Custom agents

Dark UI ChatGPT 🌹

Within the scope of psychology, it is an LLM AI-Bot research aimed at increasing human interaction with AI.

GitHub app/bot for responding to actions and events in your repository using contextual quotes from Darkest Dungeon.

Personalised Travel Itinerary Generator using RAG + LLMs

Your agent's claw on every machine 🦞

Superseded by howells/skills

The human-attention system for agent work.

Self-hostable NGINX module that serves Markdown to AI agents via HTTP content negotiation (Accept: text/markdown), powered by a Rust converter.

AICW AI Mentions (formerly AICW Rankings) is an open-source tool that helps online marketers track how often their products are mentioned in responses from popular AI chatbots.

Real-time monitoring dashboard for AI coding agent fleets: session health, output streaming, and observability across Claude, Codex, and Gemini

HIPAA-eligible DIY Twilio alternative for voice AI telephone applications. Uses Asterisk PBX and AWS Chime SIP trunking.

Secure and lightweight Python code execution environment for LLMs

emotional AI Companions for personal relationships

Asynchronous LLM Agent playing games of Mafia against human players

Code for the paper "Searching Privacy Risks in Multi-Agent Systems via Simulation"

AI-Generated AI Roleplay Simulator — 互动叙事与多智能体模拟引擎

Rust MCP framework for building AI agents

OpenClaw skill build of Web Search Plus — source-only v4.0.0. Ranked links and extracted text, no Perplexity/Kilo answers. Native plugin: web-search-plus-plugin-v2. Engine: hermes-web-search-plus + web-search-plus-mcp.

Utilities for managing agent memory, context windows, and task-focused state

Visor — AI workflow engine for code review, assistants, and automation. Orchestrates checks, MCP tools, and AI providers with YAML-driven pipelines. Runs as GitHub Action, CLI, Slack bot, or HTTP API.

Vorn - The agent command center

Agent skills distilled from the hard-won lessons of world-renowned programmers, in the spirit of "97 Things Every Programmer Should Know"

Human-vetted, community-curated skills for AI coding & agent tools.

Requirements traceability matrix package for closed-loop product development with agentic AI tools.

Skill for AI agents to be a Valyu Search Expert

Official code for the paper: "Multi-User Large Language Model Agents"

Flutter framework for multi-agent AI orchestration. Build agents that use tools, chain tasks, and talk to each other. Works with any LLM provider & no backend is needed.

The AI-native portfolio — this one talks back.

Vettore is a small vector toolkit for Elixir that keeps your data in ETS and uses Rust only where it helps. It's small, fast, efficient, simple!

Subgrapher is a local-first semantic browser workspace where references become runnable memory apps with graph context, agent execution, and hybrid RAG + Telegram Remote.

This is a fully autonomous, self-operating computer automation system designed to automate tasks on Windows without any user interaction. It runs scheduled or trigger-based workflows using Python, system tools, and smart agents — ideal for repetitive tasks, bots, or self-executing pipelines.

AI Video Engine — Turn structured data into videos. JSON timeline → Scene components → HTML/MP4.

Lightweight AI agent runtime for Go. Define multi-agent crews in YAML, run them with goroutines and channels, and let the runtime handle scheduling, parallelism, retries, and observability — without leaving the Go ecosystem.

Instant hosting for AI agents — turn output into pages worth sharing

The Vibe Coding Workstation — A desktop workspace where terminal, AI agents, and git live together for uninterrupted flow state

Multi-Agent Reasoning Systems

ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

Text2Sim MCP Server is a conversational simulation engine that transforms natural language into working simulation models. Supporting Discrete-Event Simulation (DES) and System Dynamics (SD), it integrates with LLMs via the Model Context Protocol (MCP) to transform plain English descriptions into simulation models within environments like Claude.

Adaptive Hypernetworks for Multi-Agent RL. NeurIPS 2025.

A curated list of Agent-to-Agent (A2A) libraries and SDKs, organized by programming language.

The open-source security layer for AI agents. Deterministic guardrails, PII redaction, and EU AI Act compliance in one line of code.

Demonstration of AI review of existing functional annotations

A collection of AI solutions for oracle.ai

AI Coding Agent Orchestrator with continuous learning. Orchestration layer on top of Claude Code and OpenCode

A comprehensive suite of protocols, meta-prompts, and orchestration tools designed to streamline software development workflows, project management, and team collaboration. Includes the VibeCode Protocol Suite with web interface, user manuals, and reusable templates for efficient development processes.

ESP32-S3 virtual pet with built-in WiFi security auditing, BLE peer interaction, Telegram control, and a full browser simulator.

⚡️ Real-time Knowledge Graph for AI Agents. Connect LLMs to verified weather, stock, and currency data via instant tool-calling. No API keys, no scrapers, just grounded facts in <100ms.

🐙 AI-powered presentation builder with a conversational agent, live Marp preview, and lightweight presentation on your browser.

Agent Engineering experiment, practices, codes, specs...

Блог про AI-агентов, вайбкодинг и паттерны Claude Code

End-to-end behavioral testing skills, bare system prompts, and any agent runtime — run real scenarios in an isolated git sandbox, capture the full tool-call trace, and assert it against declarative YAML.

Cephalopod Coordination Protocol (CCP) is a Rust-based client-server protocol for fast, reliable coordination between agentic systems.

