Python agents

基于OpenAI的私有资源库问答系统

A library integrating embedding and reranker models from OpenAI, SentenceTransformers etc for semantic search in vector database.

手把手教你如何开一个AI炒股公司

offical code of paper 'SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding'

Generate personalized travel itineraries based on user preferences.

Benchmarking the gap between AI agent hype and architecture. Three agent archetypes, 73-point performance spread, stress testing, network resilience, and ensemble coordination analysis with statistical validation.

TrustAgent: Towards Safe and Trustworthy LLM-based Agents

Codes for Paper "Delay-Aware Multi-Agent Reinforcement Learning".

Temodar Agent is an AI-powered WordPress plugin and theme security analysis platform built for security researchers, product security teams, auditors, and defenders. It combines AI agent workflows, multi-provider LLM orchestration, Semgrep-powered static analysis, and risk-based WordPress reconnaissance in one local-first Docker application.

Healthcare RAG agent with Neo4j knowledge graphs - Query medical data using LangChain, FastAPI & Streamlit

AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents

Code for "TrustRAG: Enhancing Robustness and Trustworthiness in RAG" AAAI 2026 Workshop on Trust and Control in Agentic AI (TrustAgent)

🚀 智能意图自适应执行引擎，只需一句话，让AI帮你搞定想做的事（数据分析与处理、高时效性内容创作、最新信息获取、数据可视化、系统交互、自动化工作流、代码开发等)

AI agent that controls a computer

[CVPR 2025] Official PyTorch code of "Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation".

Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube - your agent remembers forever. Based on Karpathy's LLM Wiki pattern.

A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic retrieval from a local vector store, queried before each message. For cross-project recall where flat memory files or vector-only RAG fall short. Local-first. Reference implementation.

[ICML 2026] JustAsk: Curious Code Agents Reveal System Prompts in Frontier LLMs | Verified on Claude Code | Autoresearch for System Prompt Extraction

从一个技术关键词出发，自动生成前沿技术领域的技术全景图谱。AI Agent Skill for Gemini CLI / Claude Code.

[NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents".

在千问最新的多模态image-text模型Qwen3-VL-4B-Instruct 进行多种lora微调对比效果，通过langchain+RAG+多智能体(Multi-Agent)进行部署

A holistic framework for advancing LLMs as data science agents

Agent skill library for PixVerse CLI — helps AI agents (Claude Code, Cursor, Codex, etc.) generate videos and images through structured, composable workflows.

🤖 Cortex AI: #1 智能量化交易系统 — 全自动加密货币套利引擎 v3.4。支持 Solana、TON、Binance (币安) 和 Bybit。2026年最佳高频量化交易机器人。

黑马程序员大模型RAG与Agent智能体项目实战教程，基于主流的LangChain技术从大模型提示词到实战项目

Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality gates, and full provenance.

Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP-compatible agent.

Lightweight Linux sandbox for AI agents. Kernel-native isolation (namespaces, cgroups, seccomp, Landlock) with REST API, MCP bridge, and web dashboard. Single Rust binary.

Sovereign Digital Twins that execute operational processes inside secure, audited environments.

Hierarchical Expert Prompt for Large-Language-Models: An Approch Defeat Elite AI in TextStarCraft-II for the First Time

Open-source terminal AI coding-agent harness for studying agent loops, tools, MCP, skills, safety, and persistence.

NGA 回复监听、股票看板与本地 AI Agent / NGA monitoring, stock dashboard & local AI agents

Midra is an agentic prompt-to-code MIDI composition framework for editable and controllable music generation.

Automation harness that compiles a screen recording into a rerunnable script, with LLMs, only at decision points and self-healing reruns.

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-agent backends through an MCP server + CLI.

Strands-based agents and harnesses for agentic benchmarks.

transformers safetensors gemma2 text-generation therapeutics drug-development

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

gradio agent-demo-track region:us

transformers safetensors qwen2 text-generation code qwen

transformers safetensors qwen3_5 image-text-to-text abliterated uncensored

Your AI agents can't see your files. ctxd connects your cloud data and makes it searchable via API, CLI, or MCP.

Solweaver: a Codex software team with GPT-5.6 Sol orchestrating Terra and Luna workers.

Open-source, model-agnostic AI company research for long-term investors. · 面向长期投资者的开源、模型无关 AI 公司研究系统。

gguf chat text-generation en arxiv:2309.16609 license:other

A production-oriented multi-agent AI Agent system for software engineering. | 面向软件研发任务的多智能体 AI Agent 工程系统

State-of-the-art prompting techniques implementation with DSpy - Manager-style prompts, role personas, meta-prompting, and more

Model-agnostic streaming TTS inference server with OpenAI- and ElevenLabs-compatible APIs. Plugin backend architecture (Qwen3-TTS included), CUDA-accelerated, built for real-time voice agents, with reproducible latency/RTF/GPU benchmarks.

AgentDNS is the core component of Agent network that facilitates agent registration and discovery, enabling large language models (LLMs) to browse the internet freely, just like humans.

Convert LangChain tools to FastMCP tools

Chatbot in russian with speech recognition using PocketSphinx and speech synthesis using RHVoice. The AttentionSeq2Seq model is used. Imlemented using Python3+TensorFlow+Keras.

Browsing-enabled GPT agents with different personalities.

Chatbot_CN项目中的Chatbot_rasa模块

The Flask server that communicates with my FB Messenger chatbot

Let taotie keep an eye for you on the information you care.

Python code that generates pixelart using OpenAI's Dall-E 3 and controls a Lego Pixelart machine using Mindstorms.

Data Agent is an intelligent data analysis system that automatically completes complex data analysis tasks through multi-agent collaboration.

Tensorflow Implementation of Multiple Landmark Detection using Multi-Agent Reinforcement Learning Paper

OpenAI Swarm Agents

General Tool-calling API Proxy

Streamlit application that leverages ChatGPT and LangChain to analyze tweet sentiment from selected Twitter authors.

Modern Desktop Application offering a suite of tools for audio/video text recognition and a variety of other useful utilities.

Bot on aiogram powered by AI

Use OpenAI TTS(Text to Speech) API with Gradio

Similarity detection for Github Issues + AI code reviews

Multi-Agents using Workflows

Architecture Details for CVPR 19 paper: Multi-Agent Tensor Fusion for Contextual Trajectory Prediction

An OpenAIGym-based framework allowing to test Delay-Aware Deep Reinforcement Learning algorithms for cooperative multi-UAV systems in fully customizable scenarios (e.g., coverage maximization, tracking, spotting).

OpenAI Gym environment designed for training RL agents to control the flight of a two-dimensional drone.

GPTStonks is a financial chatbot powered by LLMs and enhanced with data frameworks. It provides natural language conversation capabilities for financial topics, making it an ideal choice for a wide range of financial applications.

Evaluate Multimodal LLMs as Embodied Agents

My version of the Stanford experiment "Generative Agents: Interactive Simulacra of Human Behavior" in Python using a local LLM.

This template demonstrates how to create a collaborative team of AI agents that work together to process, analyze, and generate insights from documents.

Opinionated sample on how to build and deploy a RAG application with Amazon Bedrock and OpenSearch

The Most Powerful Open-Source Autonomous SQL Agents - RAG, NL2SQL

State-of-the-art prompting techniques implementation with DSpy - Manager-style prompts, role personas, meta-prompting, and more

EvoSynth is a SOTA automated LLM red-teaming framework that evolves executable, code-level jailbreak attack methods using multi-agent synthesis, evolutionary search, and self-correction.

A collection of Claude skills I have concocted to optimise my Ops/Product workflows.

AI tool that generates an Audio short story based on the context of an uploaded image by prompting a GenAI LLM model, Hugging Face AI models together with OpenAI & LangChain

Domain-Aware Neurosymbolic Agent (Dana), an agent-native programming language

A mini assistant to help you read paper quickly

LLM & IDA 主导的逆向分析平台

輸入文字或圖片，LLM會找出適合的梗圖來回覆你

JARVIS AI Assistant 🤖 A virtual assistant project inspired by Tony Stark's JARVIS, powered by speech recognition, AI chat, web browsing, and more. Features: 🎙️ Voice-based interaction using speech recognition. 🧠 AI-powered chat with OpenAI's language model. 🌐 Web browsing capabilities to open websites. 🎵 Music playback. ⏰Current time display

Route Snowflake operations from any coding agent (Claude Code, Cursor, Codex, Github Copilot, Windsurf, VSCode etc) to Cortex Code CLI — with smart routing, security envelopes, and headless execution.

Terrarium: Multi-turn data engine for evaluating and optimizing LLM agents in living environments.

高考辅导Agent：基于 LangGraph 的多智能体框架，集成情感识别、RAG 试卷检索与个性化学习规划，为学生提供全方位的智能助学体验。

Open Coscientist is an open-source adaptation based on Google Research's AI Co-Scientist research paper. We provide an open implementation that generates, reviews, ranks, and evolves research hypotheses using the multi-agent architecture described.

🤖QueryMind is an agent framework for building LLM-powered agents specialized in Text2SQL📊 tasks with agentic retrieval capabilities🔄 and enterprise-grade security🔒.

Engineering-grade ROS 1 / ROS 2 skill for Codex, Claude Code, and Gemini CLI.

AI-powered learning platform with 6 specialized agents for personalized education. Features adaptive roadmaps, quizzes, tutoring, RAG document Q&A, and learning style adaptation. Built with Phidata, Streamlit, and LangChain.

ConDB: The KV-Cache Native Context Database

Premortem skill for Claude Code — finds the concrete ways a plan could fail before commitment. Multi-agent silent scan, mitigation triplets, history snapshots, reverse-premortem. Klein 2007 + Kahneman outside view.

Claude Code skill that deploys any web app, API, or agent to the internet — strict pre-deploy audit, preview → prod flow. Bilingual EN/ES. By @soyenriquerocha · Tododeia.

Helix-AGI is an Agentic AI harness system that runs on a continous daemon pulse with spatial-based subjective memory pipelines and Affect simulator built overtop a conventional RAG memory system and utlizing a branched context window subagent task system where subagents join in memory but keep specialized skill knowledge appended directly to schema

EvE is an open-source framework for co-evolving ensembles of coding agents. Wrap Codex into an evolutionary loop that co-evolves solvers and agent guidance.

This course uses a deliberately vulnerable banking application to demonstrate common security vulnerabilities, their impact, and how to fix them. The application is built with Flask (backend) and React (frontend).

Local-first research tool with explicit fetch decisions, source evidence, and cited reports. CLI and MCP interfaces. Python, MIT.

Open-source AI-powered website audit CLI using the OpenAI API for SEO, UX, accessibility, performance, trust, and content analysis.