Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

A fast multimodal LLM for real-time voice

Approximation of the Claude 3 tokenizer by inspecting generation stream

A python package to analyze and compare voices with deep learning

LLM training in simple, raw C/CUDA

Improved file parsing for LLM’s

Starlark Language

AI-controlled Linux Containers

A natural language interface for computers

Supercharge Your LLM Application Evaluations 🚀

GritQL is a query language for searching, linting, and modifying code.

AICI: Prompts as (Wasm) Programs

Fine-tune LLM agents with online reinforcement learning

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Integrate cutting-edge LLM technology quickly and easily into your apps

The official API server for Exllama. OAI compatible, lightweight, and fast.

A fast inference library for running LLMs locally on modern consumer-class GPUs

Data-Driven Evaluation for LLM-Powered Applications

A hierarchical, schema-based solution for fetching and crafting data, from simple to complicated.

Library and tool for dealing with beats per second detection

Create native Java(FX) apps for desktop, mobile and embedded

REPL (read–eval–print loop) shell built on top of JavaFX and GraalVM stack, incorporating GraalJS, GraalPython, TruffleRuby and FastR

Unified framework for building enterprise RAG pipelines with small, specialized models

A terminal application to view, tail, merge, and search log files (plus JSONL).

LLRT (Low Latency Runtime) is an experimental, lightweight JavaScript runtime designed to address the growing demand for fast and efficient Serverless applications.

DSPy: The framework for programming—not prompting—language models

A programming framework for agentic AI

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

Fast RISC-V-based scripting backend for game engines