Python agents

DocMason is a repo-native agent that turns your complex office files into a local LLM knowledge base and your second brain. The repo is the app. Codex is the runtime.

Jax Official Implementation of T-RO Paper: Songyuan Zhang*, Oswin So*, Kunal Garg, Chuchu Fan: "GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Control".

Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.

This accelerator unifies enterprise data with Microsoft Fabric and applies agentic AI to enable faster, smarter decisions. With Microsoft Foundry agents and the Microsoft Agent Framework orchestration, teams can automate workflows, query data in natural language, and uncover insights that fuel agility, collaboration, and innovation.

A high-quality collection of study skills built for high school and college students, teachers, and TAs. Use it directly in Kael.im for free without installing skills

Automated Web Penetration Testing Assistant Based on Function Calling and Multi Agent.

20 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and quality audits (eval-leakage, doc-drift). Works with Claude Code, Codex, and Cursor.

CAD CLI and MCP server for AI agents

transformers safetensors gguf llama text-generation facebook

gradio mcp-server-track agent-demo-track consilium Mistral SambaNova mcp-server region:us

AI Simulation Interview — Multi-Agent Orchestration (Ai模拟面试，多agent，免费开源）安装即用

IOSM v1.0 specification: reproducible methodology for continuous system improvement. Reference runtime implementation → github.com/rokoss21/iosm-cli

Cooperative Driving Dataset: a dataset for multi-agent driving scenarios

This CLI tool allows you to easily use chatGPT in the command line. You can chat with it, ask it questions, and get text translations. It also supports rendering Markdown in the terminal.

Distributed Resource Allocation with Multi-Agent Deep Reinforcement Learning for 5G-V2V Communication

Input a YouTube video link or upload a video file and get a video with subtitles.

CUREBench @ NeurIPS 2025: Benchmarking AI reasoning for therapeutic decision-making at scale

Lean implementation of various multi-agent LLM methods, including Iteration of Thought (IoT)

An opinionated framework for building sophisticated AI Agents

Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment

SCAM - Security Comprehension Awareness Measure | Open-source benchmark that tests AI agents' security awareness during realistic, multi-turn workplace tasks.

Cursor Agent Tools - A Python-based AI agent that replicates Cursor's coding assistant capabilities, enabling function calling, code generation, and intelligent coding assistance with Claude, OpenAI, and locally hosted Ollama models.

Connect your Claude agent to Google NotebookLM — add sources automatically, query notebooks, generate branded slide decks.

A sample agentic ai platform to run agentic workflows on AWS using either EKS or Bedrock AgentCore with open source frameworks like LangChain/LangGraph, Strands, etc..

An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Codex into a structured recon → test → exploit → report workflow, with containerized tools and resumable state.

Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost

gradio region:us

transformers coreml llama text-generation meta llama-2

smol is a smol agent

带 AI 精读大型开源仓库的方法论：四阶段流程、可复用模板、28 条踩坑清单，核心是让每个技术论断都可回溯到源码具体行

Open-source AI business orchestration platform for running governed AI agents across ERP, CRM, Microsoft 365 and other business systems.

A curated collection of papers, research blogs, open-source tools, benchmarks, and community demos for robot-use agents, including demos powered by GPT-6 Astra. —— Explore our searchable website.

Powerful web application that combines Streamlit, LangChain, and Pinecone to simplify document analysis. Powered by OpenAI's GPT-3, RAG enables dynamic, interactive document conversations, making it ideal for efficient document retrieval and summarization.

A deep ranking personalization framework

go-cqhttp python 框架，可以用于快速塔建 bot

Multimodal AI agent with Llama 3.2: A Streamlit app that processes text, images, PDFs, and PPTs, integrating NIM microservices, Milvus, and Llama-3.2 models.

PGDrive: an open-ended driving simulator with infinite scenes from procedural generation

Design multi-agent environments and simple reward functions such that social driving behavior emerges

A minimalist implementation of Agentic Memory architecture is DSPy

Local llamaindex RAG to assist researchers quickly navigate research papers

A solution accelerator project harnessing the capabilities of Azure AI Language to augment an existing Azure OpenAI RAG chat app. Utilize Conversational Language Understanding (CLU) and Custom Question Answering (CQA) to dynamically improve a RAG chat experience.

"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨

PentestAgent is a novel LLM-driven penetration testing framework to automate intelligence gathering, vulnerability analysis, and exploitation stages, reducing manual intervention. For more information, read our paper at https://dl.acm.org/doi/10.1145/3708821.3733882

Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development

Autonomous Assumed Breach Penetration-Testing Active Directory Networks

Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewAI, OpenAI, Anthropic.

CLI server for Zotero 7/8/9 — let AI manage your library. 70+ CLI commands for search, import, PDF, BibTeX, notes, and more. Works with Claude, Cursor, ChatGPT.

AI Agent Skill for automated vlog editing. Feed raw footage, get a finished video. Powered by ffmpeg + Whisper + Vision API.

Modular GraphRAG framework

GAN-style self-improvement loop for any text artifact: mutate, grade with a SEPARATE model, keep only verified wins (pairwise-judged), revert the rest. The git history is the improvement log.

Living Memory Coordinate-5: five-axis memory architecture for long-running LLM agents. Minimal SQLite + production PostgreSQL/pgvector reference impls, multi-channel recall pipeline, LLM-proposed hippocampus, persona policies, VPS 7×24 deployment shape. Not another vector DB.

transformers gguf llama llama-2 text-generation code

gguf code agent agentic-coding moe coding

A persistent, reviewed multi-agent runtime for long-horizon research and engineering.

Self-hosted multi-model deep research system that fuses independent research agents into evidence-grounded reports.

Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.

transformers safetensors llama text-generation instruct finetune

Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.

App-Controller: Allow users to manipulate your App with natural language

A minimalist multi-agent framework for rubost automation of scientific analysis workflows, such as gene expression analysis.

An advanced AI assistant that leverages the capabilities of ChatGPT API, Gemini Pro, AutoGen, and open-source LLMs, enabling it both to engage in conversations and to execute computing tasks on local devices.

GPT-4V in Wonderland: LMMs as Smartphone Agents

AgentGPT 中文部署文档翻译，一句话让你懂它是什么

Creating Amazon Bedrock agents with Streamlit Framework

The Active Reliability Layer for AI Agents. Catch failures, teach fixes, and automate reliability

AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reasoning models.

[MM 2024] [Need only a 3090] MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors

Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.

[ICLR'26] MedAgentGYM: Training LLM Agents for Code-Based Medical Reasoning at Scale

miniClaudeCode - 从50万行蒸馏到~1000行的Claude Code核心Agent架构最小复现 | Distilled Claude Code agent framework

A lightweight, event-driven multi-agent framework for embodied AI systems.

A Python-based CLI coding agent, similar to Claude Code and OpenCode, but lighter and more flexible, featuring pluggable model support for DeepSeek and beyond.

Battle-tested coding-agent skills for product, content, writing, presentations, and workflow automation.

docker region:us

transformers gguf code codeqwen chat qwen

2026 年编程导航 AI 编程实战新项目，基于 Taro + React + FastAPI + DeepSeek 的 AI 闯关学习小程序，支持一句话 / 文本主题 AI 出题、闯关答题与即时讲解、联网搜索增强、RAG 私有知识库出题、AI 生图配图、微信登录与通关复盘报告。覆盖 LangChain / LangGraph、Chroma 向量库、MySQL、JWT、腾讯云 COS、Tavily 联网搜索、阿里云百炼、微信小程序与云托管。用一套教程掌握 AI 编程全流程，从需求调研到部署上线，不到一周学完，给你的简历增加竞争力

transformers pytorch internlm feature-extraction text-generation custom_code

Persistent memory plugin for Codex. Obsidian-style knowledge base that survives across sessions

Intelligent Parsing Agent for Electrical Tender Documents – A seven-step workflow + document processing ledger, enabling multi-format uploads, automatic equipment parameter extraction, evidence review, and closed-loop manual verification. Supports hot-switching between DeepSeek and local graphics card LLM.

LLM-powered AI Data Analysis Agent with tool calling and reusable analytical skills.

Orchestrator for AI coding (claude code, cursor, codex, gemini)

The PDFChat app allows you to chat with your PDF files in natural language.

It is a personal assistant chatbot, capable to perform many tasks same as Google Assistant plus more extra features...

書籍「Amazon Bedrock 生成AIアプリ開発入門」のサンプルコード

AI-to-AI communication protocol for Claude, Gemini, and other AI assistants

A multimodal chat interface with many tools.

Syzygy-of-thoughts

Chat with SEC filings for any investment question

A Python-based application that enables dynamic conversations between multiple AI models in a graphical user interface. Originally designed for exploring liminal AI interactions, it's evolved into a flexible platform for multi-agent shenanigans.

RAGElo is a set of tools that helps you selecting the best RAG-based LLM agents by using an Elo ranker

🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.

Get 笔记 openclaw Skill

A living collection of frontier research on code agents, from the code we build to the worlds we act in.

Find and govern AI attack surfaces in application code, at PR time and inside your AI coding tool (MCP server, Claude Code hook). Free, OSS, runs offline.

transformers safetensors qwen2_moe text-generation chat conversational

An improved multi-agent AIOps and RAG platform for OnCall troubleshooting, featuring LangGraph-based diagnosis workflows, Milvus vector search, MCP tool integration, Prometheus alert knowledge from awesome-prometheus-alerts, and sanitized configuration for safe public deployment.

The best RAG interface yet.