Custom agents

米游社高效率机器人SDK

A complete A–Z guide to Natural Language Processing (NLP) using Python — includes real-world projects, machine learning models, and chatbot implementations. Ideal for students, researchers, and data science enthusiasts.

Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement

Dynamic RAG-powered skills service for code assistants via MCP - Vector + Knowledge Graph hybrid search for intelligent skill discovery

Applying domain specific evaluations to RAG chunking and embedding functions

AI Intelligence Platform -- knowledge graph + semantic search + reasoning + multi-agent debate in a single binary

A CLI context hub for agentic work. Used by the Speakeasy engineering team

The field manual for running a real self-hosted AI agent with OpenClaw.

A sleek, open-source desktop client for OpenClaw. Built with React, Vite, and Electron for a fast, responsive, and experimental "Vibe Coding" experience.

Ship product, not plumbing. Open source framework for AI-first SaaS — identity, OAuth, API auth, webhooks, notifications, and agents in one stack.

Hire a whole company with one plugin. 75 specialized AI agents across Engineering, Product, Infrastructure, Data, Security, Marketing, Sales, Finance, Legal, and People.

Long-running unsupervised agent framework

Your all-in-one skills-as-a-service platform to manage your skills, auto-generate skills and use agent skills as simple as calling an API.

infrastructure chaos to test the resilience of ai agents

Portable web-research and browser-automation SKILLs for Claude Code, Codex, and OpenCode — Playwright, Chrome DevTools, nodriver, and HTML-to-Markdown.

Oneshot — One-time screenshots for AI agents. Mac menu bar utility.

An agentic product lifecycle accelerator. Give it an idea, get a PRD, research plan, design spec, tech spec, and backlog — in minutes.

Safety benchmark for personal AI agents under realistic prompt injection. 120 test cases across 5 professional domains, 3 injection vectors, and 5 harmful action types. (arXiv 2026)

Headless terminal emulator CLI powered by libghostty-vt

open-source CLI written in Go for translating apps, website and content with AI

在线客服，chatbot，chat，ai，AI Chat，在线客服转人工，大模型聊天，大模型IM客服，可与FreeAICC电话呼叫中心整合。

Rickbot ADK - a multi-personality chatbot built using Google ADK and Gemini, and leveraging Agent-Starter-Pack and Gemini CLI

Separator: Bitrix24 Integration Hub

Türkçe SQL Server 2025 başucu kitabı: kod örnekleri, errata, topluluk soru-cevap · CC BY-NC-SA 4.0 + MIT

Secure AI Memory MCP Server with Multi-Tenancy, Dynamic Project Routing, Auto Session Briefing, Personal+Team Summaries, Hybrid Search, Knowledge Graphs, GitHub (Issues, PRs, Actions, Kanban, Milestones), Git Mining, Team Collaboration, Native CLI, Analytics, Markdown I/O, Audit Logs, OAuth 2.1, HTTP/SSE/stdio & Unified Code Mode.

SearXNG adapter for OpenClaw — enables free, privacy-respecting web search without a Brave API key or any paid search subscription. Route your AI assistant's queries through your own self-hosted SearXNG instance.

A privacy-first, self-hosted AI assistant that plugs directly into your Home Assistant stack, this project turns local LLMs into a practical automation brain—capable of understanding natural language, calling tools, and orchestrating real-world actions across your devices without relying on the cloud. Designed for hackers and builders.

Every AI tool forgets you after every session. This repo doesn't. Ever. Zero install, zero config. Just fork and your AI remembers everything, everywhere, forever.

AI Agent Hub - Plataforma Completa para Criação de Agentes de IA com RAG Plataforma full-stack desenvolvida para criar, gerenciar e interagir com agentes de inteligência artificial personalizados, com sistema avançado de RAG (Retrieval-Augmented Generation).

Statistical evaluation framework for AI agents

Self-hosted hub that gives all your AI tools one shared memory, one toolbox, and a way to hand work to each other. Claude, ChatGPT, Codex, Gemini and any MCP client connect once; your data stays in plain Markdown files on hardware you control. Runs on a NAS, a Pi, or your own server.

Environment-mediated coordination protocol for agent fleets. Safety enforced at the boundary, not inside the agent.

Official PyTorch implementation of "MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks"

Give AI coding agents (Claude Code, Cursor, Aider, Codex) a structured autonomous loop with guardrails — boundaries, 5 verification gates, 3-layer self-reflection, and autonomous remediation. pip install ouro-loop. Zero dependencies.

