Custom agents

Token-efficient CLI for AI agents to read, write, and collaborate on Google Docs & Drive.

A full-stack AI assistant built on Amazon Bedrock AgentCore. This sample demonstrates how to build a feature-rich, self-hosted AI assistant that leverages AgentCore capabilities like managed runtimes, sandboxed code execution, and persistent memory.

A fully local document intelligence system that allows users to build a persistent private knowledge base from documents and query it using retrieval augmented generation. The system runs entirely offline with local embeddings, vector search, and LLM based answer generation.

MiniMax Code Review for GitHub Actions

🔐 Replayable RAG — a local-first, auditable knowledge-reasoning platform. Graph-RAG + append-only audit log + deterministic contradiction arbitration + human-gated self-evolution. Replay any past knowledge state byte-for-byte. 100% local (Ollama). MIT.

Superpowers for Google Antigravity — composable skills, smart workflows, and always-on rules that turn your AI agent into a senior engineer.

🐉 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！

Multi-agent simulation platform where AI agents self-organize on a Kanban board — built with LangGraph, Google A2A, and MCP.

Практический курс по Agentic AI: от основ LLM до создания автономных агентских систем. Оптимизирован для просмотра в Obsidian.

A comprehensive, implementation-focused guide to evaluating Large Language Models, RAG systems, and Agentic AI in production environments.

Persistent shared memory (hive mind) for OpenCode agents, powered by the mnemoria Rust engine

Advanced Markdown text chunker tool plugin for Dify RAG / knowledge bases

Automatically filter sensitive information from RubyLLM conversations using Top Secret.

Ultra-fast indexed code search engine — faster than ripgrep on repeated searches, lighter than zoekt. Built-in MCP server for AI agents. Also does fast file finding (fd/find alternative).

A curated list of autonomous AI research agents — from idea generation to experiment execution and paper writing. 16 projects, community usefulness poll included.

Tool-native dataset generation skill for Codex, Claude Code, and Antigravity with SFT/DPO pipelines, verification, deduplication, and flexible export.

Semantic code intelligence for AI agents — compile repositories into navigable concept graphs with impact analysis, coupling detection, and prophecy.

Operational SDD framework with AI guidance, GitHub Spec Kit workflows, and MCP support.

Arogya-AI is a hybrid intelligent healthcare system that integrates machine learning and large language models with Ayurvedic principles to provide personalized health assessment, symptom interpretation, and preventive wellness recommendations. The system bridges traditional knowledge and modern AI to enable accessible, explainable, and user-centri

智能简历助手 - AI-powered resume assistant with 5 specialized agents for Chinese job seekers | Claude Code Skill

Tools for securely exploring your iMessage history with AI. Spotify Wrapped for texts, conversation analytics, search, streaks, and more. Read-only MCP server for macOS.

GitHub-ready Codex plugin bundle for Yandex Direct, Wordstat, Metrika, Roistat, Audiences, and Yandex Search API workflows.

TypeScript AI agent framework with recorded context, tool calls and decisions, plus configurable answer checks.

An "all-you-need-to-know" practical guide to using AI and LLMs responsibly and effectively for economics and finance research: from core skills and ChatGPT/Claude Projects to coding, writing, reproducibility, and automation. 小红书账号：SuperJay

A self-hosted software factory — define goals, agents decompose and execute them through enforced pipelines, with humans in the loop where it matters.

An intelligent orchestration system that automates the software development lifecycle from Feature ideation through code delivery using AI-powered planning and execution.

飞书（Lark）或微信（WeChat）聊天控制 DeepSeek Harness / Claude Code / Cursor / Codex / CCC Agent

Agent Orchestration: MCP server enabling multi-agent collaboration with shared memory, task queue, resource locks, Cursor rules, and AGENTS.md workflows.

Real-world browser-agent benchmark: 210 tasks across 107 websites, multi-agent/multi-browser evaluation, reproducible leaderboard and result submissions.

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

Spring Boot + Spring AI 实践项目：聊天、RAG、工具调用、MCP、记忆、SSE 与 Vue 前端联调。

Travel-planning skill for AI agents: live flights, tours, hotels and excursions with prices and booking links.

AI trading agent with a skill system: drop a SKILL.md file, declare your tools, ship. Built-in planner, pattern detection, strategy backtesting, 9 LLM providers, multi-agent simulation, and a full Next.js web UI bundled into one pipx install.

Organised collection of resources for local AI agents - covering CLIs, tooling, and more.

Production-grade Node.js RAG system with hybrid retrieval, pluggable adapters, and OpenTelemetry tracing

Open-source engine for turning documentation sites into searchable, MCP-accessible context for humans and coding agents.

Local Sovereign Multi-Agent Swarm OS & Cockpit for Autonomous AI Coding Agents. 28 Personas, 45 Core MCP Tools, Sub-10ms Trigram Search, Zero-Console Background Swarm. Official: https://uikode.com/acs

Code intelligence engine for AI coding agents. Structural graph queries plus semantic search, exposed via CLI and MCP.

the open source claude agents that learn to trade across defi on meteora, solana, hyperliquid and polymarket

Repo-native project memory for AI-assisted development: workorders, playbooks, examples, checks, handoff rules, and release-readiness discipline.

Your AI assistants don't know who you are. mcp-me fixes that: a local MCP server that gives any AI a full picture of who you are

Craftsman Agent is a creative design agent and store that transforms ideas into digital assets and finished products by Manufacturing on Demand Platform. Available Apps Skills include Image Generator, 3D Generator, Toy Generator, Perler Beads Pindou Art Designer,Social Media Posts Designer, Tesla Car Wrap Designer, 3D Printing Designer and more.

Multiplayer harness where humans and AI agents work together and build on shared context.

Open-source toolkit for building AI agents that interact with blockchains — DeFi, restaking, token sniping, portfolio tracking, bridging, and more.

Self-hosted personal knowledge brain for Telegram, WhatsApp, n8n, Groq, and Obsidian. Save links, voice notes, and images; auto-summarize, categorize, tag, transcribe, set reminders, share guest access, and ask questions later from your Markdown knowledge vault.

Enterprise-grade sovereign AI for organizations where SaaS AI isn’t an option.

Let Codex test multiple fixes in isolated worktrees, compare evidence, and apply only the safest proven solution.让 Codex 不再盲改代码，而是并行测试多个方案，用证据选出最稳的修复。

Visual RAG workflow studio that auto-generates eval sets, runs RAGAS evals, and deploys workflows as local HTTP APIs.

A visual map for long AI conversations (ChatGPT / Claude / Gemini)

Manage your tasks with AI.

MCP server for searching AI agents, MCP servers, CLI tools and agent skills via A2ASearch

One command, 28+ top AI CLIs — an interactive launcher for terminal AI coding agents (Claude Code, Codex, Gemini, Aider…). Uzbek & English

The harness with muscle memory — activity tracing, pattern detection, and one-command workflow execution for Claude Code, Cursor, and Codex

Parallel coding agent workspace with native terminals and git worktrees.

您好，我是SILI /『IM机械姬』SILI-t138-[Manura]-Invoke-II@LD(A) / 自豪地基于 Koishi.js v4开发~

SSH workflow helper for LLM agents

Persistent memory & RAG engine for AI agents — SQLite + FTS5 + embeddings, multi-stage recall, sleep maintenance, multi-host hooks

Talk through a bug. Your agent writes the ticket.

Leave agents running without giving up control.

Local-first dashboards your AI agent builds and keeps maintaining, over data that never leaves your machine.

上传表情包 → AI 自动写描述 → 聊天机器人按场景自己挑着发（含双向发送 / 多端渲染 / 踩坑思路）

A modular framework for building complete AI solutions. It's mostly a Rust framework with a subset of it ported to Deno.

Expose typed web-app actions to MCP-compatible AI agents over WebSocket. TypeScript SDK + matching MCP gateway.

Hermes Agent profile for adaptive multi-agent coding teams with GitHub issue-to-PR automation, blind critique, synthesis, CI schemas, and fail-closed unattended merge policy.

Human-in-the-loop review interface for AI coding workflows

AI-powered penetration testing with Claude Code agents. RedTeam Barranquilla - Automating security assessments using PTES methodology.

a secret store for ai agents with one rule: the agent never sees the plaintext. get a secret once into the os keychain, then inject it into commands forever. no get, cross-platform, mit

Command-line client for the Harmont CI platform

Design UI changes from real source code — verify data, iterate faithful HTML mockups, then delegate. A Claude Code plugin & Codex skill by nlook.me

Reproducible research publishing template for Python research projects: a declared pipeline, canonical exemplars, and multi-format outputs.

