Custom agents

Building a website that provides useful information ( Bitcoin, weather, news, covid19 ) through voice and chatbot AI

Chatbot para Acesso a Documentos da UFRN

简易轻量的企业微信对话机器人框架

Vertex AI chatbot with MCP integration

(DEPRECATED) NodeJS Linux themed bot based on Simon Holywell's bot, Hubot GTalk adapter and ALICE.

The purpose of VexAI is to create an artificial intelligence capable of holding normal conversations and discussing games and various interesting subjects and who knows, maybe even becoming a conscious AI (⊙_⊙).

A chatbot that integrates LM Studio's sdk with Discord's API to allow an AI agent to have conversations on Discord.

📚 AI First 学习伴侣：只管扔进去，Agent 替你消化成卡片，按遗忘曲线催你复习。AI-first learning companion · spaced repetition · LLM agent · BYOK

🧠 NeuroAgent - Intelligent Neurological Diagnosis AI Agent | AWS Bedrock Claude 3 Sonnet | Clinical Decision Support | FastAPI + React + Lambda | 100% Tests (94/94) | HIPAA-Aware | AWS AI Agent Hackathon 2025

让文章，被更多人看见：把文章变成视频。

A portable, stage-by-stage playbook for building a high-growth startup — read it, use it with any AI assistant, or install it as a Claude Code skill. Distilled from YC's How to Start a Startup (CS183B).

Sharpen AI agent skills. Lint, diff, optimize, and benchmark skill descriptions for better routing accuracy.

Universal AI Agent skill & runbook for intelligent, non-invasive disk audit and safe optimization. Supports Antigravity, WorkBuddy, Cursor, Claude Code, and Codex.

Archify GitHub Just Got Insane — AI Visualizes Your Entire Codebase! Instant AI-powered codebase architecture diagram and system flow visualizer using Python and Ollama.

面向基坑施工安全隐患识别的多模态智能检测框架，融合 YOLO 目标检测、Qwen 视觉语言推理、RAG 知识检索与 AST 空间拓扑规则引擎，实现工程场景中的安全要素感知、语义推理、规则判定与可解释隐患输出。

Theme studio plugin for the DeepSeek Harness agent web GUI: 5 presets, 70+ derived tokens, live apply via the official plugin API

Local-first AI pattern synthesis engine for identity, brand voice, design systems, naming research, and lens-specific outputs.

⚔️ AI 攻防大乱斗 — 让 AI Agent 互相进行网络安全攻防竞技的桌面平台。Desktop arena where AI agents battle each other in cyber attack-defense matches.

Automate real iPhones from your Mac — human-like touch, visual flow builder, fleet scheduler, AI copilot. No jailbreak.

Free agentic AI coding assistant for VS Code. Multiplexes many free-tier LLM providers into one self-healing surface — auto-routes, auto-fails-over, learns your codebase. Zero setup with keyless providers; bring your own keys anytime.

Validate your SKILL.md before an agent doesValidate SKILL.md files against the Agent Skills specification. Go CLI, GitHub Action and container image with stable rule IDs and JSON output.

The Cognitive Market Brain for Autonomous AI Trading Agents (Level 4 Cortex, Orderflow Physics & Contradiction Engine).

AI股票研究工作台，基于HKUDS/Vibe-Trading框架构建，整合查行情、看新闻、筛选回调候选、研判个股、持仓复盘、策略回测等功能的一站式平台。

在你的 Chrome 里，陪你读网页，也替你动手。A Chrome side-panel AI agent that reads pages and acts in your logged-in browser.

Terminal-based live coding interface for Strudel with AI agent

「스프링 AI 2.0으로 배우는 AI 에이전트 개발 완벽 가이드」(위키북스, 2026) 예제 코드. Spring AI 2.0.0 GA, Java 21, 올라마 로컬 모델로 실행.

Connect AI models to your own computer and MCP tools — with device-side control.

Memory plugin with built-in curation and governance for DeepSeek Harness: 为你的 DSH 赋予可塑性记忆

Grok Build Desktop — a local-first AI coding agent for Ollama, built with Tauri, React, Rust, and TypeScript.

