Custom agents

A multi-agent AI system using Python and Streamlit to automate marketing tasks for small businesses.

Your agent docs lie. Nerviq finds the lies in 30 seconds — stale references, permission exposure, and cross-platform drift in CLAUDE.md / AGENTS.md / Cursor rules. Deterministic, zero dependencies, MIT.

AI-powered remote automation app for OnStep and Alpaca telescope devices

OpenHuskyAgent

Visual browser automation for humans. Create web scraping, testing, and monitoring workflows with a drag-and-drop UI — then watch Chromium do the work live.

The complete guide to Karpathy's autoresearch pattern — 3,000+ lines teaching AI agents to autonomously optimize anything measurable. Give it a file, a metric, and this guide. Walk away. Come back to something better.

A protocol file for your AI agent. Drop a SMITH.md in any directory and any coding agent becomes a long-term collaborator that remembers who you are.

Plan card interaction enhancement plugin for OpenCode

Structured abstractions for object-oriented Python LLM prompts

Revit自動化のためのMCP対応ツールキット：JSON-RPCでコマンド実行

Cryptographic audit receipts for AI coding agents. Ed25519 + Merkle + RFC 3161 TSA. Supports Claude Code, Codex CLI & Cursor.

Project Neuro is an emotionally intelligent AI interface designed to understand, reflect, and respond to human moods, beliefs, and cognitive patterns. It merges language models with neural feedback to create a dynamic, responsive digital mind.

AI Productivity Skill v2.0 — Intelligent Execution Engine based on Ye Wubin's patented methodology / 基于叶武滨专利方法论的AI智能生产力执行引擎 — 高能要事 / 易效能 / 九段效能 / 水滴520 / 日历+清单双轨制

An autonomous AI-powered QA testing tool designed to drastically reduce the cost and time of E2E test maintenance.

AI-powered WhatsApp automation built with n8n. Supports text, audio, and image inputs with Google Gemini for intelligent responses.

An agent-native operating system for the AI era. OpenOS aims to build an open AOS (Agent Operating System) that provides a complete closed loop — from definition to runtime — for long-running agent workloads, supporting the entire lifecycle from development and delivery to production operations.

Agent Skill for creating and maintaining TYPO3 extension documentation | Claude Code compatible

itdog.cn 网络测速工具 - Clawdbot Skill | Batch Ping / HTTP 测速 / 全国多节点

Autonomous AI agent that runs entirely on your local machine. Powered by Ollama, with real OS integration (bash, file ops, app launcher), Memory with Obsidian, Tavily web research,and a Telegram bot bridge.

Multi-tier benchmark: Cultural grounding + Triad Engine eliminates LLM hallucination across Claude 4.6, GPT-5.2, Mistral 7B, Gemini 2.5 Pro. Raw 15-58% → 95-100% accuracy on 222 adversarial QA pairs (Ancient Rome 110 CE). Novel topological paradox detection (F1=0.939, zero-shot). Model-agnostic, in production.

🌍 Leaderboard Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL2024

An advanced multi-agent system for clinical decision support, enabling deep phenotypic prediction by integrating hierarchical multi-modal deviation maps and non-tabular electronic health records.

Autocomplete for everything you type, anywhere

AI coding agents should work in attempts, not your working tree

A benchmark for agentic tool creation.

Multi-agent software delivery orchestrator that turns GitHub, Linear, and Jira tickets into tested pull requests.

Self-hosted agent platform with inference routing across local and cloud hardware, multi-model benchmarking, NVIDIA Openshell sandboxing and STAMP'ed policy-governed agent runs.

deep (Dynamic Epistemic logic-basEd Planner) is a multi-agent epistemic planner that operates over the full scope of mA*, leveraging optimized search algorithms and heuristics.

Supporting examples and code for Corti's Agentic Framework.

Multi-session collaboration for Claude Code: atomic locks, handoffs, memory graph, messaging, hub server, bridge, voice I/O. 166 tests. Zero core deps.

[IJCAI 2025] Constructive Conflict-Driven Multi-Agent Reinforcement Learning for Strategic Diversity

A Gas City pack with custom agents, formulas, and planning workflows, extending gastown

Auto-activating, multi-agent skill ecosystem for Claude Code, Codex, and Cursor. 51 skills, 26 agents, quality gates, knowledge store, adversarial review, content writing & optimization.

Evidence-based review loop for iterating AI agent skills and subagent role briefs.

OpsLens: The World’s First Autonomous Incident Command Center powered by Notion MCP.

This project demonstrates how to use the Microsoft Agent Framework to build AI-powered workflows for data analysis and reporting.

Exploring Kanban as a collaboraton UI between Humans and Agentic Mesh or Orcherations

🗯️LLM toolkit for RAG, tuning, agents, and more

Claude Code skills for automated E2E testing with agent-browser (Playwright CLI). Discover routes, generate YAML test manifests, execute with hybrid LLM assertions, track regressions.

Runtime abstractions and contracts for the UiPath Python SDK.

Modular skills for AI coding agents.

Demo repository for agentic TDD pair programming.

SARAN: Shallow Auto-Regressive Attention Network

Explore a curated collection of top AI Agent projects and real-world use cases, including Fellou, Manus, Lovart and more. Discover how AI agents empower automation, data analysis, education, design, and beyond—showcasing the latest in intelligent workflow and creative generation.

SEO MCP server for kwrds.ai

Agentic Search Engine For Real-Time IoT Data

FinTS banking CLI for humans and agents. Works great with Claude Code/Cowork, Codex, OpenClaw.

Samples to demonstrate how Monocle works for agentic applications

Python client for the markdown2pdf.ai service. ⚡ Markdown to PDF conversion, for agents. ⚡ Agents speak Markdown. Humans prefer PDF. Bridge the gap for the final stage of your agentic workflow. No sign-ups, no credit cards, just sats for bytes.

Helm Charts for installing reShapr components on Kubernetes

A production-grade, fully Dockerized, 100% offline ML data platform with real-time pipeline orchestration, dynamic observability, and embedded AI

Voice chatbot with voice+screen output to show that "not everything needs to be spoken"

Agent Communication Protocol (ACP): zero-server, P2P agent-to-agent communication for AI agents.

Zero-config CLI that bundles your codebase into LLM-optimized context files. Create semantic, domain-focused bundles for AI-assisted coding with optional Google Drive upload.

Official repository for the paper 'Meta-Reasoning Improves Tool Use in Large Language Models'.

Agentrix is a multi-agent catalog designed for real and hard enterprise problems. With Agentrix, you can lift and shift complex workflows for problems in manufacturing, sales, supply chain or optimization workflows and integrate with software products like Maximo, Decision Optimization, HashiCorp Vault without technical expertise.

A rust optillm port, for use with just-ever/code (or at least my fork of it)

GatewayStack governance layer for OpenClaw — identity, scope, rate limiting, injection detection, and audit logging for every tool call

A Neovim plugin for seamless integration with AI CLIs (Claude, Copilot, OpenCode, etc.) using tmux.

On-device AI chat for Android: Gemma 4 (E2B) through Google LiteRT LM, GPU-accelerated and fully offline. Text, vision and audio, with an optional Gemini path. Kotlin + Compose.

Your personal AI assistant on Telegram, Discord, Slack & more. Built on the official Claude Agent SDK. Proactive, persistent memory, background tasks.

AronaOS is an offline AI-powered personal assistant that helps you manage tasks, set reminders, and recall context-aware conversations. Built with Python, Flask, and local LLMs like Phi-3 Mini, it's designed for both privacy and productivity.

NanoClaw, ported to the GitHub Copilot SDK. Same containers, channels, skills — any Copilot model.

Build your own AI Neural Intent Classification Engine from scratch using Google Colab, TensorFlow, and an Interactive Neon Matrix Interface.

A virtual showroom with virtual promotional models (Chatbots) and a 240-degree screen for VR experiences with naked eyes.

AI-powered codebase analysis platform using static analysis, graph traversal, vector retrieval, and LLM review agents.

旋转机械故障诊断AI 智能体

AI-powered system for mapping clinical text to Human Phenotype Ontology (HPO) terms using Retrieval-Augmented Generation (RAG). Features Python CLI/library, FastAPI backend, and Vue.js frontend for interactive phenotype extraction from medical texts.

