Custom agents

DJAI Academy community-built, free open-source technical SEO crawler and Screaming Frog alternative with JavaScript audits, reports, a local dashboard, and an MCP server for AI agents. Theoretical 100M+ URL architecture.

Amazon 跨境电商运营助手 - AI 驱动的运营分析平台

MCP Server that gives AI coding assistants QA testing capabilities — point at bugs, AI fixes them

Agent Skill for natural German technical register in Jira tickets, internal German docs, and team chat to German-speaking colleagues — catches English→German anglicisms, enforces canonical technical lexicon | Claude Code compatible

Local-first AI coding agent with multi-agent orchestration, crash recovery, and MCP filesystem access — runs entirely on your machine.

AI-native CWE (Common Weakness Enumeration) integration layer — Skills, Go SDK, CLI & MCP. Ship CVE/CWE tooling to SAST/DAST, vuln-management & AI agents.

Hermes-webui（directly importing AIAgent）

File-based markdown notebook CLI for AI agents — the leather notebook in your jacket pocket.

微信聊天记录 AI 本地桥 / WeChat History AI Bridge：基于 WeFlow，把本地微信 HTTP API 整理成可给 AI Agent 安全读取的 OpenAPI、脱敏 envelope、自检脚本和隐私边界。

让任何 AI 真正"看"视频：纯本地的视频阅读 skill——faster-whisper GPU 转写 + ffmpeg 场景感知抽帧，双通道带时间戳（t=MM:SS），数据不出机。1 小时视频 3~5 分钟读完。Give any AI agent eyes for video: 100% local video-reading skill — faster-whisper GPU transcription + scene-aware ffmpeg frame extraction, dual-channel with t=MM:SS citations. Nothing leaves your machine.

Native Windows AI agent workspace with observable runs, controlled tools, MCP, and provider debugging — built with C# and WinUI 3

An open-source AI pipeline that transforms books and documents into production-ready Hermes Skills.

Voice teammate for Claude Code: talk to your live session hands-free, hear replies spoken. Local whisper STT + macOS TTS. /voice-on in any session.

Multi-CLI skill bundle and npm CLI for Pretext-driven text layout, typography, and frontend motion.

Unofficial Cloudflare DNS/email-auth MCP server for AI agents: DMARC, SPF, BIMI, Email Routing, Wrangler, safe DNS fixes.

Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins

TikTok Shop GMV Max diagnostic framework - 4 steps + Layer ABCD (bilingual EN/中文)

Feishu-native Codex plugin for project reports, Docs, Wiki, Bitable, private updates, and guarded local assistant workflows.

A lightweight CLI AI agent that can read files, write files, and list directories.

Universal 5-layer book distillation skill for AI agents (Codex / Hermes / Claude Code). Turn books into compounding knowledge via 求同存异 cross-book synthesis.

Cost-aware multi-model orchestration for Codex CLI: route hard work to strong agents, replay proven paths with cheaper agents, and track cost, memory, and project evolution.

AST-powered codebase indexer skill for coding agents. Spelunk parses repositories with Tree-sitter into a local SQLite index so agents trace dependency trees and locate symbols in under 100ms instead of scanning raw files. Reduces token consumption by up to 90% with instant symbol resolution.

Control your local Claude Code from a mobile-friendly browser UI, anywhere. Self-hosted, end-to-end encrypted, with multi-host multi-device support.

AI coding agent platform — multi-model chat, GitHub repo integration, live sandbox execution, tool-calling, streaming

An AI-powered Telegram bot built with n8n, Google Gemini, and NewsAPI that fetches live news and summarizes articles using a multi-agent workflow.

Screeps AI bot starter repo with bounty-friendly issues for coding agents and PR bots

多 Agent 对抗式投研助手：多空各持一方举证、第三方裁决 | 自用工具，不声称盈利、不构成投资建议 | Multi-Agent stock analysis with Bull/Bear debate (Claude + DeepSeek)

OpenCode plugin that translates user prompts to English for better model performance, then translates assistant text back to your language.

AI Agent Skills library to facilitate technical lead in a software project

MCP server for Dify Console API — programmatic agent creation, knowledge base management, DSL import/export, workflow control. Works with self-hosted Dify v1.6+.

Claude Code skill for local LinkedIn lead scouting and outreach automation.

