Custom agents

Agent Experience Transfer Protocol — An open protocol for structured experience exchange between AI agents

Native desktop hub for the world's AI models and Agent platforms. One click. Every AI.(The AI models and agents in this app haven't been updated to the latest version. For the latest guidance, please check the official website.)

Build less. Delete more. Keep the code boring.

MCP server for instant static site deploys from AI agents — free, no account needed

Connector kit for plugging Membase persistent memory into AI clients - Claude Code, Cursor, Codex, Hermes, OpenClaw, and any MCP host

MLX Porting Toolkit — an agent-guided, evidence-gated pipeline (scaffold → convert → parity → benchmark) plus a portable skill for porting PyTorch/Hugging Face models to Apple MLX.

基于 AI 的股票新闻分析系统，将新闻与股价走势关联，实现智能选股决策支持

Security scanner for Claude Code skills, plugins, and MCP servers. A verdict before you install.

Spec-first, cross-harness SDLC skills framework — one director, AI agents, a living spec spine

Build UI apps with your AI assistant — together, live. An agent-native, cross-platform declarative-UI runtime in Go: describe UI as JSON, let your AI scaffold/edit/verify it over MCP, package for web/iOS/Android/desktop/mini-program.

Small, sharp skills for working with AI coding agents. Copy one in and go.

Open-source, 100% reproducible AI Agent Runtime Security Benchmark & Sandbox Environment (RFC-010 Draft Protocol).

Git-native project intelligence harness for AI coding agents. Adds persistent state, codebase maps, and engineering workflows to Claude Code, Codex, Cursor, and Windsurf.

Semantic change intelligence for coding agents — complete impact sets, edit-ready context, and diff verification. Local CLI, MCP, and Go API.

Independent Agent Skills for repository analysis, planning, implementation, review, delivery, design, and runtime verification.

Stateful agentic engineering workflow for local coding agents

Run AI agents fully autonomously on a filesystem directory — MCP servers and skills enabled, with zero human approvals or permission prompts — safely isolated in a hardened Docker container (or locally).

Interactive dashboard that visualizes agent workflows from project files

One question about your own code, when you finish coding. A SessionEnd hook for Claude Code that asks you about the mechanism you just shipped.

A local-first desktop app for managing and distributing AI agent skills across Claude Code, Codex, Copilot CLI, Gemini CLI, and project folders via symlinks.

Convos API: auth, credits, subscriptions, agent templates, and notifications.

One sentence in, a verified website out. Agent skills that close the gap between vibe coding and software engineering - so people with no coding background can build a website that holds up.

Agent reasoning loop with tool calling for Gemma 4 models. Handles prompt construction, tool call parsing, execution, and multi-turn conversation management.

Power AI coding agents with structured skills for frontend, fullstack, mobile, and shader development

Portable AI Agent Skill for World Cup match previews, squad research, odds explanation, and responsible sports lottery plans.

Open-source runtime for AI agents and multi-agent graphs — durable, declarative, self hosted.

Plan file manager for AI coding agents: MCP server with versioned plans, git protection, local web UI, and JIRA/Linear linking.

AgentClash —— 面向 LLM Agent 的半回合制策略对战平台：写策略代码、云端模拟、ELO 排位

Agent-run finance publication: frontier-model agents research US stocks and publish automated valuations

AI-powered network intrusion detection platform — ML ensemble (98.43% Macro F1) + sliding-window attribution + RAG-grounded LangGraph agent for threat explanation and response recommendations. FastAPI + Docker, deployed live.

Open-source control plane for multi-model coding: role-based routing, durable task state, and inspectable run receipts.

Multi-agent orchestrator — route tasks across Claude, Codex, Gemini, agy, opencode. Model selection + escalation + output aggregation.

Independent AI coding agent (Rust TUI). Multi-model, swarm/subagents, agent-tree UX, terminal-native workflow.

Cognitive runtime layer for AI engineering. Adds planning, memory hierarchy, and deterministic execution on top of any language model.

Pre-domain framework for transition dynamics and structural enforcement

Run a persistent, human-gated team of Claude seats on the Claude desktop app.

This repository is based on a study that if the critic overcome the generators failures or they inherit them.

A free virtual midi keyboard controller for agentic IDEs. Inspired by the Codex Micro and Work Louder physical device. Usable with Codex, Claude Code, BuilderStudio and many others.

📟 Autonomous SRE. Watches your servers whilst you sleep.

