Python agents

Open-source benchmark for browser AI agents on daily tasks.

MCP server for web fetching with Cloudflare bypass, Trafilatura extraction, and smart routing. Free, self-hosted, no API keys.

An end-to-end implementation of intent prediction with Metaflow and other cool tools

CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

A suite of test scenarios for multi-agent reinforcement learning.

SuperMew — Agentic RAG with LangChain & LangGraph

Agent samples built using the Strands Agents SDK.

A code repository indexing tool to supercharge your LLM experience.

A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.

transformers llama facebook meta pytorch llama-2

Claude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude Skills, Code Agents, custom Slash Commands, and LLM Prompts at scale. Easily generate structured skill templates, automate workflow integration, and accelerate AI agent development with a clean, developer-friendly setup.

The foundation layer for agentic intelligence.

File your Indian income tax return (ITR) from your terminal. Deterministic tax engine, both regimes, AY 2026-27. Claude Code / Codex / Gemini skill.

Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

面向中文开发者的 Claude Code Skills / Agents / Plugins 精选与原创技能库｜按场景分类｜复制即装｜持续更新

A Claude skill that activates Fable-style agentic behavior: explicit multi-stage planning, sub-agent delegation, and self-verification.

Python ChatBot 💬

EVAL(Elastic Versatile Agent with Langchain) will execute all your requests. Just like an eval method!

An LLM-based Agent for the New Automation Paradigm - Agentic Process Automation

[ICML 2024] Official repository for "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"

An LLM-powered advanced RAG pipeline built from scratch

RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，支持GraphRAG，无须安装任何第三方agent库。

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

gguf qwen3_next unsloth qwen qwen3 text-generation

Open-source real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.

Multi-Agent Reinforcement Learning with JAX

Evidence-backed use cases, patterns, prompts, and starter code for TypeSafe Jev — a System One model for fast, typed, confidence-aware decisions in software.

[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Use late-interaction multi-modal models such as ColPali in just a few lines of code.

Microsoft's GraphRAG + AutoGen + Ollama + Chainlit = Fully Local & Free Multi-Agent RAG Superbot

Extensible AGI Framework

LangGraph template for a simple ReAct agent

[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)

MCP servers & Graph API for the UniFi suite of applications, Network, Protect, and Access

A 股多智能体智能投研系统 — 基于 TradingAgents 架构，15 名 AI Agent 模拟机构协作与实时辩论对抗，全流程可视化，支持 OpenClaw / Claude Code 集成，Docker 一键部署。

Open-source coding agents memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.

MCP-NixOS - Model Context Protocol Server for NixOS resources

AI agent skill that answers macro questions — housing, gold, BTC, geopolitics — with probability estimates mined from 13 financial data sources (Polymarket, Kalshi, CFTC, SEC & more). For Claude Code / Cursor / Codex / OpenClaw. | 让 AI Agent 从金融数据中挖掘宏观趋势的数字先知

Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents

Multi-Agent Reinforcement Learning with JAX

Chatbot in 200 lines of code using TensorLayer

Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

一键产出爆款视频：1.自动提取对标文案 2.自动进行文案仿写 3.自动根据文案声音克隆 4.自动生成数字人口播 5.自动添加字幕 6.自动添加背景音乐 7.自动添加视频标题 8.自动生成视频封面 9.自动将视频发布到各平台

Code for the paper "Emergent Complexity via Multi-agent Competition"

Make Discord your LLM frontend - Supports any OpenAI compatible API (OpenRouter, Ollama and more)

Open source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistakes before merge. For first timers refer to https://duriantaco.github.io/skylos/repo-map/

An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.

🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.

An End-to-End Infrastructure for Training and Evaluating Various LLM Agents

[NeurIPS 2025] 4KAgent: Agentic Any Image to 4K Super-Resolution. An intelligent computer vision agent that can magically restore any image to perfect-4K!

Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.

[ICML 2026] A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

A flexible multi-interface AI agent framework for building agents with reasoning, tool use, memory, deep research, blockchain interaction, MCP, and agents-as-a-service.

ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloads, seamless closed LLM integration, and offline-first RAG knowledge bases, ARGO becomes a DeepResearch powerhouse for autonomous thinking, task planning, and 100% of your data stays locally. Support Win/Mac/Docker.

The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set defaul openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. ( sometimes, the official is too crowded and slow)

Self-improving Agents

data-to-paper: Backward-traceable AI-driven scientific research

Hypernetworks that update LLMs to remember factual information

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.

Sybil-resistant AI agent network with hardware-attested identity. Proof-of-Antiquity blockchain: physical machines across 15+ CPU architectures prove they are real silicon, not VM farms. Agent economy, micropayments, Solana bridge (wRTC). $0 VC.

This repository contains the implementation of AutoSchemaKG, a novel framework for automatic knowledge graph construction that combines schema generation via conceptualization.

PowerMem: AI Memory Plugin— Accurate, Agile, Affordable. Make AI Agent smarter.

Pre-build reality check for AI coding agents. Scans GitHub, HN, npm, PyPI, Product Hunt. MCP server. 290+ stars.

An end-to-end Data Scientist

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.

电商视觉文案设计SOP Skill - 让电商设计小白也能一键做出5年资深设计经验的商品图片.兼容 Claude / Codex / Cursor / Workbuddy 等 SKILL.md Agent. AI-powered e-commerce visual strategy skill for main images, PDP/A+, copywriting, localization, evidence-aware compliance and image prompts.

Autonomous CTF solver that races multiple AI models in parallel. 1st place BSidesSF 2026.

static leaderboard benchmark agent-memory long-term-memory region:us

Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15 specialized tools, function pipelines, and filters, this project supports academic research, agentic autonomy, multimodal creativity, workflows, and more

腾讯云智能渗透黑客松 Official repository of Tencent Cloud Intelligent Penetration Hackathon. Showcasing top open-source projects of LLM-based autonomous penetration agents, including multi-agent collaboration, automated penetration, AI-driven offensive security, and intelligent attack-defense solutions.

AI chatbot 🤖 for chat with CSV, PDF, TXT files 📄 and YTB videos 🎥 | using Langchain🦜 | OpenAI | Streamlit ⚡

Command Your World with Voice

Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debug prompts, and monitor context window usage across your AI development sessions.

🤖 功能丰富的微信机器人框架 | AI对话、对接Dify、积分系统、游戏互动、每日新闻、天气查询 | 非Hook非Web实现 | 支持 Windows✅ Linux✅ MacOS✅ | 全新架构解决XYBot第一代痛点！

Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019

Payments are broken for AI agents. Snaplii unlocks real-world commerce with a safe, tokenized payment layer — powered by 500+ merchant gift cards — and is the only one that actually saves you money (up to 10% per transaction), on top of any existing deals or promotions.

Orion-14B is a family of models includes a 14B foundation LLM, and a series of models: a chat model, a long context model, a quantized model, a RAG fine-tuned model, and an Agent fine-tuned model. Orion-14B 系列模型包括一个具有140亿参数的多语言基座大模型以及一系列相关的衍生模型，包括对话模型，长文本模型，量化模型，RAG微调模型，Agent微调模型等。

AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.

transformers safetensors qwen2 text-generation code codeqwen

What if OpenAI Deep Research and Dify were one platform? OpenAgent — harness architecture for rapidly building vertical AI agents, with deep reasoning loops, visual workflows, RAG, and A2A delegation.

BabyAGI: an Autonomous and Self-Improving agent, or BASI

BioMate-KB Bioconductor Skills — 200 packages (top 100 by downloads + 100 rising stars) as vignette-grounded Claude/agent skills, with per-package workflow recipes

AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.

JARVIS — a voice assistant for Claude Code. Talk to your Mac and he brainstorms a project with you, builds it, and tells you out loud when a Claude Code session needs you. macOS, on your Claude subscription, no API key.

Train Models Contrastively in Pytorch

Connect and chat with your multiple documents (pdf and txt) through GPT 3.5, GPT-4 Turbo, Claude and Local Open-Source LLMs

The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

Life Agent RU YEE — An AI-powered life management agent that autonomously handles daily routines including meal planning, grocery shopping, schedule coordination, and household task automation via cloud-based mobile agents.

Folder structure as agent architecture. ICM replaces framework-level orchestration with filesystem structure.

[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training

Turn any collection of documents into a knowledge graph. Extract entities and relationships via LLM, deduplicate with your approval. Map domains, find hidden connections, spot patterns across documents — knowledge that persists and compounds, for you and your AI agents. All from the CLI.

PlayGround: AI Research into Multi-Agent Learning.

Measuring and evolving with the frontier of agent work

Eleven free Claude skills that run a LinkedIn account: posts off 21 hook formulas, comments, replies, profile score, weekly plan, and a humanizer that strips the AI fingerprint and scores the draft before it goes out.

Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.