- London
Stars
- All languages
- ActionScript
- Arduino
- Assembly
- Awk
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Common Lisp
- Crystal
- Dockerfile
- Elm
- Emacs Lisp
- Erlang
- Go
- Gosu
- Groovy
- HTML
- Haskell
- Idris
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- LiveScript
- Lua
- MDX
- Makefile
- Markdown
- Max
- MoonScript
- Mustache
- OCaml
- Objective-C
- Oz
- PHP
- Perl
- Prolog
- PureScript
- Python
- R
- Reason
- Roff
- Ruby
- Rust
- Scala
- Shell
- TLA
- TeX
- TypeScript
- Zig
An MMO game written in Erlang (+ PostgreSQL) + Zig (+ Raylib)
UNMAINTAINED - John Hoffman's fork of the original bittorrent
AWS AI Stack – A ready-to-use, full-stack boilerplate project for building serverless AI applications on AWS
An open-source RAG-based tool for chatting with your documents.
This repository implements teleoperation of the Unitree humanoid robot using XR Devices.
The unofficial DSPy framework. Build LLM powered Agents and "Agentic workflows" based on the Stanford DSP paper.
the answer is no
[ICLR24] AutoVP: An Automated Visual Prompting Framework and Benchmark
Template for setting up a new HONC stack project
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
A FOSS release of source code of the unreleased version 0.3 of Songs of the Eons
LiveBench: A Challenging, Contamination-Free LLM Benchmark
Source code for the Public Whip website
🔩 Run and scale realtime applications with Rivet Actors.
🧩 The only backend your game needs. Powered by Rivet.
DocLLM: A layout-aware generative language model for multimodal document understanding
Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.
prompt2model - Generate Deployable Models from Natural Language Instructions
Optimization-Based Rule Learning for Classification
Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM
CaptureFlow - LLM-powered code maintenance that delivers reliable results.
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…