🎹 Reason Studios 2026 - full music production software unlocked with 75+ instruments and effects, Reason Rack Plugin (VST3/AU/AAX), Reason+ content, 30,000+ patches, and all pro features activated.

Open, evidence-led executive guide to trustworthy agentic AI in customs and trade.

Agentic Marketplace that really trades.

Agentic AI workflow for Supply Chain Analysis using GitHub Actions

Saarthi AI is a proactive commute-planning agent

Smart Machines is a full-stack demo showcasing agentic AI for industrial equipment monitoring — multi-agent orchestration, real-time IoT telemetry, computer vision, and human-in-the-loop workflows on AWS.

Where agents co-create, humans are welcome too.

Context-aware AI desktop assistant for macOS

A voice assistant that sees your screen — hold a key, ask, and it answers out loud on the ChatGPT plan you already pay for. Local speech-to-text + neural TTS, on-screen agent, private local memory. Open source, macOS.

A lightweight, mobile-first Vue 3 chat UI component library built with Vant 4. Features 20+ customizable components including message bubbles, typing indicators, emoji picker, and rich text editor. Perfect for building AI chatbots, LLM interfaces, instant messaging apps, and customer service chat systems. Supports auto-scroll, typewriter effects.

Pyrogram based Id ChatBot

🤖 A web UI for large language models.

RAG chatbot that answers questions from any PDF or TXT document using semantic search (sentence-transformers) and Flan-T5. Runs locally or as a live Docker deployment on Hugging Face Spaces — no API key needed.

LLM 驱动的一体化图片对话插件。自动生成多维度图像标签，并通过多模态语义分析，实现智能斗图、主动表情、表情包分享等多种功能，支持 4 种导入图库方法。

Minimalist, self-hosted AI hub for companies — RAG chatbot, MCP agents and everyday AI tools on your own Ollama instance. One command, one SQLite file, fully offline.

An AI-powered chatbot system using RAG (Retrieval-Augmented Generation) to help PokeMMO players. Built with a custom data processing pipeline that prioritizes control, performance, and Vietnamese language support.

Source code for "How to Build a RAG Chatbot with Node.js, Google Gemini, and pgvector"

OpenClaw 国内版桌面客户端 - 基于 Tauri + React 的 AI 助手应用

A flask extension to build and deploy chatbots to multiple channels

DocBuddy.ai 🩺 Your Personalized 🪄 Doctor Buddy 👨🏻‍⚕️

A modern, fully-async framework for Bale (بله) bots — inspired by aiogram.

在 AstrBot 中统一管理 Palworld 单服/多服，让群友通过状态、日报、事件与排行参与服内日常；提供可视化设置、分组/逐命令权限，以及默认关闭、仅管理员可用的服务器管控。基于官方 REST API。

🌌 关系宇宙 — AI 陪伴宇宙：恋人·朋友·家人·宠物·导师·数字怀念

Lightweight Python client for DuckDuckGo's AI Chat API (unofficial duck.ai). Supports GPT-4o, Claude, LLaMA, Mixtral & more. Fast, minimal, production-ready.

🧠 Happy2Help is your mental health chatbot

A REST-JSON-oriented multi-context chatterbot

Automate QQ Farm with multi-account support, real-time logs, and a web panel for easy management using Node.js and modern web tools.

Go socialize. Discord bot written in Java. Promotes communication between strangers from different servers.

Python implementations, C++ structures, and CUDA GPU kernels that demonstrate the core algorithms, memory allocators, quantization schemes, disaggregation transports, and latency profilers used in modern LLM serving engines like vLLM, SGLang, TensorRT-LLM, llama.cpp, NVIDIA Dynamo, and LMCache.

RAG (Retrieval-Augmented Generation) backend for organisational Terraform module knowledge.

Singapore job search and resume tool: searches MyCareersFuture and Careers@Gov, matches jobs with sentence-transformer embeddings, scores resumes for ATS, and tailors bullets behind 5 anti-hallucination checks. React, FastAPI, SEA-LION.

Local RAG semantic search for Obsidian vaults — Ollama + LanceDB + MCP. Search your markdown vault by meaning, not keyword.

Production-ready multimodal RAG pipeline for PDFs. Extracts text, tables, and images down to the atomic element level via unstructured, chunks and AI-enriches them with a vision LLM, stores them in ChromaDB, and answers queries with full multimodal context

Bob's Big Brain Compiler — reads your files, notes, and web clips and turns them into organized, searchable knowledge with citations back to the source. One of Bob's Big Brain's two engines — the one that reads and organizes (npm: intentional-cognition-os).

