Python agents

Production-grade AutoCAD MCP server for AI agents — 122 tools, dual COM (live AutoCAD) + headless ezdxf engines, ISO GD&T and dimension-tolerance validation for CAD automation.

Codex skill that turns one image or text concept into a WeChat-ready Chinese sticker pack people will actually send. Sendability-gated, 4-keypose → 16-frame, no model-drawn text.

The original AI Chief of Staff built on Claude Code and Obsidian. ADHD prosthetic, open to anyone. Superseded by chief-of-staff-2.

Turn photos into source-faithful editorial artworks with an Agent Skill — adaptive layouts, controlled abstraction, and a Strict Fidelity composition path.

A local-first AI desktop planning assistant that turns goals into executable time.

🧪 Awesome list of AI Scientist papers, systems, benchmarks, datasets and open-source platforms.

A simple project for enabling LLM agents to use tools.

Gym environments and agents for autonomous driving.

Multi-Agents & Plugins repo for DB-GPT, Can complete various tasks around databases.

AI Agent Simulation generates Minecraft Settlements

Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning

Needle MCP Server for easy RAG.Long-term memory for LLMs.

Ebiose is a distributed artificial intelligence factory, an open source project from the Inria’s incubator (French lab).

+4M Downloads! Repair invalid LLM JSON, commonly used to parse the output of LLMs — Parsing ChatGPT and llm JSON stream response — Partial and incomplete JSON parser python library for OpenAI | repair invalid JSON, parse output of LLMs

AI-powered OSINT framework for multi-platform social media intelligence gathering using OpenAI-compatible APIs. Features vision analysis, network mapping, and dual web/CLI interfaces.

Run Claude in self-improving loops to optimize measurable goals.

Reverse-engineering Claude Code's 512K LOC TypeScript source: agent loop, tool system, permission model, Grove training pipeline, anti-distillation defense

Daily in-depth Chinese analyses of frontier AI research papers, including topics such as LLMs, agents, RAG, and RL. AI 前沿论文中文深度解读

Create motion-graphics videos from natural-language using Hyperframes. Researches topics, explains GitHub repos, renders the result.

Hands-on, project-based course in AI, LLMs, RAG, and agents — 24 modules in TypeScript + Python, provider-agnostic (OpenAI/Anthropic/Ollama/NVIDIA/LMStudio).

Self-hosted AI agent memory — MCP memory server with durable recall for agents

transformers safetensors qwen2 text-generation chat conversational

This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers in this list investigate the learning behavior, generalization ability, and other properties of language models through theoretical analysis, empirical analysis, or a combination of both.

Open-source, local-first AI coding agent usage and cost dashboard for Claude Code, Codex, Cursor, OpenCode, Kiro, and Pi.

Lobster0 — a self-hosted OpenClaw-inspired AI agent with persistent memory, governed autonomy, and self-evolution. 受 OpenClaw 启发的自托管 AI Agent「Lobster0」，具备持久记忆、受控自治与自我进化能力

Evidence-linked Palette Fusion for distinctive, editable, and print-ready academic posters.

A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.

The Library for LLM-based multi-agent applications

Opinionated sample on how to build/deploy a RAG web app on AWS powered by Amazon Bedrock and PGVector (on Amazon RDS)

Create your own GPT intelligent assistants using Azure OpenAI, Ollama, and local models, build and manage local knowledge bases, and expand your horizons with AI search engines. 使用 Azure OpenAI、Ollama以及本地模型创建自己的 GPT 智能助手，搭建和管理本地知识库，并使用 AI 搜索引擎扩展你的视野。

Multi-Modal-AI-Orchestrator (Reset version),AI Full-modal Full-agent:Text → Image → Music → Lights → Video, Includes "Scenario Director, Parent-Child Theater, Biofeedback, Party Collaboration Station, Scenario Recipes" - five ready-to-use scenario packages. AI全模态+全agent：含 “情境导演、亲子剧场、生物反馈、派对协作台、情境食谱” 五大开箱即用场景

A platform for building reliable AI agents

Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM

A+ Grade AI Agent Security Framework - Military-grade protection against prompt injection, command injection, and Unicode bypass attacks

[ICLR 2025] A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents

Practical Deep Reinforcement Learning Approach for Stock Trading. NeurIPS 2018 AI in Finance.

