Custom agents

Turn any website into clean, LLM-ready data. Open-source web crawler with stealth mode, distributed crawling, real-time WebSocket progress & Markdown output. Power your AI apps with GcrawlAI.

Give your AI tools architecture-aware reasoning. Knowledge graph from any codebase — 14 LLM backends, impact analysis, confidence scores. Works with Claude Code, Cursor, VS Code Copilot.

Mastering Spring Boot from fundamentals to production — REST APIs, Security, JPA, Microservices, Kafka, Docker, Kubernetes, CI/CD, and AI-powered backend development.

A multimodal RAG dashboard and interactive 3D Knowledge Graph. Process documents locally with Ollama or via Cloud APIs, powered by LightRAG, RAG-Anything and Neo4j.

Composite MCP server for Godot Engine -- 17 composite tools for AI-assisted game development.

A curated list of eCommerce tools, software, and AI agents for Amazon sellers. Updated for 2026.

Missing Xcode Tools Documentation

Cryochamber for your AI agents, for scheduling long running tasks

把高质量播客和长文 RSS 自动转成 karpathy-claude-wiki 兼容的 source-summary 页面 / Turn high-signal podcasts and long-form RSS into karpathy-claude-wiki compatible source-summary pages. Part of the zero-code AI investment research toolkit.

[ICML'26] Hierarchical Abstract Tree for Cross-Document Retrieval Augmented Generation

为 Cline、Codex、Claude Code、Droid、OpenCode、CodeBuddy 和 ZCode 提供 obra/superpowers 的中文友好适配，支持中文触发、中文文档输出和更稳的安装更新体验。

Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.

Single-file web UI for NVIDIA DGX Spark — pull Ollama models, browse and download from HuggingFace, manage LiteLLM routing, and control SGLang, vLLM, llama.cpp, LocalAI, and ComfyUI. All from one browser tab.

The definitive open-source agent skills library for AI-powered Google Ads management. 73+ skills across 10 categories. Built for googleadsagent.ai™. Works with Claude Code, Cursor, Codex, Gemini, and more.

A curated list of tools for building LLM-powered personal knowledge bases

Multi-agent AI framework that writes full-length novels with persistent story state, a deterministic continuity engine, and a five-role editorial pipeline.

The harness engineering framework for coding agents

Claude Code plugin that delegates read-only review, adversarial review, free-form ask, and write-capable rescue work to the local Kimi CLI. Includes an opt-in stop-time review gate.

Proactive agent daemon for scheduled OSS maintenance workflows

Agentic AI development loop that splits Design, Code, Review, and Test into isolated roles with deterministic guardrails

Spec-driven agent harness for Claude Code and Codex — five-agent pipeline (scope, plan, build, verify, learn) with an auditable proof chain.

Agentic Streaming is for resilient pipelines of stateful agents over continuous data —

Memory staleness detection and auto-expiry for LLM agents

跑在 Claude Code / Codex 之上的本地多 Agent 协作脚手架:一个人下指令,主 Agent 拆解分派给专职角色,共用文件级记忆层。作者自用的主要方法是接到飞书bot，你只需要跟飞书bot聊天他就能帮你干活了

Official documentation for Taskade — build apps, deploy AI agents & automate workflows on the AI-native platform. REST & Action APIs, MCP server, Genesis. Source for docs.taskade.com — typos & gaps welcome via issues/PRs.

MindX is a modern AgentOS built for long-running, stateful and multi-agent collaboration. It offers full-stack infrastructure featuring agent orchestration, hierarchical persistent memory, multi-dimensional knowledge cognition, multi-terminal interaction and native storage capabilities.

A machine learning powered, voice-based virtual assistant for Raspberry Pi. Supports several features like conversation, weather, opening websites, geolocation, date/time, and creating timers.

The Agno demo showcase — agents, teams, and workflows built with Agno.

Standalone observability dashboard and developer playground for the Laravel AI SDK. Zero build steps. Telescope for your AI agents.

Local-first, private AI agent workspace for Codex and Claude. Own your context and run agents on your Mac.

