Language

Python agents

61,093 Python AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.

61,093 agents · ranked by popularity · refine in the directory →

Python agents — page 40 of 611

youtube-agent-skill★ 187

Eleven Claude skills that run a YouTube channel: scripts off 21 hook formulas with a scored hook, title and thumbnail linted as one pairing, an edit decision list from your transcript, a retention reader that finds where viewers actually leave, a Shorts cutter, and a virality engine. Free, MIT.

jat★ 186

General multi-task deep RL Agent

Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow★ 186

Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow

openai-whisper-realtime★ 186

A quick experiment to achieve almost realtime transcription using Whisper.

presenter★ 186

A Multi-Agent AI Tool that creates beautiful presentations with voice-overs 🎦🔥

bibfixer★ 186

A Python tool that automatically cleans, completes, and standardizes BibTeX entries using LLMs and web search.

AIRouter★ 186

🚀 AIRouter - 智能AI路由器:为多个LLM提供商提供统一API接口,支持负载均衡、故障转移和智能路由 | Intelligent AI Router with unified API interface, load balancing, and smart routing for multiple LLM providers

deep-research-agent★ 186

Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search

cloud-mcp-server★ 186

A lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.

deepsearch-academic★ 186

An implementation of Google Deep Search with support for 1000+ references, local inference, chatting with your scraping session using RAPTOR, and report generation.

Qwen1.5-7B-Chat★ 186

transformers safetensors qwen2 text-generation chat conversational

gpt4-openai-api★ 185

Python package that provides (unofficial) API access to the GPT-4 through chat.openai.com. Works with langchain. Supports search DALL-E 3, plugins, continuing generation.

SubgraphRAG★ 185

[ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

meridian★ 185

Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after compaction, plug-in code standards, optional TDD mode, and zero behavior changes for developers.

AIAgentCogNest★ 185

AIAgentCogNest(AI + Agent + Cognition + Nest)主要记录大语言大模型(LLMs) 算法(应用)工程师相关的知识、从零开始的智能体原理及落地实践教程。

claude-remember★ 185

Persistent memory for Claude Code — identity, context, and continuity across sessions

llm-agents-from-scratch★ 185

Build LLM agents and multi-agent systems from scratch, with MCP, Skills, and A2A

agentic-kaggle-skill★ 185

🤖 AI Agent-driven Kaggle competition workflow. Battle-tested patterns for score stabilization, submission troubleshooting, kernel workflows, and spec-driven development.

trove-ai★ 185

中文互联网内容的个人 AI 稍后读 + 知识库 · Read-later + AI knowledge base for the Chinese internet

w7panel★ 185

web UI for Kubernetes clusters

gemma-4-26B-A4B-it-assistant★ 185

transformers safetensors gemma4_assistant text-generation any-to-any arxiv:2607.02770

pyCodeAGI★ 184
KoGPT2-chatbot★ 184

Simple Chit-Chat based on KoGPT2

dream★ 184

DeepPavlov Dream is a free, open-source Multiskill AI Assistant Platform built using DeepPavlov Conversational AI Stack. It is built on top of DeepPavlov Agent running as container in Docker. It runs on x86_64 machines, and prefers having NVIDIA GPUs on the machine.

SecReport★ 184

ChatGPT加持的,多人在线协同信息安全报告编写平台。目前支持的报告类型:渗透测试报告,APP隐私合规报告。

DyPRAG★ 184

[NeurIPS 2026 TTCL] Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement

ToolGen★ 184

[ICLR 2025] The official implementation of paper "ToolGen: Unified Tool Retrieval and Calling via Generation"

open-responses-server★ 184

Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing stateful features. Ollama and Vllm compliant.

agentica-python-sdk★ 184

The official Python SDK for the Agentica agent framework from Symbolica

BugTraceAI-CLI★ 184

Autonomous AI-powered security scanner — multi-agent vulnerability detection, exploitation, and validation engine

hermes-agent-team★ 184

基于 Hermes Agent 构建的本地多 Agent 团队协作 Web 系统

www-project-agent-memory-guard★ 184

OWASP Foundation web repository

markdown_web_browser★ 184

Renders any URL via headless Chrome, tiles screenshots into OCR slices, and streams structured Markdown + provenance back to AI agents and pipelines

Open-Arabic-LLM-Leaderboard★ 184

gradio leaderboard region:us

deepseek-coder-1.3b-instruct★ 184

transformers pytorch safetensors llama text-generation conversational

FriesTrader★ 184

Robinhood Agentic Trading agent — a fully automated AI trading bot placing real orders through Robinhood's Agentic Trading MCP, under mechanical, auditable risk rules the model cannot override. Able to run unattended on Claude Pro, no metered API spend. Not financial advice.

