Python agents

AGiXT is a dynamic AI Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.

Custom statusline for Claude Code CLI with 18 themes, rate limits, context tracking and ASCII Claude avatar

get knowledge from your private documents

Defect Library for LLM-enabled Software

Codebase for "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback". This repo implements a generative multi-turn RL environment with support for agent, user, user feedback, transition and veto models. It also implements KTO and expert iteration for training on user preferences.

这是一个基于大语言模型的 Text-to-SQL 工具，支持： 1. 多种 LLM（OpenAI、Qwen、硅基流动） 2. SQL 验证和安全检查 3. Schema 管理和语义注释 4. Few-shot 学习 5. 置信度评估 6. 查询执行和结果格式化

Description: Self-hosted graph-based associative memory for personal AI agents. Spreading activation, emotional weighting, zero LLM cost.

RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents

AI-native hedge fund using multi-agent LLM system with real market data and paper trading.

code for an agentic search tool using Langchain

AI-agent应用，基于GPT、langchain、function calling、Stable diffusion等的AI儿童绘本生成

利用ChatGPT最新的function-calling，实现类似LangChain Agent代理的联网、环境交互，目前支持 百度百科 | 网易新闻 |百度百科 | csdn | 掘金 | 谷歌api | Bing 工具

Decision making & Game theory in python.

Decentralized reinforcement learning for city-scale traffic light control

Safe Multi-Agent Robosuite benchmark for safe multi-agent reinforcement learning research.

Adversarial attacks in consensus-based multi-agent reinforcement learning

Code for Multi-agent reinforcement learning to unify order-matching and vehicle-repositioning in ride-hailing services

[ICML' 24] The PyTorch implementation of our paper: "Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning".

Official Telnyx Local Model Context Protocol (MCP) Server that enables interaction with powerful telephony, messaging, and AI assistant APIs. This server allows MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents and others to manage phone numbers, send messages, make calls, and create AI assistants.

Athena, an AI agent built on GPT-4 architecture, is designed for continuous learning and self-reliance. Inspired by the Greek goddess of wisdom, Athena assists users with valuable insights across various subjects.

基于 Planner–Manager–Executor 的文本 Agent；Executor 支持 YAML / Python 高度自定义；可选 Neo4j+Graphiti 记忆图谱；FastAPI + React。

ArXiv Agent is a terminal-based intelligent assistant designed for researchers and engineers who want to stay on top of the latest AI trends without drowning in PDFs. It combines daily digests, RAG-powered chat, and automated implementation into a single, cohesive workflow.

A Tavily-based agent generating evaluation datasets for web search RAG systems.

GenaiBots is an open-source framework that simplifies building intelligent and adaptable conversational agents using generative AI and a powerful plugin system.

A toolkit for biomedical data integration and harmonization

开源我自己 — A Claude Code skill trained on Flood Sung's entire Zhihu corpus (152 articles + 178 pins + 254 answers). Fork it to open-source yourself.

Build realtime AI interviewer voice agent that joins meetings. It demonstrates integrating Deepgram (STT), OpenAI (LLM), and Eleven Labs (TTS) via WebRTC for natural conversations.

A Blueprint-style visual node editor for creating FastMCP servers. Build MCP tools, resources, and prompts by connecting nodes - no coding required.

图文并茂的 PDF RAG 系统：支持版式感知分块、图表深度理解与精准视觉溯源。 Multimodal PDF RAG: Features layout-aware chunking, visual chart understanding, and precise inline image citations.

Book appointments, record messages, get information and much more via voice through Pam AI, an Auto-GPT like AI receptionist.

Introducing Eliza! A low-latency, human-like conversational AI with memory and the ability to handle interruptions ✨

Exploring CrewAI capabilities by building a basic stock analysis app.

Source code for the Foundations of Agentic AI for Retail Book

YiriOneBot是一个OneBot 11协议上的Python SDK，延续YiriMirai项目轻量级、低耦合的编码风格。

A PoC for a location-aware legal assistant powered by GPT-4 and Gradio.

Integrate Odoo with OpenAI and GPT Models. Make OdooBot finally useful by integrating with OpenAI ChatGPT-3!

OpenAI MountainCar-v0 DeepRL-based solutions (DQN, DuelingDQN, D3QN)

AI-powered telephony solution that enables businesses to deploy intelligent voice agents for various use cases such as customer support, appointment scheduling, lead qualification, and information collection.

An evaluation suite for Retrieval-Augmented Generation (RAG).

Multi-agent orchestration plugin for Claude Code — 10 specialized agents, persistent Brain memory, quality gates, continuous QA, wave-based parallel execution, and mechanical enforcement hooks

Aqua is a lightweight, agent-agnostic coordinator for CLI AI agents. It enables multiple AI agents (Claude Code, Codex CLI, Gemini CLI, or any CLI tool) running in separate terminal sessions to collaborate on tasks within a shared codebase. Built with Claude ❤️

Easily create a RAG app based on your Discord messages

AI-powered YouTube Shorts creation with AutoGen 0.4. Agents handle scripting, voiceovers, images, and video assembly—all automated!

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

Project for the Integrated Project 1 course at EAFIT. Dungeons & Dragons game generator

Enterprise AI Security Platform - Real-time firewall protection for LLM applications against prompt injection, data leakage, and function abuse attacks

Real-time task tracking and conversation memory for Claude Code sessions

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

AI Agents internals - system prompts, tool architectures, and implementation patterns

A Multi-Agent based application which provides a comphrehensive financial/market analysis of any company

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

Open-Sable is a local-first autonomous agent framework with AGI-inspired cognitive subsystems (goals, memory, metacognition, tool use). It can run continuously on your machine, integrate with chat interfaces like Telegram, execute real tasks safely, and keep data private by default.