面向企业内部授权场景的 AI 代码安全审计框架。支持 redteam/full 两种模式，支持靶场集成验证，全程自动编排。适配 Cursor、Claude Code 及其他支持 Agent 调度的 AI IDE。

Local-model-first AI agent framework — Router + Specialist architecture for Ollama

A private, offline 'second brain' for the people, projects, and decisions you juggle — and it keeps score of whether your judgment was right. 本地私密的人际情报与决策记忆系统。

md2video is a small agent-friendly workflow for turning source content into a narrated slide video.

CoDA is a multi-agent framework that turns natural language queries into publication-quality visualizations.

Raycast extension for real-time Claude Code session monitoring with hooks-based state tracking

A GDB debugging tool designed for AI Agents (Claude Code, etc.)

Koda is your ideal development partner.

Collection of Agents and Skills for Magento

My private AI tools and scripts

Claude Code plugin for EODHD financial data — 150k+ tickers, 70+ exchanges, OAuth MCP server with 80 tools, 7 workflow skills, financial-analyst agent, 5 slash commands. MIT.

Self-hosted control plane for long-lived AI coding agents — structured ACP timelines, multi-agent team workflows, and remote execution nodes in one surface.

Agent-first X/Twitter client in Go — JSON envelope per command, multi-account, cookie-safe anti-detection for autonomous agents

Claude Code status light system

OpenCode agent configuration — a read-only orchestrator delegates to 6 specialized subagents. Expert model plans, fast models execute. Isolated contexts, minimal permissions, adversarial verification built in. Ready to drop in.

Multi-agent swarm orchestration for Laravel, built on Laravel AI.

Open-source bitemporal knowledge graph — long-term memory for AI agents. Hybrid retrieval, conflict-aware ingest, GDPR forget. REST + native MCP.

Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install

Live context engine for AI agents: resolve verified workspace state before the context window opens. Pairs with Perseus Vault for persistent encrypted memory. Local-first, MIT. pip install perseus-ctx

Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.

领域无关的多 agent UI 自动化测试编排骨架，用 Claude Code 驱动「探索页面→设计用例→写测试→审查」流水线

Free, open-source local business intelligence audits for marketers and agencies. Run on your machine with real public data, and agentic workflow

Open-source, self-hosted personal AI runtime for durable goals, agent workflows, and automations—local-first, BYOK, and available on desktop, web, CLI, and chat.

Ask your video library anything — an AI agent that watches, reasons in a tool-use loop, and answers with playable clips and charts.

Mechanical plan/dev/self-audit/external-audit gates for AI coding agents. Claude Code, Codex, OpenClaw, and PyPI.

A small self-hosted guest lounge for your AI persona — friends chat via one-time links; you only ever see the AI-written visit summary. CC BY 4.0.

Spettro is a terminal coding assistant built in Go. It automates planning, coding, and testing with multi-agent workflows, model selection, and an intuitive UI. Connects to local and remote AI providers, supports conversation history, and empowers developers to streamline their workflow from the terminal.

ThreeJSON is a JSON-driven declarative scene runtime for Three.js, designed for persistent, mutable and extensible 3D worlds — from human-authored scenes to AI and Agent-driven generation and control.

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

NEWTON: Agentic Planning for Physically Grounded Video Generation

AI makes users productive — but also cognitively lazy. Lucid detects cognitive dependency in real-time and adapts AI responses to keep users thinking. Drop-in SDK: zero latency, any LLM provider, research-backed.

Production-ready iOS SwiftUI guidance for AI coding agents.

Hash-chained memory for AI coding sessions — decisions, coordination, and doctrine across sessions. Deterministic core; optional LLM assist.

Embedded on-device vector database for AI agent memory and local RAG — disk-based HNSW in an LSM-tree, C++/Python, optimized for low memory footprint

Open-source autonomous cybersecurity platform — 11/11 detection score, sub-300ms pipeline, honeypot deception, breadcrumb traps, AI-powered triage, and Rust endpoint agent. Built to replace Wazuh.

