🏠
Highlights
- Pro
Starred repositories
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
Claude Code skill that removes signs of AI-generated writing from text
My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接
A CLI-based, flat-file issue tracker for humans and robots. 🤖
This repository contains my personal configuration settings for Claude Code, Anthropic's official CLI tool for coding.
Integrate the DeepSeek API into popular software
Cross-platform, extensible terminal/browser for AI management
Model Context Protocol Servers
aider is AI pair programming in your terminal
MinimalChat is a lightweight, open-source chat application that allows you to interact with various large language models.
SGLang is a high-performance serving framework for large language models and multimodal models.
Geospatial Data Science with Julia
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
TorchCFM: a Conditional Flow Matching library
AI wearables. Put it on, speak, transcribe, automatically
Implementation of Nougat Neural Optical Understanding for Academic Documents
hotpdf is a fast PDF parsing library to extract text and find text within PDF documents built on top of pdfminer.six
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A Next-Generation Training Engine Built for Ultra-Large MoE Models
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with…
Stanford NLP Python library for Representation Finetuning (ReFT)
Solve puzzles. Improve your pytorch.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
Code for "Learning to summarize from human feedback"