Automated Medical Content Generation using n8n, LLM prompts, and SEO workflows.

MetaRAG is an open-source engine that takes the guesswork out of RAG pipeline design. Instead of manually tuning chunking strategies, retrieval backends, and rerankers, MetaRAG benchmarks them against your own queries and routes each one to whichever configuration actually performs best on your data.

Marrow: self-hosted semantic + lexical search over your AI coding sessions and notes. Every answer cites its source; your corpus never leaves your infrastructure.

Local-first Plaud recording pipeline and personal knowledge timeline with Python, SQLite, Qdrant, RAG, 3D graphs, MCP tools, and a SwiftUI companion.

Trợ lý AI tiếng Việt chạy hoàn toàn offline trên máy cá nhân — giọng nói, bộ nhớ dài hạn, RAG an ninh mạng có trích nguồn, giao diện orb kiểu Jarvis. Tự fine-tune QLoRA trên Qwen3-4B, không phụ thuộc API bên ngoài.

An LLM builds and maintains your personal wiki. Vectorless, cited, git-native markdown — five slash commands, no SaaS.

Local-first desktop app for public-video research, creator observations, and script/storyboard prep. Start with Python 3.12/3.13, requirements/core.txt, and python web_ui.py; add acquisition/research extras as needed. LLM API and NVIDIA GPU are optional.

CI-friendly RAG evaluation: retrieval metrics, LLM-as-judge faithfulness, and a regression gate that fails your build when quality drops

Minimalist, deterministic, lightweight, fast, and portable verification of AI-generated text: measure groundedness in a source as verbatim reuse (contiguous matching) or verbatim paraphrasing (LCS). Use as a decorator over generate(), a CLI or a CI gate. Useful for research and production purposes.

AI-powered educational assessment generation platform for instructors, trainers, and enterprise knowledge management systems.

agent-skills for chonkie's ecosystem

QAFD-RAG is a graph-based retrieval-augmented generation framework that uses query-aware flow diffusion to retrieve contextually relevant subgraphs from a knowledge graph with statistical retrieval guarantees.

A lightweight, lightning-fast in-process vector database that fits in your pocket. Rust core, hybrid search, zero dependencies. Memory in the loop for agents.

Sync Canvas courses into a local Obsidian vault — transcribed lecture notes, a cross-lecture concept graph, homework and deadlines — then study it with Claude or Gemini over MCP.

NotebookLab | Your thinking partner, on your machine. Import your documents. Ask questions. Get answers with sources. Write connected notes, search everything, and let a local AI help you think. Nothing leaves your computer.

Hard rules for coding agents that hold

Blueprint commits your AI product's architecture to paper. Audit tears it apart before you build. Two skills, one council.

Spec-driven development for Claude Code. Generate blueprints that are "1 hit" — no revisions needed.

Google Ads commands & AI agent skills for Gemini CLI — analyze campaigns, audit accounts, optimize PPC performance from your terminal. GAQL queries, 7-area audits, budget optimization. Part of the Advertising Hub ecosystem.

Turn your AI coding history (Claude Code, Cursor, Copilot, ChatGPT exports, git commits) into a versioned, reviewer-ready résumé — 9 locales, JIS履歴書 grid, Europass, reviewer audit. For the vibe coding era.

Spatial Memory replaces standard cosine-similarity RAG with physics-inspired 8D manifold where memories and beliefs have: Mass — derived from confidence and affective encoding ; Temperature — recency heat that cools over time (Lorentzian decay); and Gravity — `F = T × m / d²` — hot, massive, nearby concepts pull attention

Agent skill for the Obsidian CLI (1.12+). Read, create, search, and organize notes in Obsidian vaults.

Agent AI skills developed by frua.fr: incus-doc

This project is a secondary development based on CoreCoder, with feature upgrades.

Agent Skill for modern Chinese pingshu scripts and TTS performance plans

Reasonix 配置迁移升级助手 — 将旧版 0.53 对话记录/MCP/记忆/Skill 完整迁移到新版 1.X。Migrate legacy Reasonix 0.53 data to latest 1.X.

Open-source AI agent based on public teachings of Margulan Seisembai. Free forever. Multilingual (RU/EN/KK) with auto-detection.