The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
- claude-code
- codex
- data-processing
- harness-engineering
108,094 visible repositories in the index
865–888 of 3,039 · Most stars
The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
🐳 Docker Image of NetBox
🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code
Social reading and reviewing, decentralized with ActivityPub
Minimal Claude Code alternative. Single Python file, zero dependencies, ~250 lines.
Syncs YouTube channels and playlists to a locally hosted media server
A high-performance ASCII video rendering engine featuring real-time WebSocket binary streaming and an isolated compiler for serverless static generation. Built for low-latency 30 FPS playback on HTML5 Canvas.
🌏 Live visualization of all the pokemon in your area... and more!
A full modbus protocol written in python
Social auth made simple
Local-first WeChat intelligence system with a read-only CLI, Codex skills, searchable chat history, daily briefings, follow-ups and opportunity tracking.
Misago is fully featured modern forum application that is fast, scalable and responsive.
Python tools for 3D face: 3DMM, Mesh processing(transform, camera, light, render), 3D face representations.
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
OCR powered screen-capture tool to capture information instead of images
A CLI tool to query your local WeChat data — chat history, contacts, sessions, favorites, and more. Designed for LLM integration.
Interactive Redis: A Terminal Client for Redis with AutoCompletion and Syntax Highlighting.
💰 Cryptocurrency Trading Bot for Binance (Experimental)
Kaggle Python docker image
Offline multi-agent simulation & prediction engine. English fork of MiroFish with Neo4j + Ollama local stack.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.
Free Currency Exchange Rates API with 200+ Currencies & No Rate Limits
Use a docx as a jinja2 template