WeChat/微信 local chat history MCP server for macOS agents. Read messages, contacts, media, favorites, transfers, red packets, Moments and full-text search from local WeChat 4.x data.

Sub2API gateway subscription → Codex CLI / Codex App injector. macOS-native, zero-deps Python single-file. Supports codex2api.com and any self-hosted Sub2API instance.

面向中文开发者和中文用户的通用 AI agent 访问层：把网站、App、API 和重复流程路由到 agent-native CLI。

WeChat 4.x local WCDB key bootstrap CLI for wx-mcp

Local-first personal AI runtime — Telegram + WeChat transports, shared memory, skills, ops automation. The system layer your MCP servers plug into.

Read-only CLI for Xiaoyuzhou FM (小宇宙 FM): list subscriptions, browse episodes (loadMoreKey pagination + date windows), fetch official transcripts, search podcasts. Agent-friendly, composable, clean — for Claude Code, Codex, and any shell-capable agent.

No repository description provided.

babata 浏览器扩展 — all in one (sidebar chat / inline 翻译 / page agent / 媒体处理). 调研阶段.

🐹 Clean, uninstall, analyze, optimize, and monitor your Mac from the terminal.

Virtual whiteboard for sketching hand-drawn like diagrams

Native-first image generation fallback skill for Codex, Claude Code, Hermes, OpenClaw, and other agents

Hindsight: Agent Memory That Learns

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Core utilities for Python packages

Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.

Dedicated crash-recovery and read-back sandbox for the OSS Autonomy control plane

Profile README for r266-tech — building babata, a personal AI infrastructure stack (MCP servers, agent skills, macOS-native).

Lightweight coding agent that runs in your terminal

The agent that grows with you

Build resilient language agents as graphs.

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Backported and experimental type hints for Python

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Accelerate your web app development | Build fast. Run fast.

Familiar asyncio ORM for python, built with relations in mind

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

The little ASGI framework that shines. 🌟

Cross-platform lib for process and system monitoring in Python

Distributed Task Queue (development branch)

A minimal HTTP client. ⚙️

Apache Spark - A unified analytics engine for large-scale data processing

Codex 渠道切换工具，支持 macOS 上的账号和 API 渠道切换

Build Real-Time Knowledge Graphs for AI Agents

Yet another URL library

A high-throughput and memory-efficient inference and serving engine for LLMs

A programming framework for agentic AI

🙌 OpenHands: AI-Driven Development

The agent engineering platform

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

gunicorn 'Green Unicorn' is a WSGI HTTP Server for UNIX, fast clients and sleepy applications.

Bayesian Modeling and Probabilistic Programming in Python

Asynchronous HTTP client/server framework for asyncio and Python

The pytest framework makes it easy to write small tests, yet scales to support complex functional testing

Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

DuckDB is an analytical in-process SQL database management system

Write scalable load tests in plain Python 🚗💨

An ASGI web server, for Python. 🦄

Boto3, an AWS SDK for Python

Redis Python client

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

The Database Toolkit for Python

Retrying library for Python

Access large language models from the command-line

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Extra Pydantic types.

More routines for operating on iterables, beyond itertools

Data validation using Python type hints

An extremely fast Python linter and code formatter, written in Rust.

Scrapy, a fast high-level web crawling & scraping framework for Python.

Canonical source repository for PyYAML

Python composable command line interface toolkit

A simple, yet elegant, HTTP library.

:zap: A Fast, Extensible Progress Bar for Python and CLI

A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files

A lil' TOML parser

(Python Distribution) A carefully curated collection of Root Certificates for validating the trustworthiness of SSL certificates while verifying the identity of TLS hosts.

The multidict implementation

High level asynchronous concurrency and networking framework that works on top of either Trio or asyncio

Simple, powerful, and fast logging for Python.

Python Classes Without Boilerplate

Core validation logic for pydantic written in rust

DeepDiff: Deep Difference and search of any Python object/data. DeepHash: Hash of any object based on its contents. Delta: Use deltas to reconstruct objects by adding deltas together.

Utilities for interacting with PyPI

Faker is a Python package that generates fake data for you.

Python datetimes made easy

The Web framework for perfectionists with deadlines.

The Sphinx documentation generator

scikit-learn: machine learning in Python

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.