Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Orchestrator to spin up MC server, connect mineflayer bot, generate + execute build commands and export the structure

command loom interface

Code for "Counterfactual Token Generation in Large Language Models", Arxiv 2024.

A language model programming library.

AWS AI Stack – A ready-to-use, full-stack boilerplate project for building serverless AI applications on AWS

High-resolution models for human tasks.

A Loom implementation in Obsidian

Start building LLM-empowered multi-agent applications in an easier way.

Open-source Next.js template for building apps that are fully generated by AI. By E2B.

Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.

Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

Flashbots MEV-Boost Block Builder

turnkey self-hosted offline transcription and diarization service with llm summary

A library for advanced large language model reasoning

Retrieval-Augmented Theorem Provers for Lean

LLMs as Copilots for Theorem Proving in Lean

Supercompat allows you to use any AI provider like Anthropic, Groq or Mistral with OpenAI-compatible Assistants API.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Experts.js is the easiest way to create and deploy OpenAI's Assistants and link them together as Tools to create advanced Multi AI Agent Systems with expanded memory and attention to detail.

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

Verified Rust for low-level systems code

(Advanced) Applied Econometrics

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

An intuitive LLM prompting framework for multifunctional agents, by explicitly constructing a complex "thought process" from simple natural language prompts.

Marsha is a functional, higher-level, English-based programming language that gets compiled into tested Python software by an LLM

Ancillary open source software to support confidential computing on NVIDIA GPUs