LL

Llama Stack

Composable API server for building generative AI applications

Self-Hosted AI ★ 8.4k stars Medium setup MIT

Llama Stack from Meta defines and implements a set of standardized APIs for inference, RAG, agents, safety and evaluation, with multiple provider backends. It can be self-hosted as a unified server for building local generative AI applications.

Key features

  • Standardized AI APIs
  • Pluggable provider backends
  • Agents and RAG support
  • Self-hostable server

Strengths

  • Released under the MIT license
  • First-class Docker support for quick deployment
  • Mature project with 8.4k GitHub stars
  • Written in Python

Is Llama Stack secure?

No known vulnerabilities affect Llama Stack's latest release (v1.5.0). OSV.dev lists 3 past advisories for the project; none of them applies to this release. No known vulnerabilities is not proof of security: it means none have been publicly catalogued.

  • Most recent fixed advisory CVE-2026-85666, published 2026-09-04 (40 days ago)

Source: OSV.dev, checked 2026-10-14. How this is measured.

Llama Stack replaces

Health badge

Maintain Llama Stack? Add its health score to your README. The badge links back to this page.

SelfHostIndex: 94 · excellent

Markdown
[![SelfHostIndex health score for Llama Stack](https://selfhostindex.com/badge/llama-stack.svg)](https://selfhostindex.com/app/llama-stack/)
HTML
<a href="https://selfhostindex.com/app/llama-stack/"><img src="https://selfhostindex.com/badge/llama-stack.svg" alt="SelfHostIndex health score for Llama Stack"></a>
reStructuredText
.. image:: https://selfhostindex.com/badge/llama-stack.svg
   :alt: SelfHostIndex health score for Llama Stack
   :target: https://selfhostindex.com/app/llama-stack/

The score is recomputed on every nightly rebuild from public repository data — see how it is calculated.

Compare Llama Stack

10 head-to-head comparisons.

Similar self-hosted ai apps