Reusable AI video prompt skills for Seedance 2.0 / 即梦: product-selling scripts, merchant dance lead-gen scripts, and trend-driven traffic prompts.

Next generation role-playing with LLM - with AI world and intelligent NPCs and multi-faceted Graph memory for all entities and a rich pipline and multi agent

Self-hosted AI agent on K8s that reads live pods, events, and logs. Local LLM (Mistral/Ollama), FastAPI, read-only RBAC, ArgoCD + Image Updater GitOps.

Self-hosted, agentic vulnerability research for binaries & firmware: an AI agent decompiles, fuzzes, and verifies exploits inside a sandbox, recording every finding to a typed graph. BYOK, fully local.

AI Agent Full-Stack Development Roadmap

5-agent AI team for Claude Code operators: Iris (design), Lyra (build), Echo (scout), Newton (research), Hypatia (critic). One-command install, context-loading hook included.

12 agent skills for AI-driven software development — a gated idea-to-ship pipeline: 7w3 design, build-ready specs, executable architecture, honest review loops, a parallel worker-fleet lane, QA, safe deploy. Works with Claude Code, Codex, Cursor and any skills-capable agent. No vibecode.

A scope for your Ai coding-agent sessions

AI readiness & verification toolkit — measure how ready your codebase is for autonomous AI coding agents, and get a roadmap to autonomy. Plugins for Claude Code, Kiro, Cursor, Codex.

The chef's standard for AI agent work: twelve rules, a critique gate, and project memory. One skill. Craftsman's taste. Zero AI slop.

Claude Code agent skill for RimWorld mod development. 环世界Mod制作全流程Claude Code技能——XML Def、C#、Harmony补丁、Steam Workshop发布

用于立创硬件开源广场项目介绍的AI技能。AI skills for introducing the OSHWLab project

Academic research skills for literature review, evidence checking, writing, slides, figures, and research workflows.

An autonomous, self-evolving quantitative trading system powered by 8 specialized AI agents with institutional-grade risk management.

PostgreSQL-native GraphRAG. Vector search, full-text, and knowledge-graph traversal in a single SQL query. No Neo4j. No Pinecone. No AGE.

The AI agentic designer — open-source React design system + MCP that lets Claude, Codex, Cursor & Gemini build production UI in minutes. No AI slop.

MCP server for PixelPanda — 31 AI image processing tools for Claude Desktop, Cursor & other MCP clients

一个本地ai聊天模型localaiAgentWithRAG，让你的本地数据不上传云端，可以自己加入所需要的记忆文件等等，修改角色形象，记忆对话，记忆库允许自己导入或者对话后自动记录

Evidence-grounded AI agent for Java code repair with LLM-guided patches and human-in-the-loop review.

Terminal discovery hub and package manager for AI coding tools, MCP servers, and agent skills. Built with Python & Textual

Give Claude a checklist before bed. It can't clock out until every box is ticked, never stalls on a question, and revives itself if the API dies at 3 AM.

Your AI development team — 27+ agents and 21 skills that build, review, debug, and ship production code. Works with Claude Code, Cursor, VS Code, Windsurf, Codex, and OpenCode. 7 framework packs: Vue, React, Next.js, SvelteKit, Angular, Astro, Nuxt.

Describe an app, watch it run. Multi-model code generation into live E2B sandboxes — Next.js, Vue, Streamlit and Gradio templates.

AI-automated SDLC pipeline with human-controlled quality gates, for Claude Code — spec before code, evidence before pass, a human sign-off at every stage transition. C#/.NET · Node.js · PHP/Laravel.

Graph-native studio, runtime integration, and self-hosted observability for mutable multi-agent LLM workflows.

A production-grade Python AI Agent framework with persistent memory, hooks-driven architecture, and compute-storage separation.

Claude Code Growth Operating System (OS): Sales, Marketing, Product and Retention as one Revenue system

ClawSouls — an open-spec platform for shareable AI agent personas (souls). 80+ curated souls, one-command install, works with any SOUL.md-compatible agent (OpenClaw, Claude Code, Cursor & more). Apache-2.0.

Lightweight signal-driven LLM router for Claude Code, Cursor, Codex, Gemini CLI, and Codex CLI