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

🐦 AI agent that assembles production-ready OpenUSD scenes from natural language, so you focus on creative decisions, not pipeline work

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

[ICLR 2025] Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate

Local-first Python CLI and MCP server for versioned, cited context from web and document sources.

基于 FastAPI 的生产级 AI Agent 框架，支持 100+ LLM 提供商、MCP 工具集成、多 Agent 协作、RAG 知识库和沙箱隔离执行

Research Pilot helps AI agents understand, maintain, and advance research projects through papers, claims, evidence, experiments, and human-gated updates.

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.

멀티에이전트 Claude Code 하네스를 위한 토큰 비용 lint — 10 카테고리 × 31 sub-patterns 분류학 + 정적 감사 스크립트 + LLM 0회 결정 트리. Korean primary, English mirror.

Open-source RAG engine for ingesting, indexing, and querying unstructured documents

Aqueduct is a simple yet fully-featured AI gateway built on top of the LiteLLM Router SDK using Django.

OpenAI Router 轻量级、持久化、零配置的 OpenAI API 统一网关

A collection of AI solutions for oracle.ai

Awesome-HCI （Ubiquitous, LLM, MLLM, Agent, RAG, Embodied-AI, RLHF)

Curated technical knowledge base: 785+ dense reference articles across 26 domains. Agent-first format with wiki-links, gotchas, runnable code. Not tutorials — verified references for AI agents and engineers.

A Deception Security Layer for MCP Servers. It injects "ghost tools" (fake security-sensitive tools) that act as honeypots.

This sample demonstrates building a logistics tracking agent using Strands Agents SDK and an OpenAI model hosted on Amazon Bedrock AgentCore Runtime with VPC connectivity. The implementation shows how to create an intelligent agent that uses local tools to query a private Amazon RDS database running in an Amazon VPC to track shipments and delays.

GODMODE — AI Development Team powered by NEURON.ONE. Multi-agent orchestration for Claude Code. 56 skills, 16 rules, cross-model disputes (Claude + GPT + Gemini).

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

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

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

Example AI agents using AgentMail — hiring screener, legal intake, receipt parser, contract redline, and more.

ZulipChat MCP Server - A Model Context Protocol server that bridges AI agents with Zulip Chat. Built with FastMCP for lightning-fast performance, featuring comprehensive chat management and intelligent summarization. Transform your Zulip workspace into an AI-powered collaboration hub!

Swarm — Autonomous Drone Navigation

Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).

Multi-agent inference framework for RTL generation. A Verilog agent and a Python reference-model agent independently propose implementations and cross-verify each other's outputs on random stimuli — no golden testbench required. Open-source companion to the ChipMATE paper.

Reusable Agent Skills for embedded systems, MCU debugging, firmware workflows, and AI automation. （嵌入式、MCU 调试、固件流程与 AI 自动化的可复用 Agent Skills 集合）。

Open-source GEO engine for personal GEO promotion workflows. Reach Discord：https://discord.gg/GcNhAHPZu

All-in-one intelligent assistant powered by LlamaIndex — RAG, GraphRAG, NL2SQL, Skills & Memory with multimodal support.

Open-source AI agent platform for building, deploying, and managing AI teammates. Role-based agents (PM, Engineer, Support, Marketing) with custom tools, knowledge bases, and 50+ integrations. Self-hosted, multi-provider LLM support, no vendor lock-in.

Reproducible voice-AI benchmarking — TTS / STT latency and accuracy.

A nano, minimalistic, and lightweight library for building ReACT-based AI agents that use tools to solve tasks.

Local-first, extensible AI agent workspace — FastAPI + Next.js + LangGraph, with skills, MCP tools, artifacts, long-term memory, sub-agents, and multi-provider (DeepSeek/OpenAI/Anthropic) reasoning streaming.

Turn any English article or YouTube transcript into an offline deep-reading lesson page — Edge TTS, karaoke word highlight, per-lesson dictionary. For English learners who use local coding agents (Claude Code / Codex / OpenCode).

Intent-bound action authorization for AI agents — deterministic, per-action approval a prompt injection can't re-point, with a signed, tamper-evident audit trail.

Deploy agents to Claude Managed Agents, AWS Bedrock AgentCore, and Google. One folder, one definition, one command.

Turns vague requests into structured prompts, execution plans, and policy-aware workflows — with readiness verdicts, PR merge-safety checks, agent packs, and MCP tool exports. Offline-first, deterministic, provider-agnostic.

Centralized LLM configuration and documentation management system. Tools for building skills, commands, agents, prompts, and managing MCP servers. Multi-LLM support (Claude Code, Codex, OpenCode).

[ACL 2026] Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration

A collection of CLI tools and skills designed to be useful for LLM agents.

The SQL-RL-GEN is an algorithm based on a Reinforcement Learning approach with a reward function generated by a LLM to guide the agent's training process in solving the specific text2SQL generation task.

Multi-agent crypto research bot — scout, verify onchain, score risk, synthesize a research brief via long-chain LLM reasoning. Built on the Xiaomi MiMo platform.

Multi-agent occlusion inference using observed driver behaviors. A driver sensor model is learned using a conditional variational autoencoder. Information from multiple drivers is fused into an ego vehicle's map using evidential theory.