- via lactea
-
04:29
(UTC +01:00) - dex.moe
- https://orcid.org/0000-0002-5128-5574
- in/dex-xu
- @dexmoe
Highlights
Lists (6)
Sort Name ascending (A-Z)
Stars
- All languages
- ActionScript
- Astro
- Batchfile
- Blade
- C
- C#
- C++
- CMake
- CSS
- Clojure
- Cuda
- Cython
- Dart
- Dockerfile
- Elixir
- Emacs Lisp
- Fortran
- Go
- Groovy
- HTML
- Haskell
- Java
- JavaScript
- Jinja
- Julia
- Jupyter Notebook
- Kotlin
- Lua
- MATLAB
- MDX
- Makefile
- Nim
- Nunjucks
- OCaml
- PHP
- Perl
- Processing
- Pug
- Python
- R
- Ren'Py
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Solidity
- Swift
- SystemVerilog
- Tcl
- TeX
- TypeScript
- Vim Script
- Vue
- WebAssembly
- Wikitext
Train the smallest LM you can that fits in 16MB. Best model wins!
Stoneford — the starter world for WorldLines. 10-agent orchestrator · d20 TRPG · runs standalone in WorldLines or drop-in with Claude Code.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Fast, accurate & comprehensive text measurement & layout
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
An experiment in turning years of machine learning experience into a research loop that could run on its own
Repo for "Adaptation of Agentic AI"
Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.
AI agents running research on single-GPU nanochat training automatically
GPU programming related news and material links
Create beautiful slides on the web using a coding agent's frontend skills
Track AI coding agent usage across Claude Code, Codex, and OpenCode — SVG charts for your GitHub profile
skill to create best prompts for generating videos with seedance2.0
MLEvolve is an open-source autonomous system for end-to-end machine learning algorithm design and optimization powered by progressive search and experience-driven memory.
ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.
[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
The most powerful MCP Slack Server with no permission requirements, Apps support, GovSlack, DMs, Group DMs and smart history fetch logic.
[ICLR 2026] Official Implementation of ProxyThinker: Test-Time Guidance through Small Visual Reasoners.
Telegram bot that bridges messages to Claude Code
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
AI coding assistant skill for automated code optimization with Weco.
Algorithm powering the For You feed on X
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chem…
LoongFlow: A Thinking & Learning Framework for Expert-Grade AI Agents.
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
Fast, universal domain availability checker - 1,200+ TLDs, pattern generation, RDAP with WHOIS fallback. CLI + Rust library + MCP server for AI agents.