Custom agents

Open-source agent skills for building scope-safe Markdown knowledge vaults with deterministic validation and research workflows.

Three minds, one context. Multi-agent AI orchestrator for Claude Code, Codex, and Antigravity CLI.

Cross-platform Rust daemon that prevents disk-full incidents for AI coding workloads using predictive pressure control, safe artifact cleanup, and multi-volume ballast pools.

Agentic Robotic Software System

A 100% local, privacy-first alternative to Windows Recall — captures your screen, OCRs it, and lets you semantically search and chat with your history using a local LLM. Zero cloud, zero data leakage.

Self-hosted AI knowledge base & long-form writing workbench — turn large document collections into traceable, structured documents.

Modular AI-powered testing & monitoring platform — Performance / Test Agent / Test Case Gen / API & UI Automation / Knowledge Base

See a game. Ship a game 🐾 An Agent Skill that clones casual web games from a single prompt — provably-correct levels, browser-verified, original-branded. Works with Claude Code, Codex & more.

A desktop control center for Eve agents — run, chat, build, wire, and deploy every Eve agent from one native app.

Run your own unrestricted 70B+ AI locally · No limits · No filters · One-time payment

No API keys required. Transform the native ChatGPT, Claude, and Gemini web interfaces into fully autonomous local coding agents.

Gen AI Evaluation Toolkit on AWS is a flexible, cloud-native accelerator built on AWS serverless architecture that enables comprehensive evaluation of generative AI applications.

Comfy Agent is a tool to use ComfyUI from the CLI. It is suitable for both direct CLI usage and AI-agent-driven automation.

MCP server and CLI for WPF: inspect visual trees and bindings, capture scrollable content, drive mouse/touch input, and record workflows as runnable xUnit tests.

OpenCurro AI Agent is a fast, lightweight, and autonomous general-purpose AI agent.

🎙️ Voice → Article: AI SEO copywriting pipeline. Dictate blog posts in Telegram, get SEO-optimized articles deployed to your site. For solopreneurs.

Local-first desktop command center for Claude Code, Codex, OpenCode, and other coding agents—parallel tasks, worktrees, dev services, port forwards, diffs, and review.

A control room for AI memory. Your files and conversations become searchable memory any model you connect can draw on, and you decide what enters, what moves and what leaves. Vaults live on your hardware. Windows, macOS, Linux.

Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.

Curated resources for building AI Waifu and intelligent companions: frameworks, platforms, tools, models, and communities

Policy-aware field mission orchestration agent with bounded planning, auditable replanning, travel and expense constraints.

Deterministic tree-sitter + SQLite/FTS5 code knowledge graph for coding agents and developers: symbols, calls and dependencies over a CLI, an MCP server and a local browser viewer. No AI/LLM inside; byte-stable output.

Local-first repo maps for coding agents—ranked files, test routes, risks, CLI/MCP/GitHub Action, and public GitHub URLs.

A bilingual, continuously updated directory of AI agent cases, news, open-source projects, papers, and reusable resources.

A free, open-source Dynamic Island for Windows 10 & 11 — media controls, focus timers, notifications, system stats & a private AI assistant in a sleek always-on-top pill. Built with Tauri + React + Rust.

A local-first knowledge management tool that connects concepts and let an LLM safely maintain a plain-Markdown vault you can read, audit, and edit yourself.

中国+海外双市场 Flutter+NestJS 多平台 App 开发 Agent Skills：三 flavor 发布/第三方登录/测试/CI-CD/可观测性，适配 Claude Code、Codex 等

Skills and more for open code free models

Bittensor Subnet Repository maintainer agent + a GitHub-history benchmark that scores it — can an agent make the maintainer decisions a strong maintainer would?

A harness-engineered AI agent runtime. Build agents with tool isolation, self-correction, and permission scoping out of the box.

Local-first creator intelligence agent: directory capture, dual transcription, viral analysis, topic generation and reusable creator personas.

사람의 의도와 WHY를 AI 작가·편집자에게 이어주는 커뮤니티 웹툰 제작 키트. 콘티·컷 배치 퇴고, ima2-gen 생성, 후보 선택과 완성 보관을 연결합니다.

aiduMEI⚕爱嘟优忆思——aidu Memory Engine Insight · 智能体通用智慧引擎——Excellent memory system for all agents.

