- Hangzhou, China
- https://rustc.cloud
- @ycjcl
Lists (3)
Sort Name ascending (A-Z)
- All languages
- ActionScript
- Assembly
- Bikeshed
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Cython
- Dart
- Dockerfile
- EJS
- Elixir
- Emacs Lisp
- F#
- Go
- HTML
- Hack
- Haskell
- JSON
- Java
- JavaScript
- Jinja
- Jsonnet
- Jupyter Notebook
- Kotlin
- Less
- Lua
- MDX
- Makefile
- Markdown
- Mustache
- Nix
- Nunjucks
- OCaml
- Objective-C
- Objective-C++
- PHP
- Perl
- PlantUML
- Python
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Starlark
- Svelte
- Swift
- TeX
- TypeScript
- Vim Script
- Vue
- WebAssembly
- YAML
- Yacc
- Zig
Starred repositories
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
LLM-in-Sandbox Elicits General Agentic Intelligence
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Algorithm powering the For You feed on X
☄🌌️ The minimal, blazing-fast, and infinitely customizable prompt for any shell!
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Browser automation CLI for AI agents
Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.
Create mind maps from your obsidian markdown files
Fast, light, simple Docker containers & Linux machines
AndroidWorld is an environment and benchmark for autonomous agents
MAI-UI: Real-World Centric Foundation GUI Agents ranging from 2B to 235B
CXLMemSim: A pure software simulated CXL.mem for performance characterization
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
A toolkit for developing and comparing reinforcement learning algorithms.
OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for scenarios like Coding Agents, GUI Agent…
NVSentinel is a cross-platform fault remediation service designed to rapidly remediate runtime node-level issues in GPU-accelerated computing environments
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Information hub for our project training the largest possible historical LLMs.
GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.
Kata Containers is an open source project and community working to build a standard implementation of lightweight Virtual Machines (VMs) that feel and perform like containers, but provide the workl…