📚 Local PDF-Integrated Chat Bot: Secure Conversations and Document Assistance with LLM-Powered Privacy

An open toolkit for creating reusable skills that extend how your AI agent works.

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase. Bootstrap, Plan, & Ship.

Extend the Ollama API with dynamic AI tool integration from multiple MCP (Model Context Protocol) servers. Fully compatible, transparent, and developer-friendly, ideal for building powerful local LLM applications, AI agents, and custom chatbots

The GPT-RAG Orchestrator service is an agentic orchestration layer built on Microsoft Foundry Agent Service and the Microsoft Agent framework. It enables agent-based RAG workflows by coordinating multiple specialized agents to collaboratively generate accurate, context-aware responses for complex user queries.

Devr.AI is an advanced AI-powered Developer Relations (DevRel) assistant designed to revolutionize open-source community management. By integrating with platforms like Discord, Slack, GitHub, and Discourse, Devr.AI functions as a virtual DevRel advocate that helps maintainers engage with contributors and streamline onboarding processes.

Interactive terminals for AI agents, built for what you can't --yes away. SSH+MFA, GRUB/U-Boot, debconf installers, SOL/serial consoles, fsck, cryptsetup, pdb/gdb, apt, certbot, pwsh and even Vim in tmux-backed sessions. Agent-driven, human-assisted for secrets/MFA. Single-file Python. Agent Skill. CI with 700+ tests. BSD License.

🔬 A Researcher&Agent-Friendly Framework for Time Series Analysis. Train Any Model on Any Dataset!

【Openclaw & Hermes & 企业机器人🤖】钉钉Skill库，含：钉钉文档、知识库、AI(多维)表格、群(单)聊、会议室、日程、待办、通讯录、AI搜索等，自动管理配置，轻量级—仅依赖curl， skill经过严格测试。Lightweight DingTalk Skill Library (curl only). Includes AI search, docs, sheets, chat, meetings, calendar, todos & contacts. Auto-configured & rigorously tested.

This is an agent skill for coding agents like Claude code to use to tailor your resume, avoiding AI-generated wordings and automatically generate a concise and completely well-formatted resume in Docx for you.

Reusable GitHub Action that reviews Terraform PRs for security, cost, and style using a LangGraph multi-agent system, posting a single severity-ranked comment.

One ComfyUI skill for every AI coding agent (Claude Code, Codex, Gemini CLI, Qwen Code): drives a local ComfyUI end to end. 75 model prompt recipes, 581 templates, plus standalone Seedance, Krea and MiniMax H3 skills. Hardware-aware selection, workflow building, multi-shot video, ControlNet, HDR. By AI VFX NEWS.

transformers safetensors qwen3 text-generation agents terminal

gguf llama.cpp text-generation code coding reasoning

A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it.

Ten cooperating AI agents that turn long podcasts into short-form videos, automatically. Free and open source, runs on free AI providers.

Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, and AI-enriched metadata from research papers and books. Generate PRDs, workflows, topic clusters, and Claude Code skills from PDFs. No OCR required.

Curated collection of AI agent skills for Hermes and other agent frameworks

AI-powered data visualization assistant - Automatically generate professional charts from natural language descriptions. Supports 7 chart types and OpenAI/DeepSeek/Ollama platforms.

Codex skill for evidence-preserving academic rewriting in Chinese and English.

AsyncTool is a benchmark for evaluating the asynchronous function-calling capability of LLM-based agents in multi-task tool-use scenarios.

Rollout inference runtime for Agentic RL and multi-turn code agents

Production-ready Codex-compatible account-pool gateway with seamless failover, full-session recovery, native quota headers, WebSocket/HTTP bridge, and observability.

Local-first persistent memory for OpenAI Codex: governed recall, progressive disclosure, no hosted vector database.

A lightweight AI agent framework for vertical domain applications | 面向垂域应用的轻量级 AI Agent 框架

Load a PDF file and ask questions via llama_index and GPT

A Discord chatbot that supports popular LLMs for text generation and ultra-realistic voices for voice chat.