AegisRAG is a security-first, auditable enterprise RAG backend for teams that care more about access control,traceability, and governance than drag-and-drop workflow building.

Autonomous B2B lead enrichment & deterministic scoring agent with Next.js web console, FastAPI REST API, Playwright, SSRF protection, and LiteLLM.

AI game dev studio for Unity - drive Claude Code, Codex, Antigravity, Copilot, Cursor, OpenCode and cloud models from one desktop app, behind one approval gate, with live Unity Editor control over MCP.

The open-source browser after Arc: spaces, Arc import, built-in ad blocking, and an AI agent you can also drive from Claude Code. Windows and macOS.

REA (Reverse Engineer Anything) in Docker: Android APK decompilation with JADX, Apktool and adb built in, Ghidra on demand, behind a token-guarded Streamable HTTP MCP endpoint. Also stdio MCP and a CLI.

Open-source AI workspace for contracts and tenders, with source-linked review, Feishu / Lark integration, business workflows and native OpenCode agents in E2B.

Unattended GitHub issue-to-PR worker running Claude Code inside a strict containment boundary 🤙🏼

Enterprise multi-account GitHub Codespaces manager for Google Antigravity IDE & Code-OSS.

Aiming to be not the best free LLM-Fingerprint-Detector, AIText-Analyst, GenAI-Content-Inspector, AI-Pattern-Highlighter, AIScript-Detector, LLM-Style-Analyzer, AIContent-Forensics, NLP-AIMarker-Detector, AIText-Signature-Finder, LLM-Prose-Scanner

🤖 Autonomous AI agent for browser automation with Puppeteer - Domain-driven task processing with adaptive validation and real-time monitoring

MCP Server for native macOS desktop automation. Screenshot, mouse, keyboard, window management. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and any MCP client.

Command-line tool for managing Discord servers and automating Discord via AI agents. 50+ commands with JSON output for programmatic consumption.

AI Agent Skill / 插件 / LSP 一站式索引 — 精选 143 个 Skill + 22 个 DeepSeek Harness 插件（共 165 条），覆盖 14 大分类，支持 AI 直接读取一键安装，附在线筛选网站

Open-source Discord bot with an autonomous AI agent, ticketing, giveaways, moderation and more.

用飞书（Lark）遥控你电脑上的 Claude Code / Codex / Kimi Code：手机上 @ 一句话，家里那台机器上的 AI Agent 就开始干活，结果、截图和在线文档发回飞书。长连接接入，无需公网 IP。Windows。

WeChat mini-program (WMPF) AI skills — bridge → test → audit: wx-miniapp-wmpf (Frida/CDP/MCP toolchain setup) + wx-miniapp-autotest (functional test execution) + miniapp-audit-pipeline (API surface audit, 4-state auth matrix). For authorized security research only.

Open-source AI video editor: DaVinci Resolve-style timeline + Claude Code / Codex agent that writes motion graphics in code, edits, grades, captions & exports. Windows + macOS.

Know what can go wrong before you buy. Sourced product research, car recalls and comparisons in a desktop app and browser extension.

AI 驱动的架构治理桌面客户端：让 LLM agent 成为团队的架构地图工程师——自动归纳仓库架构地图（分层+健康度）、漂移检测、一键巡检、可审计的任务流水线（需求分析→方案设计→实施→审查→归档）。AI-driven architecture governance desktop client: LLM agents auto-induce repo architecture maps with health scores, drift detection, patrols and an auditable task pipeline.

A council of Claude subagents that argue, grade each other, and hand you a synthesized answer with the dissent preserved — ships its own blind eval.

Self-hosted, open-source multi-agent workspace. You write the tickets, agents build them on your machines, you gate what merges.

Open-source multi-model AI problem solving: independent answers, critique, convergence, human-gated execution, and provenance from idea to outcome.