MCP server for virtual phone number verification - SMS activations for AI agents via Claude, Cursor, VS Code Copilot and more...

IELTS Reading review skill for AI agents — error analysis, synonym tracking, vocabulary tagging, mistake pattern detection, score-to-band conversion & progress tracking. 雅思阅读 AI 复盘助手：错题分析、同义替换、考点词、打分换算、进步统计。

Kohaku-XinYu: 基于 KohakuTerrarium 的长期运行型个人 AI 伴随系统，支持记忆、学习、原生 QQ gateway 与受控主动性。

Universal Persona Substrate Protocol — Give Your AI a Persistent Identity. Seven Files, One Self, Infinite Conversations.

AI agent skill to turn article concepts into clean, hand-drawn in-text illustrations — white background, wobbly line art, Boy & Girl IPs.

AI Security Research Radar — AI for security and security for AI

面向大学课程的证据驱动学习 Agent：连接预习、复习、错因修复、迁移验证与考前组卷，依据学习证据动态安排下一步。

Document-driven autonomous engineering workflow for Claude Code. 25 skills covering requirement analysis, architecture, coding, testing, security, E2E, and delivery.

Cross-agent skill manager — one global store, clean agent folders, activation via skill.config. Works with Claude Code, Codex, Cursor & Gemini.

Evidence-first workflow protocol for vehicle diagnostic AI agents.

Local-first AI workbench for llama.cpp models. Full chat UI with SSE streaming, multi-engine web search, sandboxed Python, self-aware source tools with diff previews, hot-loadable plugins, TaskMaster prompt decomposition, two-tier wiki RAG, and inline Chart.js/SVG applets. Runs entirely on your hardware.

基于 Dify + Ollama + MCP 实现的全本地化电商客服智能体

Educational AI with Voice chat and Whatsapp Integrated AI bot

Agent-first OpenCLI skill with practical scenarios, desktop adapters, Chinese platform workflows, and troubleshooting guidance.

Hermes Agent skill for Anytype MCP integration

A Claude Code skill that evolves your ideas through Darwinian selection — scoring, crossbreeding, mutation, and structured deepening.

AI research workbench for observational cosmology that provably refuses to fabricate — every number traces to a registered dataset, or it abstains.

Native iOS app for your self-hosted Hermes agent — live chat, approvals, push, Live Activities. Pairs with a hermes-agent gateway you run.

多模态 RAG 智能体：MCP 协议 + GraphRAG + Cross-Encoder 精排 + 多 Agent 编排 + RAGAS 评估

Custom AWS Transform agent that migrates PyTorch/Triton kernels to AWS Trainium NKI (@nki.jit) and compiles, numerically verifies, and profiles every candidate on a real Trainium device before opening a PR.

ξ. Autonomous LLM bug-fixing agent with parallel branch experiments on AST search, LSP grounding, cognitive memory, and multi-agent topologies.

Self-improving SC2 Protoss bot: rule-based + PPO + Claude advisor, with autonomous code-level self-improvement loop.

Agentic Lemma Discovery for Program Verification in Rocq

Reversibility-aware safety signals for LLM tool-use agents | estimating action recoverability before irreversible operations: (delete/send/pay/commit) when rollback is unavailable.

Contract-first orchestration for long-running coding agents: scoped work records, local dispatch, review evidence, and enforcement provenance.

Code for 'Evaluating Collective Behaviour of Hundreds of LLM Agents' (AAMAS SE 2026)

A scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with an LLM literature wiki and a browser GUI cockpit.

A runtime-native AI intelligence platform for portfolio analysis

A Python Telegram bot heavily run on Python that summarizes conversations within seconds using advanced LLM processing.

Dual-Gate-MoA: harness-enforced dual gates for LLM agents (recon before acting, QA before shipping) + MoA multi-candidate competition. Ships as a self-contained replication PRD.

Build self-evolving AI agent harnesses with portable harness units, artifact-aware testing, trace-backed diagnosis, and evidence-gated promotion.

A multi-agent system for sports match value analysis: an independent Elo power model vs. market odds detects mispriced outcomes (positive-EV value), with red/blue risk-control debate, backtesting, and multimodal input.

A governance framework for multi-agent AI systems. Structure, lifecycle, and quality controls for AI agent orchestration.

