Skip to content

@janhq Jan

Change the repository type filter

All

    Repositories list

    35 repositories

    • jan

      Public
      Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)
      electronself-hostedgptllamacpplocalaillama2
      TypeScript
      •
      GNU Affero General Public License v3.0
      •1.4k•23k•161•8•Updated Nov 8, 2024Nov 8, 2024

    • cortex.cpp

      Public
      Local AI API Platform
      onnxonnxruntimellamacppgguftensorrt-llm
      C++
      •
      Apache License 2.0
      •116•2.1k•107•7•Updated Nov 8, 2024Nov 8, 2024

    • cortex.llamacpp

      Public
      cortex.llamacpp is a high-efficiency C++ inference engine for edge computing. It is a dynamic library that can be loaded by any server at runtime.
      C++
      •
      GNU Affero General Public License v3.0
      •3•19•2•3•Updated Nov 8, 2024Nov 8, 2024

    • models

      Public
      Models support in Jan and Cortex
      Python
      •
      MIT License
      •2•5•15•0•Updated Nov 1, 2024Nov 1, 2024

    • remote-apis

      Public
      For Remote API issues
      0•0•0•0•Updated Oct 31, 2024Oct 31, 2024

    • cortex.python

      Public
      C++ code that run Python embedding
      C++
      •
      GNU Affero General Public License v3.0
      •0•4•1•1•Updated Oct 17, 2024Oct 17, 2024

    • docs

      Public archive
      Jan.ai Website & Documentation
      websitedocumentationself-hostedjanapi-referencelocalai
      MDX
      •8•21•50•1•Updated Oct 14, 2024Oct 14, 2024

    • cortex.so

      Public archive
      TypeScript
      •2•4•3•2•Updated Oct 9, 2024Oct 9, 2024

    • cortex.tensorrt-llm

      Public
      Cortex.Tensorrt-LLM is a C++ inference library that can be loaded by any server at runtime. It submodules NVIDIA’s TensorRT-LLM for GPU accelerated inference on NVIDIA's GPUs.
      nvidiajantensorrtllmtensorrt-llm
      C++
      •
      Apache License 2.0
      •978•39•7•3•Updated Sep 26, 2024Sep 26, 2024

    • winget-pkgs

      Public
      0•0•0•0•Updated Aug 23, 2024Aug 23, 2024

    • homebrew-tap

      Public
      Ruby
      •0•0•0•0•Updated Aug 22, 2024Aug 22, 2024

    • ppa

      Public
      0•0•0•0•Updated Aug 21, 2024Aug 21, 2024

    • tokenizer.cpp

      Public
      C++
      •
      GNU Affero General Public License v3.0
      •0•2•2•0•Updated Aug 13, 2024Aug 13, 2024

    • cortex.onnx

      Public
      C++
      •0•6•2•1•Updated Aug 12, 2024Aug 12, 2024

    • cortex.js

      Public
      The official Node.js / Typescript library for the OpenAI API
      TypeScript
      •
      Apache License 2.0
      •862•3•0•19•Updated Aug 9, 2024Aug 9, 2024

    • cortex.audio

      Public
      C++
      •0•0•0•0•Updated Jul 9, 2024Jul 9, 2024

    • homebrew-cortexso

      Public
      Ruby
      •0•1•0•0•Updated Jul 5, 2024Jul 5, 2024

    • cortex.py

      Public
      The official Python library for the OpenAI API
      Python
      •
      Apache License 2.0
      •3.2k•2•0•1•Updated May 20, 2024May 20, 2024

    • pymaker

      Public archive
      Make the py
      0•0•0•0•Updated Apr 9, 2024Apr 9, 2024

    • tensorrtllm_backend

      Public archive
      The Triton TensorRT-LLM Backend
      Python
      •
      Apache License 2.0
      •104•0•0•0•Updated Mar 19, 2024Mar 19, 2024

    • triton_tensorrt_llm

      Public archive
      Shell
      •0•1•0•0•Updated Mar 15, 2024Mar 15, 2024

    • openai_trtllm

      Public archive
      OpenAI compatible API for TensorRT LLM triton backend
      Rust
      •
      MIT License
      •25•0•0•0•Updated Mar 15, 2024Mar 15, 2024

    • trt-llm-as-openai-windows

      Public archive
      This reference can be used with any existing OpenAI integrated apps to run with TRT-LLM inference locally on GeForce GPU on Windows instead of cloud.
      Python
      •
      Other
      •12•0•0•0•Updated Mar 8, 2024Mar 8, 2024

    • architecture

      Public archive
      1•1•0•0•Updated Feb 28, 2024Feb 28, 2024

    • llama.cpp-avx-vnni

      Public archive
      Port of Facebook's LLaMA model in C/C++
      C++
      •
      MIT License
      •9.7k•0•0•0•Updated Feb 19, 2024Feb 19, 2024

    • infinity

      Public archive
      The AI-native database built for LLM applications, providing incredibly fast vector and full-text search
      C++
      •
      Apache License 2.0
      •273•0•0•0•Updated Feb 19, 2024Feb 19, 2024

    • langchainjs

      Public archive
      TypeScript
      •
      MIT License
      •2.2k•0•0•0•Updated Feb 19, 2024Feb 19, 2024

    • model-converter

      Public archive
      Python
      •5•20•2•0•Updated Dec 14, 2023Dec 14, 2023

    • node-nitro

      Public
      JavaScript
      •
      GNU Affero General Public License v3.0
      •0•1•0•0•Updated Nov 29, 2023Nov 29, 2023

    • py-nitro

      Public
      0•0•0•0•Updated Nov 16, 2023Nov 16, 2023