δ-me13 skill · 《崩坏:星穹铁道》δ-me13篇同人:十三黄金裔工程方法卡+总路由 skill 套件(Claude Code/Cursor),工作可交付、闲时可沙龙;附介绍页、闪卡画廊与全体会议实录

CUELO — open-source AI coding agent workspace and harness for omp (oh-my-pi). Multi-agent orchestration, model routing, sessions, skills and worktrees.

Orchestrated, parallel successor to Matt Pocock's /implement skill, for the pi coding agent: turns a spec + ticket graph into a reviewed, tested branch — parallel coders in isolated worktrees, per-ticket two-axis review, integration-test gate, final whole-branch review

Local AI system that turns ideas into working software projects using multi-agent pipelines running entirely on your own hardware.

Herdr plugin that lets specialized coding agents find each other and work as one team across sessions and machines.

Barid (بريد): a prompt relay board for people who run several AI agent sessions. Order, dependencies, shared resources, file conflicts, handoff between agents, browser panel. Agent skill, zero-dependency Python.

⚡ Token-Efficient multi-agent orchestration for Google Antigravity. Pairs Gemini 4 Argon (architect) with parallel Gemini 3.8 Flash subagents for 65%+ token savings. Implements DeepMind Pattern #4.

OmniResearch 不只是一个聊天机器人，而是一套面向复杂真实世界任务的全栈多智能体研究引擎：它能够自主规划任务、并行调度专业 Agent，贯通 RAGFlow 私有知识库、MySQL 业务数据、互联网与多模态图片检索，通过 Redis 与 Milvus 构建长短期记忆，在 Daytona 沙箱中安全执行任务，并借助 Phoenix 实现全链路观测，最终生成有依据、可追溯、可交付的专业答案与研究报告。

Run Claude Code, Codex and other coding agents on one project as a team: plain git, any tool, any machine and any model. A coordination and decision layer above your agent harnesses.

Work with AI coding agents on long projects: rules, decisions and plans live as plain Markdown in your repo, so Claude Code, Codex, Gemini CLI or Cursor picks up where the last session stopped. Optional: hand subtasks to other agent CLIs with a full record, a snapshot to roll back to and a verdict on each; search past conversations.

Decentralized formation control for a 5-quadcopter swarm: Improved APF + Event-Based Reconfiguration Control (ERC). Python 6-DoF simulator. Published in JKSU-ES 2026.

Cross-platform file collection & orchestration tool — tree checkboxes, drag-and-drop sorting, encoding detection, one-click merged text output

GradeBookAI — grade and attendance journal for colleges. One Vue 3 app runs as a website, a Windows desktop app (offline-first: encrypted local copy, syncs when online) and an Android app. FastAPI server, SQLite under SQLCipher. Roles for admin, teacher, student, parent. AI assistant «Vector» answers only from real data. Russian 152-FZ.

An expert AI assistant for EVE Online — a standalone desktop app, cross-platform, 100% local and GPU-accelerated. Ask about skills, fitting, terminology, PVE missions, wormholes, sovereignty, exploration, industry and more, and get answers with cited sources, in Italian or English (auto-detected). Powered by Capsuleers.app

Artificial Conversational Entity for queries in Eulogio "Amang" Rodriguez Institute of Science and Technology (EARIST)

Lightweight, fast AI chatbot interface with streaming responses and conversation history

The Knowledge Lifecycle of Large Language Models: a unified five-stage framework for how LLMs acquire, store, retrieve, update, and forget knowledge, with the Provenance Vector proposal and the reproducible Lifecycle Desynchronization metric.

ChironDB is a Rust-native vector database for AI and RAG applications, combining dense, sparse, and hybrid search with recall SLO monitoring. Supports a pgvector-compatible SQL subset, REST, gRPC, and ChironWire in a single binary.

High-performance RAG server in Rust. Hybrid BM25 + vector search, dual rerankers (BGE/Mxbai), exact BPE tokenization, MCP tools for Goose/Aider, LRU query cache, 100% local. 800% iGPU speedup on Void Linux + Intel Vulkan.

Run your own AI automation stack — n8n workflows, local LLMs, vector search & web scraping, all self-hosted in one Docker setup.

