Repositories list

• LavaSR

  Public
  🌋LavaSR: Fast Speech restoration and enhancement

  Python

  •

  Apache License 2.0

  •40•0•0•0•Updated Feb 26, 2026Feb 26, 2026

• dictation_demo

  Public
  Dictation demo application

  JavaScript

  •0•1•1•0•Updated Feb 9, 2026Feb 9, 2026

• twake-drive

  Public
  Twake Drive Web App

  JavaScript

  •

  GNU Affero General Public License v3.0

  •126•0•0•0•Updated Jan 13, 2026Jan 13, 2026

• GLiNER-official-repo

  Public
  Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

  Python

  •

  Apache License 2.0

  •252•0•0•0•Updated Nov 4, 2025Nov 4, 2025

• docx-to-pdf-jwt

  Public
  A LibreOffice server wrapper that is exposed over HTTP to allow easy conversions from supported documents to PDF.

  Kotlin

  •31•1•0•0•Updated Sep 18, 2025Sep 18, 2025

• kokoro

  Public
  https://hf.co/hexgrad/Kokoro-82M

  JavaScript

  •

  Apache License 2.0

  •674•0•2•0•Updated May 3, 2025May 3, 2025

• activepieces

  Public
  Open Source AI Automation ✨ All our 280+ pieces are now available as MCP to use with LLMs

  TypeScript

  •

  Other

  •3.4k•0•0•0•Updated Apr 5, 2025Apr 5, 2025

• hallucination-leaderboard

  Public
  Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

  Python

  •

  Apache License 2.0

  •96•0•0•0•Updated Mar 26, 2025Mar 26, 2025

• directus

  Public
  The Modern Data Stack 🐰 — Directus is an instant REST+GraphQL API and intuitive no-code data collaboration app for any SQL database.

  TypeScript

  •

  Other

  •4.6k•0•0•0•Updated Mar 21, 2025Mar 21, 2025

• KBLaM

  Public
  Official Implementation of "KBLaM: Knowledge Base augmented Language Model"

  Jupyter Notebook

  •

  MIT License

  •124•0•0•0•Updated Mar 5, 2025Mar 5, 2025

• k8s-nim-operator

  Public
  An Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.

  Go

  •

  Apache License 2.0

  •42•0•0•0•Updated Feb 11, 2025Feb 11, 2025

• open-r1

  Public
  Fully open reproduction of DeepSeek-R1

  Python

  •

  Apache License 2.0

  •2.4k•0•0•0•Updated Feb 10, 2025Feb 10, 2025

• audino

  Public
  Open source audio annotation tool for humans

  JavaScript

  •

  MIT License

  •141•0•2•0•Updated Feb 10, 2025Feb 10, 2025

• smolagents

  Public
  🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

  Python

  •

  Apache License 2.0

  •2.4k•0•0•0•Updated Jan 5, 2025Jan 5, 2025

• llmops-python-package

  Public
  Kickstart your LLMOps initiative with a flexible, robust, and productive Python package.

  Python

  •

  MIT License

  •124•0•0•0•Updated Dec 10, 2024Dec 10, 2024

• audiomentations

  Public
  A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.

  Python

  •

  MIT License

  •211•0•0•0•Updated Dec 9, 2024Dec 9, 2024

• TokenFormer

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

  Python

  •

  Apache License 2.0

  •43•0•1•0•Updated Nov 12, 2024Nov 12, 2024

• Theraxus-speech-to-speech

  Public
  Theraxus AI: A modular conversational AI platform ⚙️ blending STT 🎙️, TTS 🗣️, and RAG 📚 for seamless, context-aware dialogues and human-like interactions 🤖💬

  Python

  •

  Apache License 2.0

  •3•0•0•0•Updated Nov 9, 2024Nov 9, 2024

• OuteTTS

  Public
  Python

  •

  Apache License 2.0

  •113•0•0•0•Updated Nov 5, 2024Nov 5, 2024

• Medical-Graph-RAG

  Public
  Medical Graph RAG: Graph RAG for the Medical Data

  Python

  •

  MIT License

  •127•0•0•0•Updated Oct 25, 2024Oct 25, 2024

• BitNet-1bit-inference-for-LLM

  Public
  Official inference framework for 1-bit LLMs

  C++

  •

  MIT License

  •2.4k•0•0•0•Updated Oct 18, 2024Oct 18, 2024

• swarm-Multi-agent-orchestration

  Public
  Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

  Python

  •

  MIT License

  •2.2k•0•0•0•Updated Oct 12, 2024Oct 12, 2024

• fstalign

  Public
  An efficient OpenFST-based tool for calculating WER and aligning two transcript sequences.

  C++

  •

  Apache License 2.0

  •11•0•0•0•Updated Sep 24, 2024Sep 24, 2024

• moshi

  Public
  Python

  •

  Apache License 2.0

  •906•0•0•0•Updated Sep 18, 2024Sep 18, 2024

• GOT-OCR2.0

  Public
  Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

  Python

  •701•0•0•0•Updated Sep 11, 2024Sep 11, 2024

• Nvidia-NeMo

  Public template
  A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognitio…

  Python

  •

  Apache License 2.0

  •3.4k•0•0•0•Updated Sep 5, 2024Sep 5, 2024

• directus-extension-disable-listing

  Public
  Directus custom extension to disable listing

  TypeScript

  •

  GNU General Public License v3.0

  •3•0•0•0•Updated Aug 31, 2024Aug 31, 2024

• graphrag

  Public
  A modular graph-based Retrieval-Augmented Generation (RAG) system

  Python

  •

  MIT License

  •3.3k•0•0•0•Updated Aug 26, 2024Aug 26, 2024

• speech-to-speech

  Public template
  Speech To Speech: an effort for an open-sourced and modular GPT4-o

  Python

  •

  Apache License 2.0

  •508•0•0•0•Updated Aug 26, 2024Aug 26, 2024

• directus-extension-flow-manager

  Public
  A directus custom module extension for managing directus flow includes backup/restore, duplication and grouping the flow.

  Vue

  •

  GNU General Public License v3.0

  •12•0•0•0•Updated Aug 25, 2024Aug 25, 2024