AI-Powered Crypto Analysis Dashboard!

Yutori MCP

Open-source local AI platform for building, running, and extending AI systems with one unified runtime.

A better grep for AI agents. Structural search, call graphs, impact analysis, semantic compression. 87% fewer tokens. 16 languages. Built in Rust.

Rust browser automation over the WebDriver BiDi Protocol and CDP

AI Powered SaaS Website Builder

Governed local runtime for AI coding agents: task lifecycle, mandatory gates, reviews, doc-impact checks, and auditable completion.

Automatic task memory and keep-alive loop for Hermes agents. Every task gets durable notes in Obsidian. Arm the loop for long tasks, disarm when done.

Complete Enterprise Agentic AI Architectures with .NET, Build Production-Grade AI Systems for Senior .NET Architects & Tech Leads

Agentic AI For Good

dog-raf es un chat y un sistema de consulta por generación aumentada para explorar las ediciones del Diario Oficial de la Federación de México.

RAG Multi Agents

MCP server for Olostep — the web scraping, crawling, and search infrastructure used by top AI companies. Gives any MCP-compatible AI agent the ability to scrape, crawl, batch-extract, and search the web in real time.

Zero-LLM agent memory for Claude Code and AI agents: local-first BM25, dense-vector, and reciprocal-rank-fusion retrieval. Returns original passages verbatim by default. Available on PyPI as fidelis-memory. Apache-2.0.

🌐 Automate Browser using AI with ease.

Persistent memory for AI agents. Extract once, recall forever.

Real virtual desktops for AI agents. MCP-native, self-hosted, fully isolated.

Professional AI skills for knowledge workers who make decks at 2am. PPT design, structured communication, and more.

A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.

OpenDsStar is an open-source implementation of the DS-Star agent that replaces file-based workflows with a flexible, tool-centric architecture. It supports incremental execution, reuses intermediate results, and makes complex multi-step agents more modular, efficient, and extensible.

AWS payment demo of x402 using Bedrock AgentCore, Strands SDK, and CloudFront.

A curated list of tools, frameworks, and resources for running AI locally — inference, RAG, orchestration, monitoring, and more.

Send, manage, and replay ntfy push notifications via MCP. STDIO or Streamable HTTP.

太医院 — Agentic Longevity OS with 10 AI physicians. N-of-1 trials, cross-module pattern detection, PubMed-grounded insights, Bayesian causal inference. Works with Claude Code & OpenClaw.

A collection of reusable AI agent prompts for development workflows.

Bitrix24 AI Agent skill: webhook/OAuth, events, retries, safety guardrails, and ops patterns

The enforcement tool for Canonical-Driven Development (CDD). Audit, generate, and guard your project documentation. Zero dependencies.

🔐 The password manager for terminal users and AI agents. Age-encrypted, keyring-cached, MCP-ready. Zero telemetry.

🌊 The simple wrapper of leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration

Deterministic wavelet-scattering features for physics. Open control plane (AGPL); GPU engine distributed as binaries. Nothing learned, nothing leaked.

An imperative command-line-interface for AI workload orchestration — v6.2.16

Free & Open Source AI Agent — Self-Hosted, Self-Learning, No Vendor API. Qwen2.5-7B + LoRA. 35 tools. Built on Islamic Epistemology (IHOS).

End to end AI agent that generates cinematic ASMR style short videos using GPT-4, Seedance, Fal AI, and Blotato and uploads them automatically to TikTok, YouTube, Instagram, and more.

A Pexels MCP Server for Images and Videos searching

Antigravity Supercharged Project Engine. A complete AI Agent architecture featuring jCodeMunch for 99% token savings, NotebookLM for deep research, and OpenSpec workflows for precise spec-driven development.

这是一个面向家庭场景的离线监控视频分析系统。项目以 NAS/目录中的摄像头录像为输入，自动完成视频扫描、会话合并、AI 事件识别、家庭日报生成，并提供 Web 管理后台、自然语言问答、Webhook 与 MCP 对外能力。

Agent-driven molecular optimization over chemical space, using Rowan for property scoring and RDKit for constraint-aware candidate design.

Open-source, self-hosted multi-agent AI orchestration platform. Run agents in isolated Docker containers with swarm coordination, RBAC, token governance, and multi-channel support.

A high-performance, open-source Multi-Agent Collaboration Platform built with Tauri, Rust, and SolidJS

Rust-based rewrite of Optopsy: An options backtesting engine exposed via Model Context Protocol (MCP)

Agentic Android Open Source Project (AAOSP) — Android fork with native LLM system service, MCP-aware apps, and an agent-driven launcher. On-device Qwen 2.5 via llama.cpp. Apps declare tools in their manifest. The OS runs the model.

OpenAaaS: science agent network — bring AI to your data, not your data to AI. AaaS, Agent as a Service, MCP protocol, local execution, Docker sandbox, zero-config Rust nodes.

Latent Embedding Operating System

Turn your existing webpages into an MCP server for agent control

Production-quality Retrieval-Augmented Generation with multi-strategy retrieval and comprehensive evaluation framework.

Self-learning context infrastructure for AI engineering agents. Connect repos, docs, and tools into one org-scoped knowledge graph and expose it through a single MCP.

Flutter clean architecture skill for AI agents. Riverpod 3.x codegen, Freezed 3.x sealed classes, and GoRouter patterns.