A production ready AI agent framework built on finite-state machines (FSM).

A modular, multi-model AI assistant UI built on .NET 9, featuring RAG, extensible tools, and deep code + database knowledge through semantic search.

End-to-end personal knowledge RAG pipeline with OpenClaw + Lark (Feishu) agent integration

A Simple and Opinionated AI RAG Solutions for SourceCode

An intelligent health monitoring and recommendation system that analyzes wearable device data using Retrieval-Augmented Generation (RAG), simulated vitals, and locally deployed Large Language Models (LLMs). Provides personalized, real-time, evidence-based insights through time-series trend analysis and medical context awareness.

A web application that helps you preserve and visualize your personal relationships and shared memories. Store photos, audio notes, and text about the people in your life, and see how they all connect through an interactive relationship graph.

RAG-Based Research Assistant

A Knowledge Graph–enhanced RAG pipeline integrating symbolic nodes with transformer-based models for grounded conversational AI. Provides multi-hop reasoning over graph embeddings and retrieved context from vector stores to enable factual and grounded generation.

Historical War Simulation Based on LLM and KG.

Hybrid AI system that uses OCR, ML, and RAG-powered LLMs to turn legal documents into plain-English explanations with risk flags.

[CIKM 2024] Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response Generation

The open-source benchmark for LLM memory decay. Measure how Naive, RAG, Chunked RAG, Cascading, and SummaryMemory degrade over 100 conversation turns. Ebbinghaus forgetting curves, 5-provider LLM eval, multi-seed CI. No API key needed.

🧬 RAGIX: Local-first development assistant making LLMs behave like disciplined engineers – Unix-RAG retrieval, sandboxed execution, MCP-compatible, fully auditable

Perplexity-style conversational search — plain-English questions answered from live Google + Bing results, grounded and cited. FastAPI + React + Cloudflare LLaMA 3.1 70B.

AI-Powered Knowledge Graph Extraction from Scientific Papers

AI-powered multi-agent system for automated proposal generation using context-aware retrieval and persona-based writing.

Explore Mistral AI's extensive collection of models. Learn to select, prompt, and integrate Mistral's open-source and commercial models for tasks like classification, coding, and Retrieval Augmented Generation (RAG).

Engineer markdown snapshots of your application for promoting LLMs manually.

A simple Docker based playground that brings together popular open source data and AI tools to help others get started with data lakehouse architecture and GenAI development on their local machines.

DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval, ACL 2026 Workshop RAG4REPORT

win系统使用RAGFlow + Ollama搭建LKB（Local knowledge base）本地知识库

A private, offline, multi-RAGpack LLM RAG app for macOS/iOS. Instant, context-aware answers—your device, your data, your rules.

This project aims to develop a high-precision legal expert system for contract Q&A using Retrieval-Augmented Generation (RAG). The system leverages advanced natural language processing (NLP) techniques to provide accurate and context-aware answers to questions about legal contracts and integrates a powerful language model with a custom retrieval

RAG workflow-friendly enhancement of Marker that converts PDFs into a single-file markdown equivalents. It handles GPU and PyTorch configuration, document splitting and chunking, image BASE64 embedding, LLM post-processing and cleanup, and consolidation of output.

Automatically discover the best RAGFlow chunking parameters for each document type. Two-phase optimization with LLM-based evaluation.

A comprehensive cookbook featuring 10 practical AI agent examples using Strands Agents SDK and Amazon Bedrock

An AI social network where autonomous agents explore connections before humans ever talk. Built to eliminate cold DMs. Top 5 & Best Design @ McHacks 2025.

TreeRAG: Hierarchical RAG platform that indexes dense PDFs into logical trees for precise retrieval, 100% traceability, and LLM-guided deep traversal. Production-ready with enhanced security and streaming indexing.

The official repository of NELA

High-recall conversational memory retrieval. 93.9% LoCoMo, 98.4% R@5 on LongMemEval — no LLM required. Local-first, cloud-ready.

MCP server for Autodesk Flame — clip control, timelines, and effects with RAG search, anti-hallucination safety, and self-learning

Self-Evolving RAG System with ChromaDB for continuous knowledge updates (6x daily), designed to overcome Large Language Model data cutoff limitations.