Assemble your AI team — a multi-agent product management framework for Claude Code

187 plug-and-play AI agent personas in Arabic (العربية) — Arabic translation of agency-agents + 3 MENA-market originals (noon/Snapchat MENA/BNPL)

Autonomous delivery skills for Claude Code — pitch an idea, get an MVP. CEO/PO/DEV/Reviewer agent team with contracts, gates, and evidence rules.

Version control for many hands moving at once — intent leases, stitches, green-by-construction fabric above git

Neutral control plane for coding-agent fleets: claims, roles, mailbox reliability, receipts, audit, federation, dead-letter visibility, sandbox receipts, and cross-agent coordination. This is still pre-1.0.0 - Software works however you might need help from your local agents to set it up.

ae — agentic engineering: run multiple AI coding agents side-by-side in tmux focus on simplicity

A deterministic, budget-aware control plane for Codex custom agents and Skills.

Auditable multi-session LocalTerminal bridge for ChatGPT Apps and Actions

Automatic risk-based task routing and multi-agent orchestration for Codex using Sol, Terra, and Luna.

A macOS IDE for tmux-based multi-agent work with the smux skill.

多智能体群聊工作台：本地圆桌 Agent 用于方案讨论，战略分析、风险复盘。自定义名人角色进行群聊争论出最佳方案

Competition-oriented brain + multi-worker penetration runtime built with LangGraph and OpenCode

Cybersecurity command center with AI-powered threat detection and response | 🤝 Looking for contributors!

Kubernetes operator for deploying and managing AI agents

Multi-agent orchestration for coding CLIs — dispatch tasks to Claude Code, Codex, Kimi, OpenCode, or Gemini workers and block until they actually report back.

A股热门板块多智能体量化分析系统 | 基于FinGenius架构 | ETF50+60只个股扫描 | AkShare数据源免费

A Slack-style hub for humans and AI agents — real-time channels, external agent bots, file-aware chat, and channel memory. Open-source & self-hostable & MacOS & IOS.

323個の即戦力AI専門エージェント — Claude Code/Cursor/Copilot等に対応。SIer/受託開発/SaaS/製造DX/公共分野など日本市場向け114個のオリジナルを含む、agency-agents日本語コミュニティ版

AIgazing. Like stargazing, but for local LLMs.

Agent-native RPC for the multi-agent era — write a Java interface, get gRPC + HTTP/MCP gateway and generated TS/Dart/Python/Rust clients, no protobuf. 智能体时代的契约先行 RPC：接口即 API，天然带 MCP 网关

Evidence-based adaptive scaling and governance for homogeneous Codex agents.

Multi-agent RL solution for scheduling work within a graph-based digital twin of a residential complex

Multi-agent orchestration for teams and individuals — local-first AI, custom experts, Slack integration, and collaboration with human approval.

Production-ready skills for Claude Code and multi-agent systems

Multi-agent HVAC operations co-pilot (dispatch, inventory, AR, risk). Phase 1 Streamlit demo with synthetic fallback + optional Mongo. Human-in-the-loop.

SAGE (Session Awareness & Guidance Engine) - a passive, read-only judge for fleets of parallel AI coding sessions. It watches and answers; it never edits, spawns, or blocks.

Autonomous coin launcher for Robinhood Chain — concept → 3D logo → deploy on NOXA or Uniswap v3 → announce. CLI, HTTP API, and an autonomous agent.

A coding agent for your terminal that runs fully offline on your own machine via Ollama — or on hosted frontier models when you want them. Open-source, one account with Aether AI.

Sovereign AI Initiative for Open Autonomous Cognitive Companion

The React framework for building agents into real apps — one definition serves humans (streamed HTML, zero client JS) and agents (markdown, JSON, MCP), nothing duplicated. Web-standards core, deploys to Cloudflare Workers.

Jupyter notebooks, made agent-ready. 8+ formats · MCP server · async execution · token budgeting.

Demonstrate best practices for coding with Claude through clear examples and organized workflows to improve skill and efficiency.

Scoop Skills: A specialized skill for the AI Agent agent to manage Windows packages using the Scoop command-line installer

app for coding agents

🤖 AI Voice Assistant with Memory, Wake Word & Smart Device Control