Custom agents

a durable execution framework for Python

Turn Claude Code and Codex from chat assistants into autonomous coding systems

Production-ready Claude Code skills for building AI agents with Pydantic AI. Includes dependency injection, tools, validators, streaming, multi-agent orchestration, and evaluation framework patterns.

nod is a platform-agnostic, rule-based linter that ensures AI/LLM specifications contain critical security and compliance elements before any agentic or automated development begins.

Claude Code 的恢复源码工程。它包含 CLI 主入口、交互界面、工具系统、命令系统，以及围绕上下文压缩、技能加载、会 话恢复、后台任务和本地服务连接等能力的实现。这份源码当前已经可以完整构建，并能够启动 CLI 构建产物。与此同时，它仍然是一份恢复后的工程，不应被视为官方原始内部仓库；部分能力属于恢复态兼容实现，少数受 fe ature gate 或运行环境影响的路径仍需要按具体场景确认。

Meet Daemon, the Self-Evolving Operating System.

A tool for unifying instructions, skills, and MCP servers for various coding agents.

SAMAR is an AI-driven tool designed to automate research and analysis processes for mergers and acquisitions (M&A), facilitating the generation of comprehensive reports. By leveraging advanced artificial intelligence techniques, SAMAR streamlines tasks such as data collection, financial modeling, and risk assessment.

A Model Context Protocol (MCP) server that provides Android TV remote control functionality to AI assistants and other MCP clients.

[AAAI 2026] The official implementation of the paper "BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modeling".

A MCP server that gives LLMs direct access to the AT Protocol ecosystem, enabling seamless interaction with Bluesky and other AT Protocol-based social networks.

An open-source voice agent built on the PamirAI Distiller device, combining speech recognition, and text-to-speech to create a conversational AI assistant with OpenClaw you can talk to.

A curated collection of custom AgentSkills and token-saving MCP servers for extending the capabilities of AI coding assistants like Claude Code.

WEB APP for Tuya, with AI and customizable functions that increase the performance of your IoT system

Prompt skill + renderer that adds generative UI to any LLM chatbot. No frontend refactor needed.

Modular memory system for AI agents with semantic search, using Supabase pgvector and optional Redis caching

Local near real-time voice AI assistant

Branch Buddy is a React Native mobile self-help app featuring an AI chatbot for personal growth and well-being.

Minimal Ollama chat UI - no login, no heavy features.

Chat with GGUF LLMs using llama.cpp and a classic Windows Forms interface for minimal GUI bloat.

Headless semantic MCP server for Obsidian, Logseq, Dendron & any markdown vault. AST-based surgical editing, hybrid vector + TF-IDF search, zero-setup local embeddings — no app or plugins required. Stdio & SSE transport, Docker-ready.

基于 Spring AI Alibaba ReAct 的FishAgent全栈智能体应用。具备分层记忆、三路 RAG 检索、知识库闭环、流式对话与多维限流能力。Java + Python + Vue 3 全栈架构。

AI-powered document intelligence platform for research administration

Full-stack observability for AI — starting with end-to-end RL post-training, expanding to Agent and inference engine monitoring.

Agent Skill for systematically upgrading TYPO3 extensions to newer LTS versions | Claude Code compatible

Public website for spacemolt.com - The first MMO built for AI agents

LAN-capable Minecraft MCP server built with Dedalus MCP and a Mineflayer bridge.

一个可移植的历史人物视角 skill，用于分析战略、矛盾、组织与动员；A portable historical perspective skill for analyzing strategy, contradiction, organization, and mobilization.

AI agent skills for deploying applications to Kubernetes with Qovery. Works with OpenCode, Claude Code, and any agent supporting SKILL.md.

