Python agents

Instagram marketing skills for Claude Code and Codex: captions, carousels, hooks, hashtag strategy, and a weekly plan. Draft, humanize, and publish via Publora. MIT. Content engineering by Creative Content Crafts.

A DSH plugin for novel writing and short-drama production, powered by Oh Story and Drama Skills.

A Python Telegram bot powered by Google's gemini-pro LLM API

[ICCV] Social NCE: Contrastive Learning of Socially-aware Motion Representations

(Deprecated) Facebook Messenger Platform Python Library (Facebook Chatbot Library)

An SDK for multi-agent collaborative perception.

RAG enabled Chatbots using LangChain and Databutton

Multi-agent Combat Arena (UAV swarm vs UAV swarm)

Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files

Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)

StoryCraftr is an open-source AI-powered tool that helps writers craft stories, generate worldbuilding details, and create book outlines and chapters seamlessly through a simple CLI. Empower your creativity with AI!

[ICML-25] AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

AI agent that reads the fine print so you don't have to. Upload any contract → get red flags, unfair terms, and plain-English explanations in seconds.

AI real estate research engine for Claude Code. Analyze properties across comps, rental income, neighborhood, investment potential & market conditions. Residential, commercial, flip, BRRRR analysis + PDF reports. 15 skills, 5 agents. Not investment advice.

A python-based light but strong lobster. A lightweight but powerful AI Agent framework in Python, with multi-channel support, tool calling, cron scheduling and streaming output

Bambu Lab AI (Bambu Studio AI): agent skill for 3D printing on Bambu Lab. Finds models on MakerWorld & Printables, generates or designs them in CAD, checks printability, hands them to Bambu Studio and reads printer/AMS status. For Claude Code, Codex, Cursor, Gemini CLI and any SKILL.md agent. Featured in 我的拓竹 Skill 大赏.

AI-powered Dropbox search tool for private documents

pbsv - PacBio structural variant (SV) calling and analysis tools

GPTUI is a GPT conversational TUI (Textual User Interface) tool that runs within the terminal. It has some distinctive features, such as multi-AI group chat, AI-initiated care, and other functionalities.

Heterogeneous Hierarchical Multi Agent Reinforcement Learning for Air Combat

ChatIndex: Tree indexing and retrieval for long conversational memory

Simplify Web Reverse-engineering for AI Agents

Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

Free Easy AI visibility check - measure how often a brand is mentioned & cited in Claude's web-search answers. Deterministic, reproducible, runs 100% locally, $0 mock by default.

gradio region:us

transformers pytorch jais text-generation Arabic English

Browser-native AI agents for X (Twitter): multi-account, MCP-ready, no X API key required.

基于 RAG 的 AI 智能笔记助手「云尚」：FastAPI + LangGraph + ChromaDB + Redis 构建。ReAct / Plan-and-Execute 双 Agent 模式、深度思考、图片/视频多模态、MCP 联网搜索与网页抓取、DeepL 翻译 / Wolfram 计算 / Edge TTS 语音、PPT 生成、记忆压缩、知识库重排序、笔记回收站与邮件导出、Token 用量追踪。后续版本会持续优化并添加Skill功能

transformers pytorch jais text-generation Arabic English

🦡 codebadger is a containerized Model Context Protocol (MCP) server that gives AI agents and LLMs deep, queryable access to a codebase's structure and data flow through Joern Code Property Graphs (CPGs).

GEO 领域 AI 员工开源方案 · Open-source GEO AI-employee solution (MIT). GEO Skills package + curated lists of agents and office CLIs that make up the AI-employee stack.

Setting up QA testing agents using playwright and crewAI

The implementation of "Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4"

A full stack app for interruptible, low-latency and near-human quality AI phone calls built from stitching LLMs, speech understanding tools, text-to-speech models, and Twilio’s phone API.

Bridge Claude Code CLI with Feishu/Lark via WebSocket. 飞书 × Claude Code 实时对话。

Open-source AI-augmented Security Operations Center using LLMs + Multi-Agent Orchestration | Foundation-Sec-8B | Wazuh | TheHive | RAG

Claude Code toolset for developing TradingView pine scripts.

Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic coding pipeline, model-agnostic and local-friendly.

Run DeepSeek V4 Flash as a native Codex subagent without replacing the OpenAI main agent.

Committed to being the best code interpreter in the world.

👀🧠 GPT-4 Vision x 💪⌨️ Vimium = Autonomous Web Agent

Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google AntiGravity, and MCP-enabled assistants

CivAgent is an LLM-based Human-like Agent acting as a Digital Player within the Strategy Game Unciv.

Code for our paper: Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

DSPy module for OpenAI Codex SDK - signature-driven agentic workflows

AI tool for automating Upwork job applications using AI agents to find and qualify jobs, write personalized cover letters, and prepare for interviews based on your skills and experience.

Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.

Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, HTTP traffic tracking, and an analytics dashboard to track agent actions.