Run a 4-agent AI company on Gemini free tier. 105 daily tasks, $0/month. Complete playbook with scripts, timers, and docs.

SAM - Autonomous TDD agent system for Claude Code, Cursor, Gemini CLI, GitHub Copilot, and Antigravity. PRD in, working tested app out.

An MCP server that gives coding agents instant insight into any Git repository — no guessing, no hallucination.

AI+Human software delivery methodology with risk-tiered governance, executable gates, an evidence-based lifecycle and tool-agnostic agent integration. MIT.

AI platform for GitHub pull requests with a cloud coding agent for autonomous code review, background issue resolution, and automatic PR title/summary generation.

Orchestrate a full feature lifecycle with human-in-the-loop gates across all SpecKit phases

MCP server for Liveblocks.

One place to talk to all your agents

stdio Bus: agentic process supervisor and message router, handling NDJSON-framed JSON-RPC messages with session-based routing while remaining completely agnostic to protocol semantics.

Developer tools, CLI, SDK, and documentation for MUTX & PicoMUTX


HyDRA: Hybrid Dynamic RAG Agents, An advanced, agentic AI framework that transforms Retrieval-Augmented Generation from a static pipeline into a dynamic, learning reasoning system.

Chatons is a desktop AI workspace for coding and project workflows: it lets you chat with multiple AI providers, pick scoped or full model lists, manage skills/tools, and keep conversations organized in one place.

mAItion is an all-in-one ready-to-use AI-powered tool that combines your existing knowledge with LLMs, allowing you to chat, search and interact with your data through a slick chat interface.

A production-gradeRAG platform built on distributed systems principles. Designed as a reference implementation for engineering teams who want to run RAG in production.

Save AI-generated paper summaries and deep lessons as formatted Zotero child notes.

Spec-driven governance for AI coding agents: project conventions, adversarial quality gates and a spec-to-ship pipeline for Claude Code, Codex and Antigravity CLI

🤖 AI Agent 数据库工具技能集 | Database tools skills for AI agents, compatible with OpenSkills. Supports MySQL, SQL Server, DM8, SQLite.

Chat-first toolkit for teachers to plan complete courses and lessons with multi-agent workflows, template-based artifacts, and MARP slide generation.

TUI for managing multiple AI coding agents in terminal tabs and panes, plus a Go library (libatria) for discovering agents and watching their status.

Universal MCP server for logistics. Connect any TMS/WMS to AI agents. Shipments, carriers, tenders, tracking — all via Model Context Protocol.

Standalone MCP server that gives AI agents full GUI control over macOS — screenshots, mouse, keyboard, apps, clipboard, and multi-display. Zero private dependencies.

The academic meta-prompting framework for AI agents like Claude Code, Gemini CLI, OpenCode. Features citation-aware drafting, hallucination checks, and rigorous structural planning. Built for PhDs and PIs who are tired of writer's block. AI is powerful; WTF-P makes it tenured!

Automated parallel code reviewer using AI Coding Agent CLIs

Opinionated Kiro project template with 40+ steering docs, 34 agent hooks, sample specs, and a CLI scaffolder — get a production-ready .kiro/ setup in seconds.

🛡️ Automate web app pentesting with AI to find real exploits before attackers do, enhancing your app’s security proactively.

Token-efficient browser verification for AI coding agents

AI-powered SEO content automation agent skill — trend scouting, competitor analysis, article generation in 55 languages, social media adaptations, and cron-based sessions.

A secure, local-first Python framework for orchestrating complex multi-agent think tanks with dynamic expertise-weighted routing.

Type-safe, async Rust SDK for the Agent2Agent (A2A) protocol, built to the final v1.0.1 spec — JSON-RPC, REST, WebSocket & gRPC for building interoperable AI agents

Kimi Help Center is an intelligent Q&A routing system that directs user questions to the right help articles across the full Kimi ecosystem — covering Agent mode, Deep Research, Kimi Code, Kimi Claw, Docs & Sheets, PPT/Slides, membership & billing, and API services.

BTK için hazırlanan Erişim Destekli Üretim (RAG) Tabanlı Sohbet Botu Eğitimi Belgeleri

Persistent ontology driven knowledge system with formal OWL-RL reasoning, SPARQL graph + SQLite, and 22 MCP tools for AI agent memory.

RAG-Mail is a thread-aware email processing system that semantically indexes conversations and attachments for context-rich retrieval using RAG.

MCP server wrapping the Shopline Open API into 143 AI-callable tools (75 read + 68 write) for e-commerce operations. Built for Claude Code, Claude Desktop, and any MCP-compatible AI client.

Autonomous BTC & SOL trading bot for Polymarket. ARB (100% WR) + SNIPE strategies. Auto-trades via py-clob-client, auto-claims resolved positions, Ed25519 signed receipts.

MethodCraft — generate customized AI Skills from proven methodologies

Experimental Chrome side-panel browser agent with LangGraph.js, MCP/WebMCP, local models, and semantic browser automation.

Persistent, queryable memory for AI agents with intake policy, smart recall, context packs, graph recall, and multi-agent scoping

YzPzCode - The Unified Workspace for AI Coding Agents

EDINET XBRL parsing library and MCP server for Japanese financial data

🧠 A self-contained, frontend-only RAG chat interface. Plug in any RAG API URL and Bearer token—no server, no setup, full local history, and zero dependencies.

Personal AI Chief of Staff -- built on cognitive architecture principles

Geometric agent memory for Agents: 8-tool lean contract, harness injection at wake, session handoff. 79 MCP tools. Not a vector DB. Rust + MCP.

Real-time dashboard for spawning and controlling AI coding agents across multiple hosts. Streams live terminals via PTY, tracks token usage with OpenTelemetry, supports git worktrees, and deploys with rootless Podman containers. Built with FastAPI + React/TypeScript.

MCP server that lets your ai agent press sound buttons. it's not that deep.

BMAd UI - Visual interface for agentic development workflows

An Obsidian plugin that synchronizes selected Zotero full-text items with your vault in realtime, vectorizes them and lets you chat with your pdf documents.

RAG parameter sweep and evaluation toolkit — a practical way to test how different vector databases, embedding models, chunking strategies, and retrieval methods perform across your own RAG setup. Built to help you move from guesswork to evidence, with support for any vector database.

Governed multi-agent SDLC pipeline for Claude Code and Qwen Code — plan → adversarial plan review → proven-red TDD → security scan → PR, with tamper-evident evidence at every step. Azure DevOps, Jira, GitHub, GitLab, Zoho, and local-markdown providers. Language-agnostic, discovery-driven.

KDE Plasma AI assistant with function calling, file operations, multi-provider TTS, session persistence, and full UI customization — powered by Google Gemini

FPGA hardware design guide based on real-world projects. Covers SystemVerilog, Vivado workflow, timing closure, CDC handling, and Xilinx 7 series device selection. Perfect for AI coding assistants and FPGA developers.

A production-ready full-stack system that combines semantic search with spatial proximity to retrieve and reason over geospatial documents.

Claude Code skills & agents to eliminate App Store rejections — 31 checks built from real-world rejection cases across all 5 App Store Review Guidelines sections.

Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.

CodeGraph MCP - Give persistent learning to your coding agent for a codebase across teams & token saving superpower to the coding agent

An agent-friendly general-purpose program orchestrator for busy people.

Frozen reference snapshot (Oct 2026) of a self-hosted AI operations stack — Discord bot + RAG + automation scripts on a Claude subscription. No longer developed; the author's setup moved to OpenClaw.

Starter kit for agentic WordPress development. CLAUDE.md/AGENTS.md templates, the wordpress-development skill, curated MCP servers, sub-agents, hooks. Companion to WordCamp Portugal 2026.

Automated OpenRouter API Key harvester: Outlook registration → OpenRouter signup → email verification → 2FA → API Key creation → notifications → Web dashboard. Playwright-based, supports AI Agent Skills.

AI-native methodology for Go backend microservices: rebuild the whole codebase from docs/ + .claude/skills, driven by a 12-lens high-performance architecture decision framework with mechanical doc↔code sync.

三千AI智能体 · 面向自媒体和内容团队的一站式 AI 工作台 · AI画布工作流 / 口播IP运营 / 多模型聚合 / 私有化部署

AI-powered travel guide generator skill for WorkBuddy/CodeBuddy. Xiaohongshu-first research + beautiful HTML output.

Curated reading list & living survey on long-term memory for LLM agents — 989 papers, 529 archived PDFs, deep notes mapped to memory-kernel modules. Feeds the Ymem Research Radar.

Atomic scripts for launching, collecting fees from, and trading pump.fun coins. Built around Jito bundles for atomicity across multiple txs, useful when: You need the create tx's fee payer to differ from the wallet supplying the SOL (separate funder vs creator), The creator wallet has a public/shared private key...

Security-first, self-hosted AI agents - isolation you can prove, not just promise.