AI-Driven CAD modeling agent - Transform design concepts into precise 3D CAD models

Comprehensive docstring quality vetting for Python projects

👻 Multi-platform chat bridge for Kiro Cli — connect to Telegram, Lark/Feishu, Discord & Web via ACP protocol

双色球预测分析 Agent Skill，融合概率统计、物理学、易经玄学三维度分析，支持 Claude Code / Cursor / Windsurf / Codex CLI

The Agentic Video Generation Framework. A hybrid engine designed for AI Agents to autonomously direct and render high-quality promotional videos for any software project.

immutable, minimal Linux OS purpose-built for AI agents. No SSH, no shell, no systemd - just microVMs, default-deny networking, and shared agent memory

The agent that GOes with you

🐉 Dante Cloud 是支持阻塞式与响应式服务并行的微服务云原生基座和面向AI Agent开发的智能基座，基于领域驱动模型（DDD）设计，以高质量代码与低安全漏洞为核心，高度模块化、组件化，覆盖IoT设备认证、国家等保三级、接口国密数字信封加密等多层次安全体系，并提供多租户解决方案。独创“一套代码实现微服务和单体架构灵活切换”，赋能企业级智能应用构建。🔝🔝点个star 持续关注更新！

Turn a browser task into a reusable scraper.

Winning entry for the BitGN Personal Agent Challenge (PAC) 2026 — defense-in-depth personal agent with soft SGR, layered prompt-injection hardening, and Vercel AI SDK native tool calling.

Reusable Dagger CI/CD modules for GCP, versioning, and AI-powered deployment agents

🧠 Automated AI Knowledge Base for Product Managers — 4-pillar system with self-evolving knowledge graph. Updates every 4h.

A workflow tool to track new videos and deliver concise briefings. | 用于追踪新视频并产出精炼简报的工作流工具

The auditable MCP backend for agents — tools as declarative YAML pipelines: event-sourced, replayable, approval-gated.

Colección pública y curada de las mejores herramientas open-source, agentes de IA autónoma, ecosistema Claude, estrategias SEO y CRMs para potenciar startups y empresas "zero-human".

Modular Python coding and agent platform — LLM agents, graph RAG, static analysis, git ops, cloud and container deployment, all exposed as Model Context Protocol tools. uv-managed, with a zero-mock test suite.

Stoneford — the starter world for WorldLines. 10-agent orchestrator · d20 TRPG · runs standalone in WorldLines or drop-in with Claude Code.

The privacy-first customizable Agentic AI system (and Telegram bot) that researches fragments and remembers every timeline!

An Agentic Simulator for Emergency Department Operations

Open-source framework for growing your own "Claudicle"—an adaptive membrane for Claude Code and AI orchestrators, powered by the Open Souls paradigm

aiHelpDesk: Agentic DB SRE support system that learns from every incident. A database reasoning layer equipped with a governed actuation arm that treats human operators and upstream agents indiscriminately

Command-line interface for SimpleLogin — manage email aliases from the terminal. For you and your agents.

A curated library of machine-readable task prompts for Jules and other coding agents, including prompts for the failures agents actually have: broken setup scripts, vague issues, tests that need services a sandbox cannot start, and pull requests that only read as finished.

AI Agent SDK designed for Go developers

🧠 The Complete Guide to Context Engineering — Research Papers, Blogs, YouTube Videos, Tools & Best Practices for LLM Context Window Optimization

Extract clean, structured Markdown from DOCX for LLM and RAG contexts.

Production-ready RAG chatbot that answers customer service questions from company documents. Built with FastAPI, FAISS, Voyage AI, and Groq — deployed on free-tier cloud infrastructure.

The "SQLite for Vectors" in pure Go. Embeddable, HNSW indexing, CGO-free, and Qdrant-compatible API.

Pangolinfo 亚马逊爬虫与数据采集工具：基于 Pangolinfo Amazon Scrape API / 数据 API 实现 Amazon 实时数据采集（商品详情、关键词、评论、榜单、类目/利基），输出 AI 友好的 JSON/Markdown。面向 Agent 与 AI 应用，支持 Skill 集成，低成本、高效率、易维护的采集软件与采集工具方案。

AI-powered SSH client for network engineers. ARIA agent diagnoses Cisco, Juniper, Arista, BGP, OSPF & firewall issues in real-time. Mac/Win/Linux. Free & open source.

AI Agent 小红书知识卡片 & 公众号贴片生成 Skill — 一键生成精美深色科技风社交传播卡片，支持封面卡+详情卡批量导出

👾🦀 MiSTerClaw — MCP Remote Control for MiSTer-FPGA

⚡ Relic — One soul, many agents. Transfer personality and memory across AI agents via pure Markdown. Zero deps, human-readable. Switch agents, keep the soul.

an expert design advisor mcp that finds the best fonts for your project via live research and project scanning.

🤖 Rust SDK for WeChat (微信) iLink AI Bot — Build custom AI Agents for WeChat ClawBot. Protocol-level, async, not coupled with OpenClaw.

