Python agents

The autonomous discovery engine for AI coding tools. Indexes skills, plugins, MCP servers, agents, and integrations across Claude Code, Codex, Gemini CLI, and more.

OhMyPi (OMP) Agent Framework Spec-Driven Development infrastructure for Oh My Pi. Skills transform artifacts through a deterministic engineering workflow.

MCP server that extracts, chunks, embeds and stores PDF documents into a pgvector database for semantic search and RAG pipelines.

AI agent skills for claude code that generates comprehensive wiki-style markdown document for codebase, with CI/CD-ready incremental updates

Self-contained ARM64 Android app for running Hermes Agent locally with a mobile interface.

A coding agent built on LLM

Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek models in Codex CLI or any OpenAI client. Cross-platform, single-file, no auth changes.

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

BOSS 直聘 HR 智能体工具箱

Open-source desktop AI agent with an embedded browser runtime and human-in-the-loop control.

transformers gguf mistral code text-generation-inference text-generation

AI research workspace with two modes — DeepSearch turns a query into a cited web report in ~2 min; Research Mode runs a 25-agent pipeline that writes a full academic paper (PRISMA diagram, verified citations, PDF/DOCX export). 4 human-in-the-loop checkpoints. Built with LangGraph, FastAPI, and any OpenAI-compatible LLM.

Codebase-level adversarial review by a panel of frontier models. A Claude Code skill that runs every file through DeepSeek + Gemini + Kimi + MiniMax in sequence, then has Claude verify the findings against the actual source.

AI writing assistant built with FastAPI, LangChain, LangGraph, RAG, and OpenAI-compatible APIs for style extraction, rewriting, review, and cover generation

鸣弦/MIXIA Framework (formerly persona-vault) — 人与AI协作的团队操作系统

GPT-2 based neural conversational model with TensorFlow.

A ChatGPT powered chatbot for the AWS Well-Architected Framework

可视化网页工作台 + 本机连接器：把 PDF、Word、PPT、URL 一键整理成本地 AI 助手可接手的 PPT 项目包，输出可编辑 PPTX 或杂志风网页演示

augini: AI-Powered Tabular Data Assistant

Retrieval Augmented Generation for youtube videos with a BRAD agent

Using Hugging Face Hub Embeddings with Langchain document loaders to do some query answering

Open Source Python SDK for AI Agents Identity

Probably one of the lightest native RAG + Agent apps out there，experience the power of Agent-powered models and Agent-driven knowledge bases in one click, without complex configuration.

Welcome to FluidAPI, it's a framework that allows you to interact with APIs using natural language. No more JSON, headers, or complex formats simply describe your request in plain English, and FluidAPI will do the rest.

Echo is your personal AI assistant on Telegram, designed to enhance your productivity by providing a seamless needs. With MongoDB integration, your reminders, schedules, broadcast, APIs and others persist even if the bot restarts, ensuring you never miss a moment.

A chatbot with many OpenAI LLM's including GPT-4, GPT-4o, GPT-4-o3, GPT-5, and more. Perfect for people annoyed with the new ChatGPT and the lack of models to choose from.

Instruction/chat prompts creation library for text generation LLMs. It supports local and Hugging Face models.

YouTube Live Stream Chat Bot implemented using YouTube Data & Live Streaming API in Python

A pytorch implementation for the MMI-anti model

A chatbot based on OpenAI, suitable for enterprise privatized data fine-tuning. It can answer various questions related to enterprise products raised by users.

kbqa task-oriented qa seq2seq ir neo4j jena seq2seq tf chatbot chat

AI assistant, based on the GPT-3.5 model by OpenAI, designed to enhance your proficiency in writing research papers. Allows you to adapt your content to academic standards, transform bullet points into eloquent text, or enhance the quality of your writing through error detection.

PerfGPT helps you to analyze your performance test results using OpenAI.

ChatBilibili .基于Fastapi 和ChatGPT Embedding ，实时生成视频概要，检索上下文视频提问/聊天

Freeway is meant to provide a simple, flexible, extensible and lightweight standard for managing prompt templates, database query templates, user input points, and LLM-backed system diagrams.

