Python agents

humanizer-ru: редактура русского текста для AI-агентов. Убирает канцелярит и шаблонные обороты, сверяет смысл и факты. 67 признаков, 21 жёсткий запрет, сканер, CLI, MCP и расширение Chrome. | Russian text editing for AI agents: removes bureaucratese and template phrasing, checks facts.

Monitor and drive your herdr agents from menu bar, phone, or Telegram. Zero config locally. Free tunnel for remote. No Tailscale needed.

AutoDoc-ChatGPT is a Python script that leverages the power of ChatGPT model to automatically generate documentation for any programming language. With AutoDoc-ChatGPT, you can easily generate comprehensive documentation for your codebase.

[ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

[ICLR 2025 Spotlight] The official implementation of our ICLR2025 paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs".

Official code for "Self-Distilled Agentic Reinforcement Learning"

The missing bridge between your ML models and your AI agents.

[NeurIPS 2026] SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Skills for Film and Television Creation Agents|31 个影视创作评估策划Agent Skills｜AI影视自动化工作流｜竖屏短剧长剧IP改编｜情节题材提炼｜剧本小说IP创作策划评估｜人物小传｜拉片人物剧集故事五元素分析｜大纲生成｜

Super performant RAG pipelines for AI apps. Summarization, Retrieve/Rerank and Code Interpreters in one simple API.

A curated list of awesome Agent Skills for automating legal work

XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation

AI agent for end-to-end software development, from requirements to operations.

Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.

Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)

AgentCoder: multi-agent code generation framework.

A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.

Open-WebUI-Functions is a collection of custom pipelines, filters, and integrations designed to enhance Open WebUI. These functions enable seamless interactions with Azure AI, N8N, Google Gemini and other AI models, providing dynamic request handling, preprocessing, and automation.

Reflexion: an autonomous agent with dynamic memory and self-reflection

故事想法 → 多智能体协作 → 漫剧成片 | 基于 LangGraph 的 AI 漫剧生成平台

A RAG pipeline implementation built on the 'Epstein Files 20K' dataset from Hugging Face (Teyler).

User-Agent , X-Forwarded-For and Referer SQLI Fuzzer

Framework to bring LLM applications to production

An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vault. Runs 24/7 on the Claude subscription you already have.

10 Claude skills that generate studio-quality AI video prompts for Seedance 2.0 on Higgsfield. Viral hooks, SaaS demos, personal brand, faceless content, luxury aesthetic & more.

AgentPy is an open-source framework for the development and analysis of agent-based models in Python.

Automatically generate youtube shorts easily with this simple script!

An agent skill for managing isolated execution environments

Intelligent error monitoring agent that uses Airweave to find context from your code, tickets, and Slack. Clusters similar errors, enriches with relevant context, and creates actionable alerts.

AI-powered companion for Homebox. Snap photos and let AI auto-identify and catalog items into your inventory, then use the AI Chat to organize, search, and update your inventory effortlessly.

LLM-powered trading agents that turn plain natural language into a five-pillar strategy: Trend, Mean-Reversion, Momentum, Volume, and Risk. Each strategy is hosted, self-evolving, configurable through 30+ tunable parameters, and bit-exact between backtest and live execution. Built for simulated Hyperliquid perpetuals.

Free-Dall-E-Proxy, an open-source repository that serves as a proxy for API-based interactions with OpenAI's DALL·E 3 image generation model provided by coze.

RL agent fusing real-time Binance futures data into Polymarket prediction markets. On-device training with MLX on Apple Silicon.

One agent. Every kind of work.

使用CrewAI+FastAPI搭建多Agent协作应用并对外提供API服务，同时支持gpt、国产大模型、Ollama本地大模型。

Oliva Multi-Agent Assistant

从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness：24 章 Python 教程，覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹

把工作流变成可研究、可评测、可发布的乔木 Agent Skill | Turn workflows into researched, tested, release-ready agent skills.

PrimoAgent: Multi-Agent Stock Analysis

transformers pytorch qwen text-generation custom_code zh

Transforms Databricks Unity Catalog tables into a materialized knowledge graph, with ontology design and reasoning exposed as tools via MCP.

OpenAI-compatible Web Chat API proxy with GPT, Grok, Gemini account management and Docker self-hosting

Azan + Prayer Time + MCP + AI Agents + Islamic + Salah + A lightweight MCP library to calculate prayer times and trigger Azan with a single tool call. If you’re building an AI agent or prayer application, there’s no need to deal with astronomical calculations, timezones, or edge cases again.

Agentic Generative Engine Optimizaiton

Powers add specialized context and tools to the Kiro agents on-demand. No more MCP context overload.

Vicoa is the agentic IDE for running a team of coding agents from desktop, mobile, VPS. Open-source, self-hostable.

