LEAKED SYSTEM PROMPTS FOR CHATGPT, GEMINI, GROK, CLAUDE, PERPLEXITY, CURSOR, DEVIN, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

AI chat assistant for Obsidian with contextual awareness, smart writing assistance, and one-click edits. Features vault-aware conversations, semantic search, and local model support.

Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.

The official Meta Llama 3 GitHub site

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Math OCR model that outputs LaTeX and markdown

Build and iterate on your UI 10x faster with AI - right from your own IDE ☕️

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Draw a ui and make it real

A programming framework for agentic AI

Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.

Images to inference with no labeling (use foundation models to train supervised models).

Code/Data for the paper: "LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding"

Tensor library for machine learning

An Open-Ended Embodied Agent with Large Language Models

Use your own AI models on the web

Experiments with applying Fourier transofrms to various plane-filling curves and patterns

Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wikitext-103 on a single A100 in <100 seconds. Scales to large…

Project Euler GPT Resolver

The definitive Web UI for local AI, with powerful features and easy setup.

Port of OpenAI's Whisper model in C/C++

AI sends pull requests for features you request in natural language

Let us control diffusion models!

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

🧀 Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".

Train transformer language models with reinforcement learning.