Python agents

AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)

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

AGI 社交网络 Bot. BiliBili | 直播聊天数字人 | 视频@自动回复 | 私信bot | 终端聊天 | 语音交互

JamTools是一个跨平台的小工具集类软件，支持Windows7/8/10/11、Macos、ubuntu系统(其他系统可以直接从源码编译打包)。包含了(滚动/区域)截屏、录屏、文字识别、多种语言互译、多媒体格式转换、鼠标键盘动作录制播放、局域网文件传输、聊天机器人等功能，完全开源!

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

Conversational voice AI agents

Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.

AI coworker self-improving agent

This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented Generation (RAG) pipeline.

Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex

An open source implementation of code execution with MCP (Programatic Tool Calling)

Command-line interface for ChatGPT, Claude and Bard

browser controlling AI agent that applies to relavant jobs on internet autonomously. join chat @ https://discord.gg/umgnyQU2K8

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

A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

Interactive LLM Powered NPCs, is an open-source project that completely transforms your interaction with non-player characters (NPCs) in any game! 🎮🤖🚀

[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome

AI-based stock analysis and trading system

LangGraph-powered ReAct agent with Model Context Protocol (MCP) integration. A Streamlit web interface for dynamically configuring, deploying, and interacting with AI agents capable of accessing various data sources and APIs through MCP tools.

Agent that empowers software testing with LLMs; industrial-first in China

ChatGPT Team(Business) 促销码自动扫描工具 — 批量发现/验证/价格收集，支持 17 国 34 个码，最高折扣 71% | ChatGPT Business promo code scanner — batch discovery, validation, price collection, 34 codes across 17 countries, up to 71% off

Run Hermes Agent and OpenClaw on the same WeChat account

Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.

An LLM Based Diagnosis System (https://arxiv.org/pdf/2312.01454.pdf)

Facebook chatbot that I trained to talk like me using Seq2Seq

If you can read ~100 lines of Python, you understand agents.

Cookiecutter template for FastAPI projects using: Machine Learning, uv, Github Actions and Pytests

LLMFlows - Simple, Explicit and Transparent LLM Apps

Talk to research papers like talking to authors - Python package with AI agent for arXiv papers

Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.

Open-source AI marketing plugin for agencies & in-house teams — 158 skills, 25 specialist agents, 12-Part Strategy Flow, Cowork team-persistent, EU AI Act Article 50 ready, 6-platform AEO/GEO incl. Google AI Mode. Installs on Claude Code, Cowork, Codex, Cursor, Copilot CLI, Antigravity. MIT-licensed.

Open-source local-first AI agent for desktop work. No account, no telemetry: use local models with Ollama/Rapid-MLX or bring your own provider key.

基于自然语言理解与机器学习的聊天机器人，支持多用户并发及自定义多轮对话

MCP configuration to connect AI agent to a Linux machine.

ComfyUI-IF_AI_tools is a set of custom nodes for ComfyUI that allows you to generate prompts using a local Large Language Model (LLM) via Ollama. This tool enables you to enhance your image generation workflow by leveraging the power of language models.

Design visual, review-gated agent loops for Claude Code before you run them.

The official Python library for Arklex framework

Open Source Company Brain

transformers safetensors deepseek_v2 text-generation conversational custom_code

FofaMap v2.0 是一款基于 Python3 开发的全网首个 AI 驱动红队资产测绘智能体。在延续原有 FOFA 数据采集、存活检测、统计聚合、图标 Hash 及批量查询等核心功能的基础上，2.0 版本原生支持 MCP 协议，可无缝接入 Cursor、Claude 等 AI 平台。其核心内置了 AI 自我反思机制，能根据查询结果自动调优语法，并智能联动 Nuclei 推荐精准扫描策略，实现从“被动采集”到“主动智能决策”的红队作业进化。

Autonomous Android and computer use using any LLM (local or remote)

SEO agent skill for OpenClaw,Claude Code, and AI agents. Generate beginner SEO audits and advanced technical SEO reports for any page.