Framework for Building Virtual Assistants with Dialogflow and python

Living memory for AI

Optimized local inference for LLMs with HuggingFace-like APIs for quantization, vision/language models, multimodal agents, speech, vector DB, and RAG.

Multi-objective multi-agent API and environments

gradio region:us

Django MCP Server is a Django extensions to easily enable AI Agents to interact with Django Apps through the Model Context Protocol it works equally well on WSGI and ASGI

智能体设计模式

A Pytorch implementation of the multi agent deep deterministic policy gradients (MADDPG) algorithm

The easiest, and fastest way to run AI-generated Python code safely

Connect your agents with anything. Make your tools composable. Secrets stay out of agent context.

illo skill — an AI agent skill that turns ideas and articles into original print-style editorial illustrations, starring a recurring mascot. 30+ characters packs, with ability to create your own.

The AI agent that physically operates a phone — the way you do.

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

transformers pytorch safetensors llama text-generation llama-2

Use your ChatGPT subscription to generate images from the command line — no OPENAI_API_KEY, no gateway, no daemon. Zero-dep Python CLI + AI-agent skill.

Multi-agent orchestration system for Claude Code with parallel execution, automated quality gates, Board of Directors, and bundled Superpowers skills

[EMNLP 2026] Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"

ATHF is a framework for agentic threat hunting - building systems that can remember, learn, and act with increasing autonomy.

Official AMD catalog of AI agent skills. Empower your AI agents with AMD's optimized SW stack.

A collection of Docker skills for AI coding agents to help them build, test, debug, and optimize containerized apps with consistent, reusable workflows.

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

基于 LangChain/LangGraph 的 ReAct Agent ，结合 RAG、工具调用与 Streamlit 界面，面向智能客服与报告生成场景。

Multi-agent orchestration for Claude Code — decompose tasks, coordinate agents, visualize everything in a rich terminal UI

Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.

Open-source reference implementations for AI-enabled payment security, blockchain fraud detection, and AML/CFT compliance reasoning.

✍🏻 gpt2-client: Easy-to-use TensorFlow Wrapper for GPT-2 117M, 345M, 774M, and 1.5B Transformer Models 🤖 📝

A basic 2D maze environment where an agent start from the top left corner and try to find its way to the bottom left corner.

Co-create PowerPoint slide decks with AI

siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems

Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode

面向硬件产品PCB方案设计的AI Agent，Agent会自动帮你进行需求确认，实时分析国内外各类芯片技术方案，进行器件选型，下载datasheet，输出BOM表，计算价格，输出模块原理图，最终整合成可落地技术方案。

Codex-first SEO skill suite. 26 workflows, 24 TOML agents, DataForSEO/Gemini/Google/Firecrawl integrations, GEO/AEO, CWV, schema, backlinks, local/maps, and deterministic reports.

A lightweight Python framework for parallel, isolated, collaborative AI reasoning.

AI Agent Skills built for Founders who hate Marketing

The Tree of Thoughts (ToT) framework for solving complex reasoning tasks using LLMs

A generative AI-powered framework for testing virtual agents.

Dynamic-memory-first collaborative AI framework for long-form story generation, chapter planning, and coherent narrative writing

Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.

Repeatable agents-plus-code workflows, packaged as one skill, stamped into any repo. Deterministic Python owns the graph; coding agents are bounded nodes inside it.

Official Python SDK for the Vulners vulnerability-intelligence API — search CVEs, exploits and advisories (CVSS/EPSS/KEV), audit software, Linux/Windows hosts and SBOMs, and stream the whole graph. Typed sync + async clients, 100% v3-compatible, with a built-in MCP server for AI agents.

配置和维护桌面应用中的原生子 Agent，支持选择模型、检查路由、修复、停用和卸载。

ChatWithBinary: Advanced AI-powered binary analysis tool leveraging OpenAI & LangChain (2023)

A RAG pipeline implementation built on the 'Epstein Files 20K' dataset from Hugging Face (Teyler).

Benchmark for Continuous Multi-Agent Robotic Control, based on OpenAI's Mujoco Gym environments.

Power rename/refactor tool for CLI and agent use

A MCP-Ready Intelligence Engine for Data & Agent-as-a-Service.

Make your Cc like agent from 0 to 1.

Turn Codex into your investment workflow team

The definitive OpenAI, Claude, MCP, Harness, Evals, and Production Agent Systems learning roadmap.

transformers safetensors qwen text-generation custom_code zh

streamlit region:us

Multi-Agent Connected Autonomous Driving (MACAD) Gym environments for Deep RL. Code for the paper presented in the Machine Learning for Autonomous Driving Workshop at NeurIPS 2019: