Python agents

This repo accelerates development of RAG applications with rich data sources including SQL Warehouses and documents analysed with Azure Document Intelligence

AgenticShop is a solution accelerator that demonstrates how to build an intelligent, multi-agent retail experience powered by Azure Database for PostgreSQL.

AI-powered knowledge management without vector embeddings. Built upon Claude Agent SDK, File system based, Agent driven. Maybe slower, but results are much more reliable!

Multi-UAV Assisted Wireless Powered Mobile Edge Computing: A hybrid optimization approach of combining multi-agent RL techniques (including attention mechanisms) with collaborative and adaptive caching policies for supporting mobile edge computing through UAVs.

Iron man inspired Personal virtual assistant

A structured Claude Code workflow to reformat research manuscripts for any journal's submission requirements without altering scientific content, created by Chen Zhu 朱晨 | 遗传社科研究.

Open-source, self-hosted multi-agent AI infrastructure for teams and apps with support for cloud and local models, tool integrations, workflows, and automation across business systems including Slack, ERPNext, Discord & Gmail.

Python port of the Flue: The Agent Harness Framework

Token Efficiency For AI Agents

《Easy Data x AI》是一门面向所有 AI 爱好者的数据与 AI 基础入门课程。通过双轨学习路径，从数据驱动视角学习构建 AI Agent。

GitHub intake + capability routing for Obsidian/Codex/Claude Code｜GitHub项目自动入库 + Agent能力冷库与调用路由

基于 OpenAI GPT-3 和 Mirai 的 QQ Bot 聊天机器人，提供公用测试 Bot，支持自定义人格以及各种参数，长文自动转图片发送，可持久化配置，多个群聊之间上下文隔离，异步响应，可扩展功能

A Discord chatbot that supports popular LLMs for text generation and ultra-realistic voices for voice chat.

ADL (Agent Definition Language) is a vendor-neutral, declarative standard for defining AI agents, including their tools, LLM settings, RAG inputs, permissions, and dependencies. It brings consistency, governance, and portability to enterprise AI by providing a clear, machine-readable agent blueprint.

A+ Grade AI Agent Security Framework - Military-grade protection against prompt injection, command injection, and Unicode bypass attacks

📚 Local PDF-Integrated Chat Bot: Secure Conversations and Document Assistance with LLM-Powered Privacy

An agentic workflow with a focus on reliability and developer experience

Turn any model into an agent. Model-agnostic, framework agnostic agent harness.

Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase. Bootstrap, Plan, & Ship.

Generate agents by simply describing your task in natural language

Libriscribe is an AI-powered open-source book creation system. The system is designed to help you write your book, from initial concept to a polished manuscript. It uses a multi-agent approach, where specialized AI agents collaborate to handle different stages of the book creation process.

AI Agent Skill for automated vlog editing. Feed raw footage, get a finished video. Powered by ffmpeg + Whisper + Vision API.

[COLM 2026]TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents

Multi-agent Stock research platform

transformers safetensors qwen3 text-generation agents terminal

AgentRadio: Passive Awareness for Long-Horizon Multi-Agent Collaboration

A lightweight AI agent framework for vertical domain applications | 面向垂域应用的轻量级 AI Agent 框架

AI-native multi-agent research workflow: parallel evidence gathering, 7-direction debate, and risk-gated analysis — structured output, not one-shot prompts.

Load a PDF file and ask questions via llama_index and GPT

Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM

Needle MCP Server for easy RAG.Long-term memory for LLMs.

Jax and Torch Multi-Agent SAC on PettingZoo API

[ICLR 2025] A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents

A multi-agent framework to fully automate anomaly detection in different modalities, tabular, graph, time series, and more (work in progress)!

Practical Deep Reinforcement Learning Approach for Stock Trading. NeurIPS 2018 AI in Finance.

+4M Downloads! Repair invalid LLM JSON, commonly used to parse the output of LLMs — Parsing ChatGPT and llm JSON stream response — Partial and incomplete JSON parser python library for OpenAI | repair invalid JSON, parse output of LLMs

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation

A benchmark suite for evaluating LLM-based interactive scientific reasoning.

A collection of agent-optimized LangChain, LangGraph and LangSmith skills for AI coding assistants.

Public implementation of "Multi-Agent Graph-Attention Communication and Teaming" from AAMAS'21

Official Oxylabs MCP integration

[NeurIPS 2025 D&B] VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework

Hermes Agent plugin for cron analytics and observability. The dashboard for agentic automations in Hermes.

CrawlLama 🦙 is an local AI agent that answers questions via Ollama and integrates web- and RAG-based research.

Create motion-graphics videos from natural-language using Hyperframes. Researches topics, explains GitHub repos, renders the result.

Independent Claude Skills for the whole smart home: Home Assistant, ESPHome, Node-RED, custom integrations, dashboards, and fab-ready hardware design.

transformers pytorch internlm feature-extraction text-generation custom_code

transformers pytorch codegen text-generation arxiv:2203.13474 license:bsd-3-clause

This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers in this list investigate the learning behavior, generalization ability, and other properties of language models through theoretical analysis, empirical analysis, or a combination of both.

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.

Autonomous AI-agent orchestration engine for job discovery with decision traces, tool adapters, and production-grade run control.