transformers pytorch gpt_neox text-generation en license:apache-2.0

亚马逊选品 之 Listing全维度穿透分析报告 加上 全品类分析 ，关键词分析，差评分析 ，市场调研 等等。codex/claude code agent skill, amazon sorftime MCP/西柚mcp/sif mcp/卖家精灵sellersprite 智能体skill. 亚马逊跨境电商skill工具集。

A life simulation Game powered by GPT-4's “Advanced Data Analysis” function , offering you a second chance at life. 由GPT4的Advanced Data Analysis功能驱动的人生重来模拟器，给您人生第二春。

A pytorch implementation of MADDPG (multi-agent deep deterministic policy gradient)

An open source Scheduling Agent for Generative AI

Find zero-days while you sleep. DeepZero is an automated vulnerability research framework that parses, decompiles, and analyzes thousands of Windows kernel drivers for exploitable IOCTLs natively using AI agents.

transformers safetensors llama text-generation llama-factory orpo

Hierarchical agent loops with recursive self-organization.

"AnyTool: Universal Tool-Use Layer for AI Agents"

CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.

Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.

Readymade evaluators for agent trajectories

🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techniques, 24+ state-of-the-art Reranking models, and multiple RAG methods.

An Educational Project (step by step) to teach how to build a production-ready app for RAG application.

Pytorch implementation of the MARL algorithm, MADDPG, which correspondings to the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments".

Automata: A self-coding agent

An end-to-end Data Scientist

A Diagnostic Guardrail Framework for AI Agent Safety and Security

What if OpenClaw, Claude Code, Codex etc. knew how to do your work without you saying it? AgentHandover observes you, learns and teaches your agents with self-improving skills.

司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents

Repeatable agentic engineering. The workflow layer that turns AI coding agents into a disciplined factory: durable specs, fresh-context workers, adversarial cross-model reviews, receipts. Everything in your repo, zero dependencies. Claude Code · Codex · Cursor · Droid.

transformers safetensors qwen2 text-generation conversational en

A simple CLI to run LLM prompt and implement MCP client.

Chat with multiple PDFs locally

A Multi-Agent Trading System Based on Internal Contest Mechanism

Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

Shell and coding agent on mcp clients

A list of open-source AI projects you can use to generate income easily.

13 curated Agent Skills for research, product decisions, decks, publishing, audits, and more — portable across skills-compatible agents.

Spec Driven Development 🤠 Write codebase-aware specs for AI coding agents so they don't derail.

RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.

The AI-Q NVIDIA Blueprint is an open reference example for building intelligent AI agents that connect to your enterprise data, reason using state-of-the-art models, and deliver trusted business insights.

[EMNLP 2025] ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

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

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

transformers safetensors qwen3_5_moe image-text-to-text qwen world-model

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.

transformers safetensors gguf stablelm text-generation causal-lm

E-commerce skills for AI agents — product research, marketing automation, supply chain optimization, and business analytics for online sellers across Amazon, Shopify, Etsy, TikTok Shop, and all platforms.

Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)

The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.

Extract clean conversation logs from Claude Code's internal storage

Robin: A multi-agent system for automating scientific discovery

A PyTorch library for building deep reinforcement learning agents.

MCP servers for the UniFi suite of applications, Network, Protect, Access, and Drive

Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

Give your AI agent a brain that remembers. Local memory system for Claude Code — 100% private, GPU-accelerated, zero cloud dependency.

The Zero-Dependency, Sub-Millisecond AI Memory System for Hermes Agents and Everyone Else!

A practical approach to managing multiple AI agents in Cursor through strict file-tree partitioning and domain boundaries.

A swarm of disposable agents for unattributable web interaction. The user never acts on the web directly, delegating instead to agents that are destroyed on completion, leaving nothing that leads back.

A LLM-based Agent that predict its tasks proactively.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

ChatGPT at home! A better alternative to commercial smart home assistants, built on the Raspberry Pi using LiteLLM and LangGraph.