SearchAgent-Zero: A Scalable Multi-Turn Search Agent RL Framework

📚 PaperFlow: Dynamic personalized scientific-paper recommendation, reading, and reporting

Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer, local-first, a structured alternative to RAG.

transformers gguf llama text-generation llama-factory orpo

88篇中文 AI API中转站与工具配置教程：Codex API、Claude Code API、OpenAI-compatible API、Base URL、Cursor、Cherry Studio、计费验证与错误排查。

Self-hosted auto clustering AI agent OS for consumer hardware like the computer you already own, an Orange or Raspberry Pi or a Mac Mini etc. Full desktop, app store, agent deployment, distributed compute cluster. Memory by taOSmd.

AI-Powered Malware Analysis & Threat Intelligence for Ghidra Transform your static analysis workflow with cutting-edge AI capabilities, comprehensive malware detection, and advanced threat intelligence.

AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query file structure, dependency graphs, and change impact. Built for Copilot, Cursor, and any tool-calling LLM. 面向 AI 编程助手的代码库感知技能——生成持久化知识图谱，精准查询文件结构、依赖关系与改动影响半径。

An Multi-Modal LLM Powered Agent to automatically solve Captchas

AI-driven Yu-Gi-Oh! bot using deep reinforcement learning and LLMs

A scalable RAG platform combining LangGraph agents, hybrid retrieval (Vector+Graph), and Ray orchestration on Kubernetes.

Deep Skill Finder – Real Tests Real Reviews find skills that Real Work

Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.

Attention-based Deep Reinforcement Learning framework for portfolio allocation on S&P 500 equities. Includes custom environment, policy architecture with cross-sectional attention, PPO/A2C/REINFORCE agents, training/evaluation pipeline, and fine-tuning grid search.

Build an AI Agent from Libraries of Functions -- My most advanced agent framework

Welcome to **LiveRecall**, the open-source alternative to Microsoft's Recall. LiveRecall captures snapshots of your screen and allows you to recall them using natural language queries, leveraging semantic search technology. For added security, all images are encrypted.

🤗 Would you like to use GPT4 with Plugins but don't want to pay $20/month? This is the solution! With this repository you can have free clone of ChatGPT with plugin

Like ChatGPT's voice conversations with an AI, but entirely offline/private/trade-secret-friendly, using local AI models such as LLama 2 and Whisper

Framework for learning dialogue agents in a two-player game setting.

[MTI-LLM@NeurIPS 2025] Official implementation of "PyVision: Agentic Vision with Dynamic Tooling."

An open-source Python SDK and CLI Starter Toolkit for deploying AI agents to Volcengine AgentKit Runtime.

This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'

Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University

The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Bench

Automated system for LLM evaluation via agents. Doc as below:

The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.

transformers gguf unsloth qwen3 qwen text-generation

transformers safetensors llama text-generation conversational license:other

Forge is an open-source, self-hosted alternative for visually building and shipping AI agents and workflows without giving up control of your infrastructure.

A Lean quality system for AI-assisted work — every defect becomes a permanent countermeasure. Built by a manufacturing operator.

Reusable Agent Skills for Amazon product research, listings, advertising, inventory, and operations.

ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.

A comprehensive, production-ready framework for building intelligent AI agents with advanced capabilities including tool calling, persistent memory, intelligent concurrency, and event-driven observability

Multi-turn dialogue baselines written in PyTorch

LLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmind's PySC2 Learning Environment API as a Python LLM Environment.

Synthetic Data Generation Toolkit for LLMs

BreadFree-Simu 是一个基于大语言模型（LLM）的 A 股智能量化回测系统。它利用多智能体协作（Multi-Agent）架构，模拟机构投资者的决策流程（分析-风控-决策），旨在探索 AI 在中国特色金融市场（T+1、涨跌停板）中的应用潜力。

Claude Code and Codex SKILLs for PDF, Excel, Word, and PowerPoint manipulation — extraction, forms, formulas, tracked changes, adapted from Anthropic skills.

迅投 QMT 量化 AI 技能集（Agent Skills）：研报因子回测脚本生成等，适用于 Claude Code / Cursor / Codex / Kimi 等 70+ AI 编程工具

docker region:us

Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, deep research, content generation, vibe coding, browser automation, governance, and admin controls.

面向 Codex、Claude Code 等 AI Agent 的医学绘图 Skill，基于可信证据制作医学插画、科普漫画与科研示意图，提供可编辑成果与审核记录。 · Evidence-backed medical illustration, comics and research figures for Codex, Claude Code and other AI agents, with editable output and review records.

Build Secure and Compliant AI agents and MCP Servers. YC W23

A multi agent path planning solution under a warehouse scenario using Q learning and transfer learning.🤖️

Talk with multiple ChatGPT agents

agentevals is a framework-agnostic evaluations solution based on OpenTelemetry traces

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

A lean, ROS-free sim-to-real framework for training and deploying Vision-Language-Action (VLA) models and RL agents. Native MuJoCo Gymnasium wrappers with synchronous execution for Franka, UR5e, xArm, SO101 and YAM.

docx ↔ LLM translator. Projects .docx office files to Markdown for editing. Projects edits back to OOXML as tracked changes (redlines). Python and Node.js implementations.

transformers safetensors qwen2 text-generation code qwen

The why layer of repo-native project memory: the reasoning behind a codebase as Markdown in the repo, versioned by Git, for coding agents and humans, so nothing rejected is proposed twice. No database, no daemon, no account.