Example inspired by @joaomdmoura sample project

Jax and Torch Multi-Agent SAC on PettingZoo API

The ChatGPT/DeepSeek Voice Assistant uses a Raspberry Pi (or desktop) to enable spoken conversation with OpenAI or DeepSeek large language models. This implementation listens to speech, processes the conversation through the OpenAI/DeepSeek service, and responds back. Like Apple Siri, Amazon Alex, Google Nest Home, Mi XiaoAi etc.

顺便一提，我们支持 RWKV | 「Intel 2025 人工智能创新大赛」🚀AutoOPS: Provide the chaos brought by language models to the operation and maintenance industry! 🏆使用 LLM 提供的动力实现全自动运维，支持 Windows Server/Linux/macOS/Cisco IOS，可进行全网自动管理，让我们颠覆运维行业【带外管理/自动运维/IoT设备管理/WebHook监控/任意平台/全模态Workflow】

医疗问诊系统multi-agent框架

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation

An agentic workflow with a focus on reliability and developer experience

A benchmark suite for evaluating LLM-based interactive scientific reasoning.

A collection of agent-optimized LangChain, LangGraph and LangSmith skills for AI coding assistants.

Public implementation of "Multi-Agent Graph-Attention Communication and Teaming" from AAMAS'21

OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM

A Virtual Sales Agent that uses LangChain, LangGraph, and Gemini Flash to simulate customer interactions. Features include product inquiries, order management, and personalized recommendations through a user-friendly Streamlit interface.

[ACL2026 Main] AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts

DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue

Production-ready multi-agent academic illustration system with Chinese GUI, background generation, plot workbench, and portable result bundles. Extended from PaperBanana.

MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning

A resource-efficient C++ vector index engine built for low-RAM production workloads

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

transformers pytorch internlm feature-extraction text-generation custom_code

transformers pytorch codegen text-generation arxiv:2203.13474 license:bsd-3-clause

transformers safetensors gemma text-generation license:gemma text-generation-inference

transformers safetensors gemma4_unified image-text-to-text gemma4 coding

transformers safetensors qwen3_5 image-text-to-text vlm vision

An MCP-powered agentic RAG system that transcribes, indexes, and intelligently queries audio content using advanced retrieval-augmented generation.

Agentic memory infra for AI agents

Open-source AI-assisted HR onboarding for Feishu/Lark: configurable workflows, document OCR and review, Bitable sync, reminders, and a zero-credential demo.

Local-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.

好想上岸 / JD-Scout · AI agent that analyzes any JD against your resume, built with LangGraph + Chroma RAG + FastAPI. Paste JD, upload resume, get structured match report and rewrite suggestions.

A multi-agent campus social simulation built with LangGraph, featuring memory, RAG, personality evolution, and durable execution.

Search & apply to ~4,700 salary-transparent tech jobs across 7 countries (🇨🇭🇩🇪🇬🇧🇺🇸🇨🇦🇳🇱🇫🇷) from your terminal or AI agent — zero-dependency Python CLI + MCP server + Claude Code plugin

VetarAI 是一款运行在本地的agent桌面应用，可自由创建多个隔离项目，项目内动态编排主 Agent 与子 Agent。原生支持任务委派、可视化工作流等。全部数据保存在本地，不依赖任何云端服务。内置Rag知识库，真正降低上下文缓存读取压力，且支持自动关键词或语意索引，随时调用知识仓库的内容。

Task orchestration and engineering delivery for AI agents: definition, assignment, supervision, checks, verification, acceptance and rework. Knowledge/memory provide context. Reusable MCP/CLI capabilities; Claude Code/Codex adapters. Full supervision needs host adaptation and validation. Independently developed; noncommercial.

Evaluation Framework for all your AI related Workflows

AI Agent Nexus is an open-source platform for developing, testing, and hosting AI Agents, built with Streamlit and Gradio. It offers a user-friendly chat interface and focuses on teaching core concepts of building full-featured AI agents. The platform supports multipl AI Agent and assistant patters, and complements the book "AI Agents In Action."