Python agents

A collection of apps powered by the LlamaIndex LLM framework.

Get the information of a Github Repository using the power of LLM.

Get control of your overflowing inbox using GPT-3 to classify your emails by importance.

A basic AI chat using the OpenAI API and its GPT-3 models

A strongly typed Python DSL for developing message passing multi agent systems

基于ReAct构建的电商智能客服代理

🤖 Sam-assistant is a personal assistant that is designed to understand your documents, search the internet, and in future versions, create and understand images, and communicate with you. It is built in Python, mainly using Langchain and implements most of Langchain

Demo repo for connecting an LLM Agent to a Whatsapp webhook

RinAI agentic chat stack. Includes graphRAG memory, parallel tool calling, DeepSeek R1 powered web search, advanced LLM gateway and active context summarization.

Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging simulated continuous control single agent tasks. These methods have further been extended to multiagent domains in cooperative, competitive or mixed environments. This paper primarily focuses on multiagent cooperative settings which can be modeled for several real world problems such as coordination of autonomous vehicles and warehouse robots. However, these systems suffer from several challenges such as, structural credit assignment and partial observability. In this paper, we propose Recurrent Multiagent Deep Deterministic Policy Gradient (RMADDPG) algorithm which extends Multiagent Deep Determinisitic Policy Gradient algorithm - MADDPG \cite{lowe2017multi} by using a recurrent neural network for the actor policy. This helps to address partial observability by maintaining a sequence of past observations which networks learn to preserve in order to solve the POMDP. In addition, we use reward shaping through difference rewards to address structural credit assignment in a partially observed environment. We evaluate the performance of MADDPG and R-MADDPG with and without reward shaping in a Multiagent Particle Environment. We further show that reward shaped RMADDPG outperforms the baseline algorithm MADDPG in a partially observable environmental setting.

Build production-ready AI agents in days, not months. Python 3.13+. Save development time with minimal code, deploy anywhere with confidence, and scale from simple assistants to complex multi-agent systems without the headaches.

pytorch implementation of "Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control"

Agent Kit is a comprehensive AI agent development framework that integrates Claude Agent SDK, providing a complete solution from frontend to backend. This project aims to help developers quickly build, deploy, and scale production-grade AI Agent applications.

Lightweight, local-first memory for AI agents. Hybrid vector + BM25 search, LLM-powered fact extraction, zero infrastructure — just pip install.

Official Arcade Python Client

LangGraph ReAct Agents with an ability to use MCP Tools dynamically

LangGraph+A2A+MCP 实现的Agent RAG

Prompt Hardener analyzes prompt-injection-originated risk in LLM-based agents and applications.

[ToN 2024] Ensuring Threshold AoI for UAV-assisted Mobile Crowdsensing by Multi-Agent Deep Reinforcement Learning with Transformer

LangGraph Mastery Playbook: guided, code-first lessons for building memory-aware LLM agents and workflows with LangGraph, TrustCall, and LangChain.

700+ AI skills for Claude and Cursor — PLG, marketing, security, DevEx, and more. One command to install.

Sample for context-aware Agentic RaG, Q&A with multi-source verification, and self-curating knowledge base. Powered by Azure AI Foundry Agent Service, Azure AI Search with agentic retrieval and query rewrite, Semantic Kernel and LangGraph agents running in Azure Container Apps, and ready for Copilot Studio

UAV Flocking with Multi-Agent Reinforcement Learning. The Code of the paper: "An invulnerable leader–follower collision-free unmanned aerial vehicle flocking system with attention-based Multi-Agent Reinforcement Learning", which implemented fixed-wing UAV/Drone flocking with collision-free.

Kai Fusion Build AI Agents & Workflows, Visually

Multi-agent system that designs and generates complete agent team structures through conversational interviews. Supports Claude Code and Codex.

Outline-Driven Development - opinionated methodology between vibes and specs. AST tooling + context engineering + loop engineering on your hands. Plugins for Claude / Codex / Gemini / Cursor.

Since November 2025 D-PC Messenger, a decentralized, Privacy-First Infrastructure for Human-AI-Team Collaboration

[npj Digital Medicine 2026] HealthFlow: Automating electronic health record analysis via a strategically self-evolving multi-agent framework

(Let's start with a) Scalable question-answering system utilizing FastAPI, LangChain (LCEL), and PGVector, featuring an ingestion pipeline. Deployed on GCP Cloud Run via Terraform.

BitQuant is an open-source AI agent framework for building quantitative AI agents, leveraging specialized models for ML-powered analytics, trading, portfolio management, and more.

AI agent set for cloud security purple teaming, runs inside Claude Code, Gemini CLI, and Codex.

Quickly build MCP servers that expose your Django Rest Framework APIs as tools for LLMs and agentic applications to work with

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a generated IT-approval pack. Zero-dependency Python OSS.

LatentMem: Customizing Latent Memory for Multi-Agent Systems

PurpleCrew based on CrewAI with AI agents

Agent Skills for traceable requirements, independent verification, human approval gates, and auditable AI-assisted engineering. Supports Claude Code, Cursor, VS Code, and GitHub Copilot; ISO 9001/27001 aligned (design phase), GxP-aware.

memweave is a zero-infrastructure, async-first Python library that gives AI agents persistent, searchable memory — stored as plain Markdown files

A minimal, composable AI agent harness framework in Python.

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

Adversarial multi-perspective council MCP server for hermes-agent

AI crypto research engine for Claude Code. Analyze tokens across on-chain, tokenomics, sentiment, technical & fundamental dimensions. DeFi analysis, narrative tracking, token screening, PDF reports. 15 skills, 5 agents. Research only — not financial advice.

