, ARIZ-85C, 3 worked examples.

High-performance toolkit for running AI tools (OpenClaw, Pi Agent, n8n, Ollama, Hermes) natively on Android via Termux.

AI design skills + 46 MCP tools for Claude Code, Cursor, Windsurf, Copilot, and any AI agent. Install: npx skills add pablostanley/efecto-plugin

Open-source, self-hosted project management: tasks, sprints, Gantt, Kanban, docs, automations and time tracking with timesheets. Connect Claude or ChatGPT over MCP. A free Jira, ClickUp, Linear and Monday.com alternative.

AI coding agent framework — portable, stage-gated harness for Claude Code, Codex, and OpenCode

AI-agent workspace for quantitative trading — backtest, validate, and paper trade strategies with multi-agent collaboration

A local-first, LLM-agnostic memory layer for AI assistants

Portable Agent Skill for codebase understanding and developer onboarding, producing source-cited Markdown artifacts with architecture, flows, error paths, and unknowns.

The testing standard for MCP servers. Lint (14 rules), test, and fuzz over real stdio/SSE/HTTP transport. 18 assertion types in YAML. Found 4,794 schema issues across 55 servers. Any language, no mocks, single binary.

Portable MBSE domain agents for AI-assisted systems engineering

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

Agent Skill for Overleaf — Automate LaTeX project management, sync, and compilation for AI assistants

Permanent code intelligence layer. Learns what matters, expires what changed, proves what existed. Content-addressed graph with Merkle proofs, 25 extractors, 23 MCP tools. Gets smarter with use.

The issue tracker that lives in your repo. Built for AI agents. Works for humans.

A curated collection of skills for Claude Code and Codex — specialized capabilities across development, design, AI, security, and more. Part of the cdd.dev/skills family.

Cloud security audit tools for AI agents — AWS, Azure, GCP misconfiguration detection via MCP. 38 tools, 60+ checks. The agent finds vulns, not you.

bb-huge 🤗 , Personal bug bounty findings hub and bug bounty orchestration for multiple agents

Curated research on memory systems for LLM agents

The open-source client-agnostic agent harness

CLI, MCP server, and TypeScript library that extracts text, layout, and page images from PDFs for AI agents — when extraction goes wrong, it says so per page and says what to do next.

Full-stack backend infrastructure for AI agents: Postgres, auth, storage, serverless functions and atomic deploys. TypeScript SDK, CLI and MCP server. Paid with x402/MPP. Open source.

Agent mux terminal.

Cortex Space is a local-first developer workspace built with Tauri v2 + React. Replace static terminals with a fluid, keyboard-driven environment featuring recursive split layouts, drag-and-drop panes, AI agent workflows, command snippets, and automatic port detection.

A structured knowledge base for large language model technologies, covering LLMs, Agents, RAG, model training, evaluation methodologies, and AI engineering practices.

Type-correct, brand-aware HTML deck builder for Claude Code. Pitch, sales, launch, keynote, all-hands. PDF and PPTX import.

Open-source agent skills library for building SaaS, marketing systems, creative assets, and frontend design workflows

A RiveScript chatbot written in Go that supports Slack and XMPP.

MCP Abilities Elementor - Add-on for mcp-expose-abilities WordPress plugin

A simple studio to use agent

Claude Code skill for negotiating car leases over email using Chris Voss tactics + lease calculator

User-invoked soft autopilot for recoverable, issue-driven AI coding workflows

An AI-driven multi-agent trading platform for options trading and stock trends analysis. This project leverages advanced machine learning, real-time market data, and a modular multi-agent framework.

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AMD Vulkan. Commercial-OK licenses.

基于 AI Agent 的渗透测试自动化框架，严格遵循 PTES（Penetration Testing Execution Standard）标准，覆盖渗透测试全生命周期。| An automated penetration testing framework based on AI agents strictly adheres to the PTES (Penetration Testing Execution Standard) standards and covers the entire life cycle of penetration testing.

Coding-agent skills for building with Agno.

Self-evolving skills for your coding agent — auto-create and auto-improve skills as you work, no trigger needed.

Enable interaction with distributed, decentralized LLMs on the Morpheus network through a desktop chat experience

基於 Google ADK 與 MCP Toolbox 的保險科技推薦 Agent 原型。核心 Agent 能理解保險需求、主動追問，並透過受控 SQL 工具查詢醫療、意外、家庭與收入保障產品。後端採 FastAPI 提供 SSE 串流與 WebSocket 即時互動，前端以 Next.js 呈現對話介面。知識庫結合 PostgreSQL 與 pgvector 實現 FAQ 語意搜尋與 RAG 查詢，並支援多模態 Live Agent 語音互動。安全層涵蓋 JWT 驗證、PII 脫敏與 SHA-256 雜湊鏈防篡改稽核日誌。品質保證採 ADK evalsets 評估驅動開發，部署支援 Docker Compose、Cloud Run 與 Terraform 多環境配置。

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.