omnisim★ 184

Open-source robotics simulator for coding agents: HTTP/JSON + MCP control, Newton physics, wgpu rendering, ROS 2, and reproducible benchmarks.

instagram-agent-skill★ 184

Thirteen Claude skills that run an Instagram account: Reels off 26 scored hook formulas, a viral research skill, a caption linter, and a humanizer. Free, MIT.

private-chatbot-mpt30b-langchain★ 183

Chat with your data privately using MPT-30b

Gobigger-Explore★ 183

Still struggling with the high threshold or looking for the appropriate baseline? Come here and new starters can also play with your own multi-agents!

PowerGridworld★ 183

PowerGridworld provides users with a lightweight, modular, and customizable framework for creating power-systems-focused, multi-agent Gym environments that readily integrate with existing training frameworks for reinforcement learning (RL). https://arxiv.org/abs/2111.05969

sivalabs-agent-skills★ 183

Spring Boot skills for AI coding agents

ai-reverse-engineering★ 183

AI-Assisted Reverse Engineering with Ghidra

PaperLens★ 183

AI-Powered Research Assistant for Academic Paper Discovery, Analysis, and Citation Intelligence

ToolReplay★ 183

Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.

aws-mcp-server★ 182

A lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.

SpatialAgent★ 182

An AI agent for spatial biology

4D-ARE★ 182

Build LLM agents that explain why, not just what. Attribution-driven agent requirements engineering framework. Based on the 4D-ARE Paper - https://arxiv.org/abs/2601.04556

osbrain★ 182

osBrain - A general-purpose multi-agent system module written in Python

UHGEval★ 182

[ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.

MedAgentSim★ 182

MedAgentSim: Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions, MICCAI 2025 (oral and early accepted)

Frappe_Claude_Skill_Package★ 182

60 deterministic Claude AI skills for Frappe Framework & ERPNext v14-v16 development and operations

chunky★ 182

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.

jentic-one★ 182

Self-hosted execution layer for AI agents: connect any agent to real APIs, scope exactly what it can touch, and keep credentials out of the agent's hands.

generative-media-skills★ 182

Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.

habit-hooks★ 182

Automated quality checks that nudge AI coding agents toward better habits

redcache-ai★ 181

A memory framework for Large Language Models and Agents.

hal9★ 181

Hal9 — Build and Deploy AI Agents

ComplexFuncBench★ 181

Complex Function Calling Benchmark.

graphite★ 181

Graphite Agentic Framework by Binome Technologies

MASS★ 181

Official implementation of MASS: Multi-Agent Simulation Scaling for Portfolio Construction

indydevtools★ 181

An opinionated, Agentic Engineering toolbox powered by LLM Agents to solve problems autonomously.

os-ai-computer-use★ 181

AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app ready.

ClawSwarm★ 181

A smaller, lighter-weight version of OpenClaw, natively multi-agent, compiles to Rust, and built on the Swarms framework and Swarms ecosystem. One API, unified messaging across Telegram, Discord, and WhatsApp with optional Claude-powered reasoning.

nanzi-ai-agent-platform★ 181

🚀 开源企业级多智能体平台与 ChatBI 数据洞察平台。支持多 Agent 协作、RAG 知识增强、物理数据源直连与安全沙箱执行、Redis 长期记忆引擎,并集成多模态 EmbedChat 挂件与全方位 Token 消耗审计看板,完整 RBAC权限控制和 Harness支持。

local-deepsearch-academic★ 180

An implementation of Google Deep Search 🕵️ with support for 1000+ references, local inference, chatting with your scraping session using RAPTOR, and report generation.

GO-Bot-DRL★ 180

Goal-Oriented Chatbot trained with Deep Reinforcement Learning

Unity_ML_Agents★ 180

This is the code for "Unity AI" by Siraj Raval on Youtube

crewai-updated-tutorial-hierarchical★ 180
dbt-llm-agent★ 180

LLM based AI Agent to automate Data Analysis for dbt projects with remote MCP server

AiShell★ 180

AiShell: A Natural Language Shell like GitHub Copilot X, Powered by ChatGPT

Goida-AI-Unlocker★ 180

🛡 Установщик разблокировщика зарубежных AI-сервисов (и не только) для России 🌍

RelayFreeLLM★ 180

A restful API designed to route user prompts to various AI model providers.

