Python agents

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).

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.

A local-first multi-agent runtime for ML research. One task in, continuous iteration out, with leader, researcher, and trainer working through a forum-style runtime board and a separate training queue

Local memory infrastructure for AI agents. Store knowledge and skills in isolated vaults you compose, control and query.

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

LLM Agent Skill for YARA rule authoring and review

Clarity is a financial analysis agent framework built on native Claude-skill architecture. Adopting a Planning-with-Files approach, it coordinates specialized sub-agents via persistent task plans, research findings, and progress logs to tackle complex financial analysis workflows.

PenGym: Pentesting Training Framework for Reinforcement Learning Agents

AI agent that controls a computer

ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs (OpenAI, Anthropic, Gemini, LangChain, MCP)

MCP server that connects AI agents to your running Neovim instance via msgpack-RPC — no plugins required.

[NeurIPS 2025] MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks

Production-ready platform for building, deploying, and operating AI and agentic applications

MCP Android agent - This project provides an *MCP (Model Context Protocol)* server for automating Android devices using uiautomator2. It's designed to be easily plugged into AI agents like GitHub Copilot Chat, Claude, or Open Interpreter to control Android devices through natural language.

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

輸入文字或圖片，LLM會找出適合的梗圖來回覆你

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".

Source code graph RAG (GraphRAG) for C/C++ development based on clang/clangd

Git for agent memory. Branches, diffs, PRs, and rollback for what your agents know.

ATM-Bench: A benchmark for long-term personalized memory QA spanning ~4 years of multimodal data (images, videos, emails). Features referential queries, evidence-grounded answering, and multi-source reasoning. Paper: "According to Me: Long-Term Personalized Referential Memory QA"

Terminal neurovisualizer for Hermes Agent. 100+ animated themes that react to what your agent is doing. Watch your AI think.

🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

An AI-backed threat hunting assistant that aligns to the PEAK framework.

Subagent Delegation framework for Pydantic AI, enabling nested subagents that can spawn their own specialists on-the-fly, with smart sync/async/auto mode selection, runtime agent creation, and clean multi-agent architecture. Adds specialization, parallel execution, and task cancellation.

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。

AI coding workstation: OpenCode + Claude subscription support + 30+ tools + headless browser + multi-agent orchestration

Autonomous AI-driven QA framework — give it a URL, get comprehensive test coverage

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

A local-first AI memory system with hybrid search, MCP integration, and a knowledge graph.

AI 驱动的多领域安全分析 Agent 平台 —— 让 LLM 端到端完成安全分析

A travel planning Agent powered by LangGraph, Amap POI, route clustering and LLM-based itinerary generation.

AI Agent 科研全流程教学包，能教学生从零部署 Codex、Claude Code、OpenClaw、Hermes 等 Agent，学会使用 Skills、飞书、AMiner、AI4Scholar、Zotero、Obsidian 等工具，完成真实文献检索、文献日报、知识库搭建、选题生成、理论建构、情景实验设计、量表开发、统计分析、因果推断、文本挖掘、EEG/ERP 实验、BCI 脑电智能建模、论文写作、审稿自查、期刊排版和盲审投稿包制作；学生学完后可以按课程模板一步步让 AI Agent 协助完成从“找文献、定选题、做实验、分析数据”到“写论文、查引用、改格式、准备投稿”的完整科研流程。

gradio agent-demo-track region:us

gradio region:us

transformers gguf llama llama-2 text-generation code

transformers pytorch safetensors llama text-generation conversational

Native Word (.docx) generator tool for Open WebUI — Markdown/JSON in, cover pages, styled tables, callouts, TOC out. MIT.

自媒体视频发布前违规风险审核。检查画面/声音/文字/封面/评论/带货信息/资质/引流，输出 Pass→Blocker 五级风险报告。覆盖抖音/小红书/视频号/B站/快手+千川低质素材。Claude Code、codex、workbuddy、hermes skill

🤪 Русскоязычный чат-бот для Discord на архитектуре Transformer

This is a documents loader. (文档解析加载器，rag文档解析，rag知识库构建)

Submission for MAVEN: Multi-Agent Variational Exploration

Algorithm that combines QMIX with SAC for Multi-Agent Reinforcement Learning.

[COLING 2025] Official code of the paper "The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models"

This repo provides guidance on setting up a bedrock agent to webscrape and internet search via action groups

A comprehensive Model Context Protocol (MCP) server for Nigerian banking operations using the Mono Open Banking API.

[ACL 2024] The project of Symbol-LLM

Multi-runtime automation infrastructure for AI agents. Native CDP browser control, metadata-driven Recipe system, and persistent Run context management.

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

Structured Output Is All You Need!

Build your own RAG and run it locally on your laptop: ColBERT + DSPy + Streamlit

Repository of Telegram's BotListBot

ChatGPT ShellMaster enables command-line interactions via chat using OpenAI's ChatGPT Plus. Run scripts, manage files, and monitor processes directly from your chat. Use responsibly, mindful of security implications.

💥💥 This is a easy installable extension for OpenAi Gym Environment. This simulates SpaceX Falcon landing.

Small web frontend for using openAI's GPT-3.5 and GPT-4's API

Automatically extracts, processes, and indexes code snippets from GitHub repositories into a searchable vector database.

Minimal implementation of multi-agent reinforcement learning algorithms

A simple, easy to use framework for adding randomized, anonymous IP addresses and user-agents to web scrapers, crawlers, and penetration testing solutions

Enterprise Grade, Voice AI simulation SDK for testing your AI Agents

NoneBot2 猫娘聊天插件

TrustAgent: Towards Safe and Trustworthy LLM-based Agents

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

Mental health chatbot developed in RASA Framework, to analyze person's chances of mental illness on the basis of a survey questionnaire. Have a fun conversation with the bot and uplift your mood!

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.

Evaluate Multimodal LLMs as Embodied Agents

🚀 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)

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

Efficient multi-strategy Zotero search using code execution pattern

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

Tara Bot — AI Telegram agent: search flights, compare prices, inject affiliate links

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

An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks

基于CrewAI框架的A股智能投资分析系统，使用多智能体协作进行投资决策。本系统仅供教育和研究目的，不构成实际投资建议。

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

CLI enabling more autonomous black-box penetration tests using Large Language Models (LLMs)

Open-source Environment toolkit of claw-like agents, support task/harness generation and evaluation

[ICML2026]A method to use LLM function calling with real-time level speed, empowering latency-sensitive applications like robotics, game AI, and autonomous agents.

An AI-powered process mining suite that converts natural language to process models and uses autonomous agents to analyze event logs and generate actionable process insights.

Turn any website into a CLI/API for AI agents

An AI girlfriend or boyfriend that lives inside your terminal. Real personas, real conversations, your shell as a chat room.

STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models

The official repository for paper: Agentic Robot: A Brain-Inspired Framework for Vision-Language-Action Models in Embodied Agents

The runtime reliability layer for AI agents.

The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.

Drop-in skill so coding agents (Claude Code / Codex) can search the Banodoco Discord message feed for video/image generation best practices.

Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, deterministic checks, built for CI.

Use any LLM with Claude Code — proxy that translates Anthropic API to OpenAI, Gemini, DeepSeek, Ollama, and more. Full tool calling, streaming, ReAct XML fallback, hot-reload config.

here is the collection of ai agents mostly and highly used in specific filed for our day to day life check them out and fast&up your work

An AI agent skill that extracts subtitles/transcripts from video platforms and generates structured summary notes with keyframe screenshots. Works with **Cursor** and **Claude Code**.

239 evaluated academic Claude/agent skills across 17 research domains (bioinformatics, data science, clinical, social-science methods, Turkish academia & more). Executable eval per skill, deterministic citation verifier, research→write→review→publish pipeline, and a skill-finder front door. Claude Code, Cursor, Codex, Gemini CLI & Copilot.

Helix-AGI is an Agentic AI System that uses a spatial-graph memory retrieval system. Agents receive a rolling adaptive system prompt of memories and skills that afford the agent a highly dynamic center of conceptual gravity. By avoiding long identity files and subagent-heavy workflows, Agents can develop continuously without spiraling costs.

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).

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

基于 Claude Agent SDK 构建的自托管 Agent 工作台，可以复用 Claude、ChatGPT 订阅额度。集成文件、预览、AI 对话和真实终端。多工作目录、主流模型一键接入、HTML／Markdown 即写即渲染，以及桌面端、移动端多端内容同步。

Find and redact secrets in AI coding agent histories (Claude Code, and more).