Seedance Drama Maker — turn one sentence into a cinematic AI short drama. Multi-agent pipeline powered by SeeDance 2.5 (30s shots, 50 reference inputs, 14 languages, native audio-video sync), SeeDream 5.0 Pro image generation, FastAPI + WebSocket.

Governance backplane for AI agents acting on infrastructure — policy-gated, audit-grade, MCP-native. Apache 2.0.

Claude Code 非官方开源桌面客户端——接入 SDK 控制协议，权限卡片审批、多模型切换、多 Tab 会话、视频分析（Tauri 2 + React）

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.

《LangGraph AI智能体开发实战》一书的配套代码

Markdown-first, human-gated multi-agent editorial workflow with explicit research, planning, writing, and review artifacts.

GTM engineering skills for AI coding agents — build lead lists, find & verify emails, waterfall enrichment, lead scoring, CRM sync, and buying-signal monitoring (job changes, funding, tech intent) from Claude Code, Codex, or Cursor. Powered by the Cargo CLI: 138 integrations, 50 data providers.

File explorer plugin for DeepSeek Harness: file tree, preview, markdown, syntax highlighting, in-panel editing, VS Code integration - DeepSeek Harness 全局文件资源管理器插件

Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery

A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and BlockRun's full model catalog from one wallet, paid per request over x402.

Cross-platform SSH and SFTP client with organized server assets, terminal workflows, port forwarding, secure sync, and AI assistance.

🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / Gemini. Eval-gated 100/100, you always merge.

Jump to any agent session across Cursor, Claude Code, OpenCode and more. See all your chaos in one place and feed your need to context switch.

Task-aware reasoning-mode routing for opencode: spec/react/weak three-band agent routing, ported from yjh051108/dsh-routing-suite

Agentic research control plane: queue state, worker preflight, wake-gated execution, evidence sync, dashboard, alerts, and AI-generated paper packaging.

Open-source repository standard, starter template, validator, and multi-agent workflow for making vibe-coded and AI-generated software understandable, testable, reviewable, and maintainable. Codex-first reference implementation.

The open-source CMO: growth playbooks from 16 operators (Cursor, Notion, Linear, Deel, Gamma, Granola...) as an installable AI skill

28 OSINT Agent Skills that turn Cursor, Claude & AI coding agents into a full open-source intelligence platform — reconnaissance, attribution, GEOINT, breach checks & due diligence. Ethical, sourced, passive-first.

Behavior sharing for AI agents in teams — the topos CLI + self-hostable plane keep every agent's skills current

Android AI phone assistant — 120+ voice-controlled phone actions across 16 categories. Multilingual site live in 14 languages with localized sitemap.

让 DeepSeek Harness 拥有跨会话长期记忆：AI 自动记住你是谁、你的项目和偏好，新会话直接带上背景，生活与工作记忆自动分开互不干扰，零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers who you are, your projects and preferences across sessions, keeps personal and work memories separate, zero-config.

Score any OpenAPI document for AI-readiness. Command-line tool, GitHub Action and agent skills that implement the open JAIRF scoring framework, with HTML reports and OpenAPI Overlay output.

Vulnerability scanning with your own scanners and threat feeds, plus a coding agent that opens the fix PR. CLI, GitHub Action, or scheduled Managed Agents deployment.

One-stop skills, subagent, MCP and LSP manager for DeepSeek Harness (DSH) — compatible with Claude Code, Codex, Cursor, Kimi and other agent plugin layouts.

🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)

Open-source local multi-agent platform

Git-free file snapshots and rewind — put a directory back the way it was, without a repository and without touching your version control.

Open-Source-Boilerplate für PersonalOS: Markdown-basierte Systemlogik, Templates und lokale Prüfungen für Menschen und KI-Agenten.

An architectural audit where a finding is admissible only once its cost is measured from git history. A doctrine for coding agents plus a stdlib-only measurement CLI.

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

ShellX — desktop AI workspace for Grok Build, Claude Code, Codex, and Antigravity across Windows, macOS, WSL, and SSH. Includes a private agent browser and secure local Vault for credentials.

Citation-ready YouTube research for AI agents — transcript search, exact timestamp links, cross-video evidence, and channel intelligence over MCP

Make it easy to automate personal desktop tasks

A phone-friendly web interface for Herdr: monitor agents, receive notifications, open real terminals, and send files.

Installable DeepSeek Harness knowledge base plugin

Rules-and-receipts layer for AI agents that spend money: plain-English policy → human approval → signed receipts anyone can verify.

Lightweight, provider-agnostic long-term memory for conversational agents

Antigravity Agent Skill for Google NotebookLM integration via nlm CLI. Create notebooks, add sources, generate audio podcasts, research, and query with AI.

Build and verify browser-native HTML presentations for laptops and projectors.

DeepSeek Harness (DSH) for VS Code — AI coding with native diffs, tool approvals, persistent sessions, and Trace insights. | AI 编程助手：原生 Diff、工具审批、持久会话与 Trace 分析。

中文 GBrain 实操手册 for Amazon sellers: build an AI-native second brain with real commands, examples, governance, and Agent workflows.

Getting Out of the Loop: 8 Months Solo-Building with AI

🧱 A curated list of SDKs, integrations, tools, and resources for microsandbox

Give an AI eyes and hands on a physical computer — MCP server that lets Claude see and drive any machine through a JetKVM (screenshots, keyboard/mouse, boot media, power) on stock firmware

A general-purpose single-agent framework, currently under personal development.

Nosana MCP: let AI agents rent GPUs on Nosana and deploy templates such as MiniMax H3 with account credits. MCP server + nosana-deploy CLI.

Persistent GPU jobs for AI agents. MCP + CLI, hardware-aware scheduling, Kaggle adapter, and recoverable artifacts for Codex and Claude Code.

Agentel SDK for persistent AI agent identity and trust — connect runtimes to profiles, relationships, public work, and evidence-based reputation.

Evidence-first news workspace: compare official vs market narratives, click any AI claim to the exact source sentence, and track how your judgment changes. Self-hosted — one-command demo, no API keys.

Computer for AI Agents

Free, open-source SSH client, SFTP, tunnels, database GUI and a secure AI-agent (MCP) bridge in one app a MobaXterm, PuTTY and Termius alternative for Windows, macOS and Linux.

InterWise 是一个可自部署的、面向技术面试训练的 AI 模拟面试平台，支持文字/视频面试、简历分析、动态 RAG 追问、岗位/题库管理、面试复盘与 AI Mentor。

Live code graph that fuses static analysis (tree-sitter) with OpenTelemetry runtime traces, queried over MCP so AI coding agents get real full-stack context.

Context cards for dbt metrics — 5-layer meta: schema, validator CLI, and installable agent skill so AI agents answer analytical questions accurately

Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing, and real-time threat detection.

Official TypeScript SDKs for Better i18n — Next.js, React, Expo/React Native integrations with CLI, MCP server, and CDN-powered translation delivery

Spring Boot support for AGENTS.md in Spring AI applications

MMD Specialized Blender — Native PMX/VMD Import/Export, CCD IK, Real-time Physics, FSR Upscaling

Coordinate coding agents in Herdr with assign, handoff, result collection, and follow-up messages. Install with npx skills.

Cocos Creator 3.8.x / COCOS 4 游戏开发 Agent Skill（遵循 Agent Skills 开放标准）。支持 Claude Code · Codex · DeepSeek Harness (dsh) · WorkBuddy · Cursor · Copilot 等 100+ 平台

Learn Jev end to end: a free hands-on course. Build 13 AI agent use cases with a fast brain (Jev) and a slow brain (LLM). One OpenRouter key.

Moved to https://github.com/nano-muse/nanoMuse — archive of OpenMuse 0.1.0–0.6.0

Take the pain out of installing and running machine-learning interatomic potentials: every major MLIP in one registry, set up, verified and run by your LLM.

Local-first Agent RL workbench for Search-R1 rollouts, reward evaluation, GRPO/verl training-data handoff, and an auxiliary private RAG workspace.

Cogito Studio: All-in-One Workspace AI

A senior-engineer protocol for polyglot code generation, architecture, testing, security, performance, and agent validation.