MediSense AI puts a structured clinical triage assistant in the hands of every community health worker — in under 90 seconds, on any device with a browser.

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

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

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.

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

Swift/AppKit terminal multiplexer for Claude Code + shell sessions

LLM-free, layout-aware PDF chunking for RAG pipelines. Preserves document structure via regex and font heuristics. Written in pure Rust.

Not just an agent demo — a local coding-agent platform: plan mode, sub-agent teams, cron, memory, MCP. Single Go binary, DeepSeek-native, MIT.

Turn macro intuition into validated Dynare .mod files — a coding agent skill for DSGE modeling.

Plugin kênh Zalo OpenClaw đầy đủ tính năng, xây dựng trên zca-js, hỗ trợ nhắn tin, quản lý nhóm, phân quyền truy cập và tích hợp công cụ cho agent.

A powerful offline chat application that provides AI mentors specialized in various tech domains. Learn programming with intelligent, emotionally-aware AI mentors that understand your needs and guide you through your development journey.

All your Zotero annotations in one place — filter, export with citations, and turn highlights into linked, searchable ideas. Plus grounded Q&A with clickable page citations.

Flash-P: Turning decades of biology into accurate causal networks with AI agents

Drive, inspect & record terminal sessions from the CLI

AI Agent skills collection by geekjourneyx for agent-compatible coding, creator, and automation workflows

Give your agent a real phone number and an email inbox — in minutes, not days.

DukOS — autonomous, scheduled multi-agent operations on Claude Code

Plain-English legal writing skill for AI agents (Claude Code, Codex, Antigravity). For lawyers, paralegals, and in-house counsel: audits and rewrites legalese and AI slop in contracts, briefs, memos, and client letters into clear prose using Garner's plain-language rules, while preserving legal terms of art.

Playwright and Cypress E2E testing skills for AI agents. Generate Playwright tests, review test quality, and debug failures in Claude Code and Codex.

Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

Web search tool for the pi coding agent — batch queries, ranked readable markdown results ready to fetch. Pairs with pi-smart-fetch.

Avito MCP server for chats, listings, orders and analytics. 148 tools, read-only profiles, dry runs and confirmations. Try the local demo without API keys.

Evidence-graded, agent-executable thinking-method skills - 63 frameworks reduced to their working mechanism, honestly graded, and producing a concrete artifact. 63 frameworks + 4 tools + 9 recipes for Claude Code, Codex, and other AI agents. Advanced (Gold) tier.

Self-contained Codex skill for ad-hoc development sessions on session branches.

all human experts into AI agents

Open-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.

A local-first control layer for AI agents

Declare the outcome, skip the logic. The developer-first infrastructure engine for structured, multi-turn AI conversations with built-in safety, async follow-ups, and native compliance

Multi-agent coding template — persistent memory, spec-driven workflow, skills and security hooks for Claude Code, Cursor, Windsurf, GitHub Copilot and any AGENTS.md-reading tool. No dependencies.

Short-horizon order-flow pulse engine for Robinhood crypto markets.

A tiny, declarative, agent-friendly library for your Git repositories.

《生产级多智能体系统：从架构判断到工程落地》中文开源书

ACP-friendly Node.js SDK for local coding agents: run Codex, Claude Code, Cursor, OpenCode, and Pi with streaming, abort, and session resume.

Desktop coding assistant — Electron, React and TypeScript.

Supervise Codex CLI and Claude Code workers from OpenClaw with async progress, routed delivery, wake, resume, and automation support.

Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.

We heard you like harnesses, so we built a harness for your harness, so you can harness while you harness. Feel me?

Take the reins of your real browser

Debugger CLI for AI agents — run, control, and inspect binaries programmatically with structured output for LLM tooling

Local-first AI Employee OS: discover, hire, supervise, verify evidence, and grow AI employees.

Playwright-powered Fanqie novel publishing skill with guides and thin adapters for OpenClaw, Hermes Agent, Claude Code, Codex CLI, and Cline.

한국 취업 자기소개서를 기업조사→초안→글자수→리뷰→윤문→검증 8단계로 완성하는 Claude Code 플러그인

The first LLM-maintained knowledge wiki purpose-built for Product Managers — Karpathy's LLM Wiki pattern turned into a PM schema, rituals, and a complete worked pilot. Clone it, point your agent at it, and your product knowledge starts compounding.

Don't write a bug report — record it. Local MCP: screen recording → transcript, frames, OCR, wall-clock evidence for coding agents.

SOUL.md governance framework for Hermes Agent — structured memory, skill management, and operational rules