# janhq/cortex.cpp

Local AI API Platform

Repository: https://github.com/janhq/cortex.cpp
Canonical: https://ross.abutalabs.com/products/cortexcpp
Homepage: https://cortex.so
Language: C++
License: Apache-2.0
License Family: permissive
Topics: gguf, llamacpp, onnx, onnxruntime
Archived: true
Last push: 2025-07-04T07:38:05+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 30, release rhythm 40, longevity 77
- inputs: {"age_days": 1087, "days_push": 425, "days_rel": 444, "gap_med": 13, "n_releases_24m": 14}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2752, forks 173 (observed 2026-08-28T04:07:18.097861+00:00)

## What it is
Cortex.cpp is a C++ local AI platform that runs GGUF (llama.cpp) and ONNX models on your own machine, exposing an OpenAI-compatible HTTP API plus a CLI for pulling and running models. The repository has been archived and development has moved to menloresearch/llama.cpp.

## Use cases
- run local llm with openai-compatible api
- self-host chat completions endpoint on my machine
- download and run gguf models from huggingface via cli
- replace openai api with local inference server
- serve llama models offline for private apps
- manage local model downloads and running processes

## When to choose
- you need an OpenAI-compatible local inference server and are fine pinning an older release
- you want a simple CLI to pull and run GGUF/ONNX models locally

## When to avoid
- you want active maintenance or new features - the repo is archived and development moved to menloresearch/llama.cpp
- you need a polished desktop chat UI - use Jan instead
- you need multi-GPU or production-scale serving - consider vLLM or llama.cpp directly

## Facets
- artifact type: service
- maturity: abandoned
- function: llm-inference, http-server, cli, api-framework
- domain: large-language-models, artificial-intelligence, self-hosted, developer-tools
- platform: windows, cli, self-hosted, cpp
- tags: gguf, llamacpp, onnx, openai-compatible-api, local-llm, archived, macos, linux

## Member repositories
- janhq/cortex.cpp (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:18.097861+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:18:55.119957+00:00, confidence not recorded.
  - readme: https://github.com/janhq/cortex.cpp (fetched 2026-08-28T04:07:18.097861+00:00, sha 26fb4a12a30d)
  - homepage: https://cortex.so (fetched 2026-08-29T09:56:56.447237+00:00, sha 60545b206fd5)
  - site_page: https://www.jan.ai/docs/desktop/quickstart (fetched 2026-08-29T09:56:56.449788+00:00, sha 2373afba1aad)
  - site_page: https://www.jan.ai/docs/agent/quickstart (fetched 2026-08-29T09:56:56.451955+00:00, sha 21e9e948641a)
  - site_page: https://www.jan.ai/docs (fetched 2026-08-29T09:56:56.454102+00:00, sha 973ae11d9859)
  - site_page: https://www.jan.ai/docs/agent (fetched 2026-08-29T09:56:56.459061+00:00, sha 31ff50e76cdd)
  - site_page: https://www.jan.ai/docs/desktop/api-server (fetched 2026-08-29T09:56:56.460748+00:00, sha 5d612eb26595)
  - site_page: https://www.jan.ai/changelog (fetched 2026-08-29T09:56:56.455755+00:00, sha 11d532705d56)
  - site_page: https://www.jan.ai/handbook/who/who-we-are (fetched 2026-08-29T09:56:56.457523+00:00, sha b9de53bc3821)
- Data as of 2026-08-30T08:39:29.467469+00:00.