DeepSeek-V2-Chat-0628★ 180

transformers safetensors deepseek_v2 text-generation conversational custom_code

Qwen3-Coder-480B-A35B-Instruct-GGUF★ 180

transformers gguf unsloth qwen3 qwen text-generation

humanizer-ru★ 180

Skill для AI-агентов (Claude Code, Codex, OpenClaw, Hermes): убирает 37 признаков AI-генерации из русского текста и проверяет, писала ли его нейросеть - канцелярит, штампы ChatGPT, артефакты копипаста | Russian AI-text humanizer & detector skill for coding agents

raggenie★ 179

RAGGENIE: An open-source, low-code platform to build custom Retrieval-Augmented Generation (RAG) Copilets with your own data. Simplify AI development with ease!

naptha-sdk★ 179

Naptha is a framework and infrastructure for developing and running multi-agent systems at scale with heterogeneous models, architectures and data

twitter-agent★ 179

Build AI-powered Agents for Twitter🐣

multimedia-gpt★ 179

Empowering your ChatGPT with vision and audio inputs.

wayflow★ 179

WayFlow is a powerful, intuitive Python library for building sophisticated AI-powered assistants. It is a reference runtime for Agent Spec, with native support for all Agent Spec Agents and Flows.

Severus★ 179

A tool for somatic structural variant calling using long reads

crewai_stock_analysis_system★ 179

基于CrewAI框架构建的智能股票分析系统,利用多Agent协作和智能流程控制,提供全面的股票投资分析服务。 🚀 特性 : 智能股票分析 基于AI的多维度股票分析, 批量处理 高效的批量股票分析, 实时监控 股票价格和指标实时监控 , 预警系统 智能预警和通知, Web界面 直观的Web管理界面

nano★ 179

One file. Under 200 lines. Zero dependencies. It's a coding agent.

Agent-MemoryForge★ 179

Production-grade memory layer for AI agents with durable multi-tenant memory, semantic recall, async distillation, and SDK/Gateway integration.

Zhihu-Collections-MCP★ 179

将知乎收藏夹(公开和私密)批量导出为 Markdown 格式文件. 支持配置收藏夹列表并批量下载, 支持基于URL自动去重, 支持下载专栏和图片, 支持自定义保存路径, 支持调试和错误日志. **同时提供 MCP Server**,可被 AI Agent (如 Claude Code) 直接调用,为大模型提供保存知乎收藏夹的能力。

personal-ai-assistant★ 179

Your personal AI assistant powered by multiple AI agents. Connects to WhatsApp, Slack, or Telegram to manage your emails, schedule, to-dos, messages, and daily research.

armor-crypto-mcp★ 179

The MCP server for interacting with Blockchain, Swaps, Strategic Planning and more.

iterative-development★ 179

Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints autonomously

easy-data-x-ai★ 179

《Easy Data x AI》是一门面向所有 AI 爱好者的数据与 AI 基础入门课程。通过双轨学习路径,从数据驱动视角学习构建 AI Agent。

Beacon★ 179

Lighting the path for every math modeling student. An end-to-end multi-agent LangGraph pipeline that turns competition problems into complete papers.

dsh-alpha-desk★ 179

把 dsh 会话变成合规、可复现、可追责的 AI 投研工作台:ai-hedge-fund 回测 + risk-gate 风控 + cron 盯盘 + 记忆复盘 | compliance-first AI investment desk

ChatData★ 178

ChatData 🔍 📖 brings RAG to real applications with FREE✨ knowledge bases. Now enjoy your chat with 6 million wikipedia pages and 2 million arxiv papers.

tf2multiagentrl★ 178

Clean implementation of Multi-Agent Reinforcement Learning methods (MADDPG, MATD3, MASAC, MAD4PG) in TensorFlow 2.x

open-webui-pipeline-for-ragflow★ 178

使用open-webui中的pipelines技术在open-webui中调用ragflow的agent实现基于知识库的智能对话,并拥有美观的界面。

crispr-gpt-pub★ 178

CRISPSR-GPT LLM Agent Public Welcome Page

prompt-guard★ 178

Advanced prompt injection defense system for AI agents. Multi-language detection, severity scoring, and security auditing.

vitabench★ 178

[ICLR 2026] VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

pokemon-agent★ 178

AI-powered Pokemon gameplay agent with headless emulation, REST API, and live dashboard. Works with any LLM.

skill-forge★ 178

Ultimate Claude Code skill creator — design, scaffold, build, review, evolve, and publish production-grade AI agent skills

Browse other language pages