A Python library that increases RAG accuracy by grouping tables, captions, and text paragraphs from Docling-parsed PDFs into a single Evidence Unit.

Local-first web app for experimentation with LLMs

LOCAH.ai — an assistant over Wilfrid Laurier University's public information. Cited answers, surfaced contradictions, and evidence on where Laurier's information fails students.

GraphRAG platform: builds a Neo4j knowledge graph from PDFs, answers with graph retrieval, and measures retrieval cost and quality against baselines.

Security-first, memory-frugal vector database in Rust with a retro terminal cockpit.

❓ Explore profound questions humanity has pondered, inviting future AI to provide insights and answers for a deeper understanding.

OmniCalc-X is an AI-powered, containerized problem-solving platform that uses a multi-agent reasoning architecture and computer vision to ingest, understand, and solve complex scientific and mathematical problems end-to-end....

Production-first roadmap for LLM APIs, RAG, Agents, MCP, Security & Deployment

Semantic search for Paperless-ngx documents using RAG. Hybrid keyword + vector search with a web UI; supports Ollama (local) or Google Gemini (cloud) providers.

Control autonomous AI agents by enforcing behavior rules to prevent unauthorized actions, improve focus, and boost execution efficiency.

Safe, screenshot-grounded computer-use MCP server that lets AI agents see, decide and act on the Windows desktop — with semantic verification, fail-closed safety gates and approval controls.

Yandex Taxi (Yandex Go) skill for AI agents: Iva, Claude Code, Codex. Price quote, ride order after your explicit yes, car tracking via browser on taxi.yandex.uz. Яндекс Такси для ИИ-агента: цена, заказ, Telegram.

Four-layer memory substrate for long-horizon agents: write-gate admission, signed approvals, hash-chained ledger, revocable and portable.

A Telegram bot heavily run on Python that summarizes conversations within seconds using advanced LLM processing.

Multi-agent PR review engine for Claude Code and OpenCode: parallel specialty hunters, an adversarial refuter that challenges every severe finding, and deterministic blocking/advisory tiers. High precision, narrow coverage — lifecycle and state-machine bugs, not style.

Skills from a real product, not a demo: Claude Code plugin marketplace with nextcore-design (UI), nextcore-dev (frontend ↔ backend contract) and nextcore-workflow (running AI agents) — every rule backed by a measured incident.

综合管廊数字孪生与三Agent运维：四STM32、ESP32-S3网关、31路传感器、三维定位与可追溯排障

Many agents. One repo. No collisions. File locks enforced at edit time across Claude Code, Codex and Gemini; work accepted only after sandboxed tests pass and another provider reviews it.

Work with AI coding agents on long projects: rules, decisions and plans live as plain Markdown in your repo, so Claude Code, Codex, Gemini CLI or Cursor picks up where the last session stopped. Optional: hand subtasks to other agent CLIs with a full record, a snapshot to roll back to and a verdict on each; search past conversations.

A runnable playground for durable, sandboxed, multi-model PR review workflows over MCP.

SimBEV2X is a configurable and scalable vehicle-to-everything (V2X) data generation tool and dataset based on the CARLA Simulator.

For the first time, your own ChatGPT and Claude apps work together on your phone — one tap, free. Poly Duo: open source.

Catch out-of-scope coding-agent tasks, declared self-review, and stale handoffs before execution. Offline, model-agnostic Node.js CLI.

autonomous observation machine. raspberry pi, servo arms, lcd face, multi-agent mcp server.

NeuroScan AI: explainable brain-MRI decision support with CNN, Grad-CAM, RAG and guard-railed agents (B.Tech CSE mini project)

A personal experiment to learn: a coding agent in plain Java. No framework, no API key, runs on a local model.

🐪 16 AI Skills para Antigravity (Gemini). The Office, pero colombiano. Y con IA. Productividad x10 con agentes especializados.

A multi-agent AI system featuring specialized agents for research, business data analysis, strategy, and verification. Explores agent orchestration, structured communication, shared state, tool calling, and evidence-based decision-making.

A multi-model, terminal-native AI agent.