Highlights
- Pro
Stars
Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- H…
Real-time Speech-Text Foundation Model Toolkit (wip)
A throughput-oriented high-performance serving framework for LLMs
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
A Kubernetes deployable instance of GroundX for document parsing, storage, and search.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
A Conversational Speech Generation Model
No fortress, purely open ground. OpenManus is Coming.
FreeSWITCH is a Software Defined Telecom Stack enabling the digital transformation from proprietary telecom switches to a versatile software implementation that runs on any commodity hardware. From…
Cost-efficient and pluggable Infrastructure components for GenAI inference
Free, simple, and intuitive online database diagram editor and SQL generator.
This is the template I use to start new full-stack projects.
Generate fully typed Python client for any GraphQL API from schema, queries and mutations
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
Dynamic Memory Management for Serving LLMs without PagedAttention
Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs
Open Source framework for voice and multimodal conversational AI
A high-performance inference system for large language models, designed for production environments.
The fastest way to build robust AI agents
FlashInfer: Kernel Library for LLM Serving
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.