🚀 AI-Powered Windows Automation Server using Model Context Protocol (MCP) | Control Windows apps, automate tasks, and manage systems through natural language commands with Claude, ChatGPT & other AI assistants | 80+ automation tools

Code samples for building AI applications on AWS with Amazon Bedrock, including Converse API, tool use, RAG with Knowledge Bases, guardrails, and a full agent built with the Strands Agents SDK.

A Python runtime for multi-entity AI collaboration — agents, humans, and tools on a shared protocol layer.

Hermes Agent中文站- 中文实战入口：上手路径、国内落地、OpenClaw 共存迁移、排障参考与可下载方案包。

计算机专业 Skills 大合集：610 个 Claude Code / OpenClaw 风格 skills，覆盖编程、前后端、云平台、AI Agent、科研、自动化与安全审计。

Long-term Research Assistants with Self-Scheduling

OpenAI-compatible proxy for assistant-ui.com free LLM endpoint. Supports streaming, tool calling, vision, and 5 models.

Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server for seamless AI assistant integration.

Multi-agent debate system for Hermes Agent — spawn custom-composed expert agents to debate any question in structured rounds, producing visible transcripts and synthesized recommendations. Pure SKILL.md, zero new infrastructure.

Run your Mac with your voice — gpt-realtime-2 + agent-desktop. Clone it and teach your agent any app.

An autonomous photonic device design agent iteratively optimizes silicon photonic devices — no human in the loop.

docker region:us

transformers safetensors qwen2 text-generation code chat

gradio leaderboard region:us

transformers safetensors qwen2 text-generation feature-extraction mteb

transformers safetensors qwen3_moe text-generation abliterated uncensored

LemonClaw, an open-source, universal AI digital employee agent

Multiple agents, one source of truth: a Planner/Coder/Reviewer demo of how a shared Statewave subject prevents parallel-agent context collisions.

Private local AI Photographer Agent on AMD Radeon and ROCm

A collection of free AI coding tools! :copilot:

Local-first Agent Skills for safe social-web workflows—starting with Douyin and designed around reusable browser adapters.

Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, same scoring pipeline.

对话即创作 · AI Agent 驱动的小说写作工作台 ｜ Chat to create — an AI-agent-driven novel-writing workbench

Tutorial on using LLM APIs for computational social science research: OpenAI, Anthropic, open-source models via OpenRouter, and local LLMs with Ollama

Evidence-driven autonomous SOC team on AgentTeams: hash-bound approvals, HMAC audit chain, rollback and reproducible attack scenarios — auditable governance primitives for agent infrastructure.

Rebuild Claude Code's agent harness step by step with LangChain and LangGraph — from agent loops and tools to permissions, subagents, context compaction, memory, and recovery.

Repository retrieval and context engine for Claude Code and Codex: finds relevant code, reuses project knowledge, and pairs each task with specialist skills and verification.

Submit trading order to CEX & DEX with multi messaging platform and plugin support | EST. 2022

Fibo is a cutting-edge framework designed to build and deploy AI agents that seamlessly integrate automated task execution with interactive chat capabilities.

Python package that provides an agent framework that can be used to build agents that serve Sentient Chat events.

Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method search.

Long-term Research Assistants with Self-Scheduling

Fully automatic asynchronous AI operated Twitter bot using Large Language Models through OpenAI and Hugging Face to schedule and generate contextual content.

My first attempt at building an AI "agent". The agent will try iteratively solving Advent of Code puzzles.

Simple keras chat bot using seq2seq model with Flask serving web

Download music and play on Telegram for free

A Production-Ready agent components framework that compatible with other agent framework, such as agentscope, langgraph, autogen, more on the road

Task-oriented Dialog Policy Learning with Multi-Agent Reinforcement Learning

This project demonstrates a multi-agent system using Google's Agent Development Kit (ADK), Agent2Agent (A2A) and Model Context Protocol (MCP). that integrates Notion for information retrieval and ElevenLabs for text-to-speech conversion.

Multi agent scalable reinforcement learning for formation control with collision avoidance

Formation control for a multi-agent system in a bidimensional space. Various types of formations available. Implementation in ROS2 Foxy.

step-by-step guide on creating your very own AI bot using Python, Telegram, and OpenAI GPT models.

My attempt at implementing retreival augmented generation on Ollama and other LLM services using chromadb and langchain while also providing an easy to understand, clean code for others since nobody else does

Code and data repo for "DiagGPT"

Autoresearch with PhD-level workflows and modular agent skills. Built for the autonomous AI Scientist.

Dremio MCP server

AI-native application framework and runtime, simply write a YAML file.

Synthetic Role-Play Conversation Dataset Generation

A complete Retrieval-Augmented Generation (RAG) application that demonstrates modern AI capabilities for answering questions about Ultimate Frisbee rules and strategies. This project showcases how to build a production-ready RAG system using cutting-edge technologies.

MASA: Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management.

Light weight Claude Skills and Agents for every day tasks.

A FastAPI extension for integrating common AI agent frameworks.

This project demonstrates how to use AWS Bedrock with Anthropic Claude and Amazon Nova models to create a web automation assistant with tool use, human-in-the-loop interaction, and vision capabilities.

HTTPS C&C Framework with encrypted beacons, web dashboard, and Windows agent.

KGARevion: AI Agent for Knowledge-Intensive Biomedical QA

Zero-code LLM security & observability proxy. Real-time prompt injection detection, PII scanning, and cost control for OpenAI-compatible APIs. Built in Rust.