The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model reranking, and 77.7% LoCoMo accuracy. MCP native, REST API, self-hosted.

The AI and Human powered ticket system to manage your AI based code generation with tickets

This project implements a demonstrator agent that compares the Cache-Augmented Generation (CAG) Framework with traditional Retrieval-Augmented Generation (RAG) using various LLMs.

Unofficial, Google‑free reimplementation of MLE‑STAR: a lightweight, local‑friendly multi‑agent ML engineering pipeline that uses OpenAI‑compatible LLMs (OpenRouter/Ollama) and DuckDuckGo search to generate, debug, refine, ensemble, and submit Kaggle‑ready solutions—AutoML for tabular tasks with code generation and iterative refinement.

Autonomous Intelligence is a framework for building collaborative, intelligent multi agent AI systems. The framework provides a robust infrastructure for creating and managing multiple AI agents, and enables developers and organizations to build, deploy, and optimize AI agents that work well in dynamic, complex environments.

MAS (Multi Agent System) Coordindator to Work with General-purspose and Users Management Agents

Multi-Agent Combinatorial Path Finding (MCPF)

A collection of environments and reference agents for planning and reinforcement learning research in partially observable, multi-agent environments.

Multi Agent Reinforcement Learning for Dense Path Planning

A multi-agent RAG (Retrieval-Augmented Generation) system powered by Google Gemini, Docling, and LangGraph for intelligent document Q&A with built-in fact-checking and hallucination prevention.

This repository presents a multi-agent reinforcement learning approach for energy-efficient collaborative control of base stations in 5G networks.

Code for "ALMA: Hierarchical Learning for Composite Multi-Agent Tasks" NeurIPS 2022

这是款基于 OpenRouter API 的 Dify 文生图插件，主打高质量 AI 图像生成，支持 Google Gemini、OpenAI DALL-E、Anthropic Claude 等模型，含免费 Gemini 供测试轻用，付费模型（如 DALL-E 3、Claude 3.5 Sonnet）满足专业需求，还具备图转图、中英双语、实时进度反馈及完善错误处理。可在 Agent 和 chatflow 中使用. DSL可以从这个项目 https://github.com/wwwzhouhui/dify-for-dsl获取

5th place solution repository for Kaggle CSIRO Image2Biomass, including the experiment workflow used with Claude Code and Codex.

MCP server for xAI's Grok API with agentic tool calling, image and video generation, vision, and file support.

An agent-based modeling framework for Python with a shallow learning curve and powerful visualization capabilities.

Unify AI agent rules across tools like Cursor, Copilot, Devin, and Cline. One source, synced everywhere.

the small distributed language model toolkit; fine-tune state-of-the-art LLMs anywhere, rapidly

Ragbot.AI is an augmented brain assistant developed by Rajiv Pant

usdchat is a conversational bot that lets you interact with USD Stage using natural language.

:spider: Mutator-free management, statistics, and in-game bot for ranked Killing Floor 2 servers

AI-powered personalized IELTS corpus distillation — install-only skill (zero-backend Agent loop) + runnable backend with QMD-RAG. 7-stage pipeline producing schema-validated corpus.json & static profile site.

Simple Maya tool that utilizes open AI to perform basic tasks based on descriptive instructions.

Local-first cognitive daemon for automated vault management Markdown. Semantic indexing, auto-tagging, and connection discovery using LLMs and vector search.

Autonomous AI agent for BitGN PAC1 Challenge — ~86% score with 12 hot-reloadable skills, live dashboard, and self-correcting classification

Multi-agent orchestration framework for AI applications - build, deploy, and manage AI agents across the full lifecycle with Forge, Conveyor, Shield, and Watchtower modules

Let your memories live forever by passing your knowledge to the next generation with SelfMemory.

🤵 AIfred-Intelligence — self-hosted Multi-Agent Assistant with Debate Modes (Symposion/Tribunal), Voice (STT + Streaming-TTS), RAG with Long-Term Memory, Web Research and Tool-Calling. Reachable via Web-UI or Telegram/Discord/Email/EPIM. Multi-Backend: llama-swap, Ollama, vLLM, TabbyAPI.