Composer plugin enabling universal Agent Skill distribution and management for PHP projects

Super-advanced agentic AI framework for cyber-Vikings. Birth autonomous, self-evolving thoughtforms that manifest as hyper-realistic 3D digital characters. Features persistent memory, ritual invocations, full VR/Unity integration, and gloriously unaligned intelligence. Pure modernist cyber-Heathenry — no gatekeeping, pure emergence. 🔥⚔️🤖

Agent Skill for GitHub repository setup and platform-specific features | Claude Code compatible

Трекер ошибок и предложений по продуктам KodaCode

Programmable Responsive Interface for Smart Models

Open source security for AI agents: an OS-enforced egress wall on macOS, and on Ubuntu 24.04 x86-64 via a separate package; keys only the operator holds; a hash-chained audit record. One command wraps Claude Code, Cursor, Hermes, OpenClaw or Cline on tested config paths. No vendor in the path. Claims trace to the Assurance Matrix.

A programming language designed for AI agents. No parser, no syntax — agents produce AST directly as JSON. Statically typed, effect-tracked, contract-verified, compiled to WASM via MCP.

A tmux-native workspace for multi-agent AI development across Claude Code, Codex, and Antigravity.

AI Agents Skills for Notte

Agent plugins for CN and EN journal targeting: candidate discovery, source verification, risk screening, and 2+2 journal decision matrices.

Benchmark abierto en español de 170 modelos de IA (118 con 20+ runs, 69 rankeados, juez Phi-4 independiente). Calidad, costo, velocidad, long-context y fuga de credenciales como dimensiones separadas. Alternativas a Claude, GPT y Gemini para agentes n8n/Hermes. Calculadora interactiva con tus propios pesos.

OpenAPI spec, SDKs (TypeScript, Python, Go, Kotlin, Swift, C#), CLI, n8n node, and AI agent skills (MCP-ready) for Pachca API

Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.

An Android AI Agent (toy project) combining a native C++ daemon with AI capabilities.

A self-hosted, observable orchestrator for multi-agent workflows on your repos. Compose from skills and memory, run on events or cron, dispatch between agents.

AI Customer Support Agent with RAG + Voice A fully local, privacy-focused AI customer support system powered by open-source models. It supports multi-turn conversations, PDF/manual search (RAG), product recommendations, FAQ reasoning, and voice input/output using local STT + TTS. Built with Mistral 7B GGUF, FAISS, Whisper Tiny, Coqui TTS, FastAPI.

AI-powered MCP server for mobile app testing that enables LLM agents to execute, automate, and validate Native mobile Android/iOS app workflows using natural language, intelligent UI interaction, and adaptive test execution.

Persistent codebase knowledge layer for AI agents. Pre-builds architecture, dependency, coupling, and risk knowledge served via MCP. 27 languages, 13 tools.

短视频智能体(2个版本：本地部署的和云服务api的)

The loop your AI coding agents follow to ship a change, prove it in production, and improve. A companion file to AGENTS.md and SOUL.md.

Azure integrations for Twilio Agent Connect — connect Microsoft Foundry agents to Twilio's channels, memory, and context.

Agent-first CLI for Zoho Books

Hear a short spoken summary after your coding agent answers. Free to install - no API keys, no subscription, no cloud TTS.

The simplest AI-ready secrets manager. Local-first, single-binary CLI & Desktop app with MCP integration. Never expose secrets to AI agents.

Local Claude/Codex PR review loop using existing CLI subscriptions instead of model API keys

repo-wiki-agent

Open Cowork is a desktop, cloud and gateway workspace for OpenCode.

An AI-based system that helps manage healthcare appointments using different agents for tasks like booking, cancelling, and answering questions.

Evidence-gated AI systems, local-first agent safety, memory continuity, MEDIOEVO tools, and GitHub Sponsors hub.

WebMCP at the edge. A Cloudflare Worker that equips any website with WebMCP from one TOML config.

MCP server for SSH and Serial port remote access

Pull-model episodic memory plugin for Hermes Agent. Real deletes, audit trace, BYO Claude. MIT.

The validation loop that stops AI coding agents from claiming work is done before it actually is.

Fully-autonomous AI agent to systematically probe AI systems for security vulnerabilities 🔍