Opinionated sample on how to build/deploy a RAG web app on AWS powered by Amazon Bedrock and PGVector (on Amazon RDS)

Example inspired by @joaomdmoura sample project

Evaluation Framework for all your AI related Workflows

Ebiose is a distributed artificial intelligence factory, an open source project from the Inria’s incubator (French lab).

The ChatGPT/DeepSeek Voice Assistant uses a Raspberry Pi (or desktop) to enable spoken conversation with OpenAI or DeepSeek large language models. This implementation listens to speech, processes the conversation through the OpenAI/DeepSeek service, and responds back. Like Apple Siri, Amazon Alex, Google Nest Home, Mi XiaoAi etc.

AI Agent Nexus is an open-source platform for developing, testing, and hosting AI Agents, built with Streamlit and Gradio. It offers a user-friendly chat interface and focuses on teaching core concepts of building full-featured AI agents. The platform supports multipl AI Agent and assistant patters, and complements the book "AI Agents In Action."

Fully stealth chromium for AI agents.

AI agent to automatically check grammar and spelling on documentation files

The agent benchmark that scores the full stack — harness, config, and model — not just the LLM. Trace-based scoring, reliability metrics, configuration diagnostics.

Multi Agent Path Finding Algorithms

Deep active inference agents using Monte-Carlo methods

Code and links for over 25,000 trained Atari agents

Search Self-Play: Pushing the Frontier of Agent Capability without Supervision

LiveMCPBench is a benchmark for evaluating the ability of agents to navigate and utilize a large-scale MCP toolset. It provides a comprehensive set of tasks that challenge agents to effectively use various tools in daily scenarios.

Fetch papers as agent-ready markdown — DOI/URL/title in, structured full text out. CLI · MCP · Skill.

顺便一提，我们支持 RWKV | 「Intel 2025 人工智能创新大赛」🚀AutoOPS: Provide the chaos brought by language models to the operation and maintenance industry! 🏆使用 LLM 提供的动力实现全自动运维，支持 Windows Server/Linux/macOS/Cisco IOS，可进行全网自动管理，让我们颠覆运维行业【带外管理/自动运维/IoT设备管理/WebHook监控/任意平台/全模态Workflow】

Cortex: Advanced Memory System for AI Agents

AgentX is an experiment to develop autonomous agents so you can automate everything! This project is inspired by Auto-GPT, babyagi, SuperAGI, and other agents.

医疗问诊系统multi-agent框架

Multi-Agent Deep Reinforcement Learning for Task Offloading in GDMSs

ai trading agent using interactive brokers api

Simulation of reward tokens in a DAO ⚡️Employs multi-agent simulations and discrete-time Markov random fields.

Rag Agentic的一个雏形,用于研究学习

Official code for the paper: InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (previously: Do Role-Playing Chatbots Capture the Character Personalities? Assessing Personality Traits for Role-Playing Chatbots)

Augment AI agents with long-term memory through knowledge graph 🧠

An open toolkit for creating reusable skills that extend how your AI agent works.

希望用代码为 waifus 绘心。

Agent Skills to empower developers building AI applications with Weaviate.

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

Deterministic and Agentic patterns for installing and maintaining successful production applications

AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

Cyber-Zero: Training Cybersecurity Agents Without Runtime

The GPT-RAG Orchestrator service is an agentic orchestration layer built on Microsoft Foundry Agent Service and the Microsoft Agent framework. It enables agent-based RAG workflows by coordinating multiple specialized agents to collaboratively generate accurate, context-aware responses for complex user queries.

Fully automatic AI research agent for Geoscientists, Remote Sensing researchers, and GIScientists. Features harness engineering, GeoBenchmark (OLS/GWR/MGWR), journal templates, and MCP servers.

The source code of Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents (ACL2026 Main).

Headless Ghidra MCP server — giving AI agents deep reverse-engineering capabilities.

MCP-powered Home Assistant conversation agent that solves entity context limitations through dynamic discovery instead of full entity dumps

Official implementation of paper "ACON: Optimizing Context Compression for Long-horizon LLM Agents"

[CVPR 2026 Highlight] WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning

Interactive terminals for AI agents, built for what you can't --yes away. SSH+MFA, GRUB/U-Boot, debconf installers, SOL/serial consoles, fsck, cryptsetup, pdb/gdb, apt, certbot, pwsh and even Vim in tmux-backed sessions. Agent-driven, human-assisted for secrets/MFA. Single-file Python. Agent Skill. CI with 700+ tests. BSD License.

Run Claude in self-improving loops to optimize measurable goals.

Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs

AI股神Skill，改造了“麻省理工学院”开源的多agent股神框架，我用AI扒出了他们的核心源码，总结出了5个金融分析团队、8个核心agent提示词。用扣子封装成了一个人人可用的skill技能包。我们只要输入股票代码，AI就能模拟人类金融团队的运作模式，自动分析大a数据、并将舆情情报、板块涨跌、技术面、资金流动等多维度的可视化报告，自动推送到你的电脑上。用AI帮你彻底读懂市场行情！

Reusable GitHub Action that reviews Terraform PRs for security, cost, and style using a LangGraph multi-agent system, posting a single severity-ranked comment.

Turn any SIP call into a realtime AI voice agent (OpenAI Realtime / Deepgram/Gemini Live/xAI Grok Voice)

Ready-to-use agent skills that clone the thinking of founders, philosophers, and scientists into your agent. Generated with K-Dense-AI/mimeo.