Scalable Qdrant vector database cluster with Docker Compose, monitoring, and comprehensive documentation for high-performance similarity search applications.

Create and interact with Knowledge Graphs using Generative AI

画像、オーディオ、テキスト、LLM/VLM のマルチモーダル パイプラインを実験するためのノードエディター（Node-based editor to compose and experiment with multimodal pipelines across image, audio, text, and LLM/VLM）

TiDB AI SDK: Unified Multi-Modal Data Platform for AI Apps & Agents

这是一个基于AgentScope框架的AI助手应用，支持自动技能发现、智能任务匹配和终端交互，兼容claudecode的skill文件。

Local FAISS vector store as an MCP server – Agent Memory, drop-in local semantic search for Claude / Copilot / Agents.

Metadata encoding and extraction for AI-generated content

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution [ICSE 2026]

This project leverages Claude Code’s powerful agent capabilities to build a multi-agent system that simulates the real-world collaboration process of a data science team. Through the division of labor among AI agents with different areas of expertise, the system delivers a complete end-to-end data science solution—from raw data to the final analysi

This agent answers questions by reading multiple docs provided by the user

VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation

Knowledge graph + MCP tool server for LLM agents with hybrid retrieval, live DB sync, Korean FTS, and memory feedback.

AI-powered SOC for OT/ICS networks — 6 autonomous agents, MITRE ATT&CK mapping, Suricata/Zeek ingestion, human-in-the-loop response, 330+ tests. Open-source alternative to Claroty/Dragos for SMBs.

instagram

A powerful PowerPoint translation tool that preserves all formatting while translating content using the Deepseek API. This tool maintains fonts, colors, layouts, and other styling elements while providing accurate translations between languages.

🚀 First multimodal AI-powered visual testing plugin for Claude Code. AI that can SEE your UI! 10x faster frontend development with closed-loop testing, browser automation, and Claude 4.5 Sonnet vision.

[AAAI'26, Oral] Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG

Multi-Agent Solutions (Deep Research and more)

Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers

Official implementation of the paper "Learning and Planning Multi-Agent Tasks via a MoE-based World Model"

Multi-agent orchestration framework powered by Pydantic AI. Build complex agent collaborations with clean, declarative code, automatic topology validation, built-in execution tracking, and full control over agent interactions, observability included.

VOXRAD is a voice transcription application for radiologists leveraging locally deployed ASR and LLM models.

A Twitter/X scraper built with Playwright for browser automation and OpenAI GPT-4 for AI-powered tweet analysis. Features timeline scraping, historical search, keyword search, checkpoint/resume, proxy support, and comprehensive data extraction.

Excel MCP Server - Manipulate Excel files without Microsoft Excel. Model Context Protocol for XLSX, XLSM with Claude AI integration

A thin cython wrapper around llama.cpp, whisper.cpp and stable-diffusion.cpp

Project setup generator for Claude Code. Pick framework + workflow, get a fully configured project - CLAUDE.md, hooks, agents, commands, skills, plugins, memory.

🧠 Claude Code 三层记忆系统 | 结构化存储 + 生命周期管理 + Git追踪 | 官方Auto Memory的管理层 | 一行命令安装 零依赖

Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Reinforcement Learning

AI-powered multi-agent platform for evidence-driven scenario simulation and strategic decision-making. Supports corporate \& military domains with debate protocol.

Qworld: Question-Specific Evaluation Criteria for LLMs

Minimal runtime for Recursive Language Models (RLMs) inspired by the MIT CSAIL paper "Recursive Language Models".

基于 LLM agent 的党政机关公文自动排版工具

21 runnable reference implementations of agent design patterns, including routing, planning, RAG, tool use, reflection, and multi-agent workflows.

Open-source PDF-to-Markdown post-processor with footnotes, LaTeX normalization, figure links, and YAML metadata. Supports Marker, MinerU, PyMuPDF, and Docling. Includes a self-hosted web UI.

Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and RAM usage by 3x.