khursani8

Sani's starred repositories

dataease

🔥 人人可用的开源 BI 工具，Tableau、帆软的开源替代。

Language:JavaGPL-3.017397 161 4879

gateway

A Blazing Fast AI Gateway with integrated Guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Language:TypeScriptMIT5913 34 303

CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Language:PythonApache-2.04840 50 355

SuperPrompt

SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

4184 66 15

maturin

Build and publish crates with pyo3, cffi and uniffi bindings as well as rust binaries as python packages

Language:RustApache-2.03709 29 609

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

Language:PythonApache-2.02825 25 170

mini-omni

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

Language:PythonMIT2507 91 68

LOMO

LOMO: LOw-Memory Optimization

Language:PythonMIT974 13 70

claude-prompt-generator

Language:PythonApache-2.0968 480

rerankers

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

Language:PythonApache-2.0850 8 15

Easy-Voice-Toolkit

可本地部署的AI语音工具箱 | A user-friendly audio toolkit for voice recognition, voice transcription, voice conversion etc.

Language:PythonGPL-3.0620 3 5

voicechat2

Local SRT/LLM/TTS Voicechat

Language:PythonApache-2.0475 5 15

cloudflare-rag

Fullstack "Chat with your PDFs" RAG (Retrieval Augmented Generation) app built fully on Cloudflare

Language:TypeScript42400

sio

Go implementation of the Data At Rest Encryption (DARE) format.

Language:GoApache-2.0360 320

ASTRA.ai

TEN(theten.ai) agent is an open-source multimodal AI agent that can speak, see, and access a knowledge base(RAG).

Language:PythonApache-2.0343 15 83

llm-decontaminator

Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"

Language:PythonApache-2.0266 3 6

hf-llm.rs

Language:RustMIT191 5 4

seed-vc

zero-shot voice conversion with in context learning

Language:PythonGPL-3.017600

CrisperWhisper

Verbatim Automatic Speech Recognition with improved word-level timestamps and filler detection

Language:PythonNOASSERTION16800

Ditto

A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".

Language:Jupyter NotebookMIT153 9 9