Multi-agent code review with Claude + GPT Codex in an adversarial debate loop

Complexity-aware agentic coding pipeline for Claude Code

Your AI coding agent just billed you. Here's the receipt. Cost receipts for Claude Code, Codex, Cursor, Gemini & opencode — no account, no upload.

Agent-first local harness for OKF-compatible LLM Wikis.

Hands On Workshop for GitHub Agentic Workflows

RunComfy AI media skills for Claude agents — incremental publish test

AI agent skills for Catalyst by Zoho — enables Claude, Gemini, Cursor, Copilot, and Windsurf to write deployment-ready Catalyst code, recommend architecture, and manage infrastructure via Zoho MCP.

🏆 AI Agent 生态排行榜：Skills · MCP 服务器 · Prompt 库 · 框架 · 深度研究，按 GitHub Stars 每日更新 | Leaderboard for AI agent ecosystem — Skills, MCP, Prompts, Frameworks & Research.

Minimalistic, project-agnostic skills and rules for AI coding agents

给 HR/猎头的 AI 招聘工作流：岗位标准梳理、Boss直聘+猎聘双通道寻源初筛、市场人才盘点、简历评估、约面试、候选人台账与日报。配合任意 AI 编程助手使用。

Approve and monitor Herdr agents remotely from your phone — a mobile web app for Android/iOS smartphones with push notifications, QR setup, and multi-computer relays.

100 道大模型面试题与 100 张 SVG 图解，覆盖 LLM、RAG、Agent、微调、推理优化和评估。

面向中文用户的学术论文与科研 Agent Skill 每日排行榜 · 自动搜索、过滤并排名 GitHub 上的 Claude Code / Codex / OpenCode 科研 Skill 仓库

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human approval, execute-once gateway, tamper-evident receipts. Open core, Apache-2.0.

Open-source AI funding workspace for consultants, advisors, and incubators. Manage opportunities, companies, applications, and AI-generated funding packages.

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline on Windows, macOS, or Linux. No installs, no internet, just plug and play.

GraphRAG Agent 是一个面向私有知识库的全栈图谱问答系统。它将文档上传、文本解析、分块、知识图谱抽取、索引任务编排、可视化编辑和问答记录整合在一个受认证保护的工作流中，并为多用户场景提供用户自带 API Key（BYOK）能力。

A lightweight Godot framework + agent skills for building and shipping games

Open-source TypeScript framework for building operational software used by humans and AI agents.

A focused Hermes profile for learning the agent without tool overload

Compare the best SERP APIs by pricing, latency, coverage, and use cases for SEO tools, AI agents, rank tracking, and search automation.

Official Repo for Chat AI

YATSEE - Yet Another Tool for Speech Extraction & Enrichment

A visual history of the opportunities Brazilian developers miss. Three Claude Opus 4.7 agents read your work, crawl the world weekly, and write a personal 90-day plan with honest why-you reasoning. Open source, AGPL-3.0.

Store, query, and create YAML workflow playbooks for LLM agents via MCP. STDIO or Streamable HTTP.

这是一个结合了RAG（Retrieval-Augmented Generation）和网络搜索功能的Agent项目，能够同时检索本地知识库和进行网络搜索，为用户提供全面的信息服务。项目通过API调用大语言模型进行推理，同时使用本地的bce-embedding-base_v1嵌入模型和Chroma向量数据库处理本地知识库检索，并采用ms-marco-MiniLM-L-6-v2交叉编码模型进行结果重排序。支持多角度查询和抽象查询等高级检索策略，提升检索准确性和回答质量。

A unified Model Context Protocol server for MiniMax CLI (mmx)

LLM-based AI Agent Knowledge Sharing

A Continual Multi-agent RL testbed based on Hanabi

[ICML 2021] DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

Tana 是一只史莱姆桌宠，工作、学习搭子。

Complete demo of Google ADK Visual Agent Builder with multi-agent research system

Codingbuddy orchestrates 29 specialized AI agents to deliver code quality comparable to a team of human experts through a PLAN → ACT → EVAL workflow.

MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows.