# ogx-ai/llama-stack-apps

Agentic components of the Llama Stack APIs

Repository: https://github.com/ogx-ai/llama-stack-apps
Canonical: https://ross.abutalabs.com/products/llama-stack-apps
License: MIT
License Family: permissive
Archived: true
Last push: 2025-08-05T14:49:58+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 35, release rhythm 35, longevity 57
- inputs: {"age_days": 799, "days_push": 393, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4302, forks 643 (observed 2026-08-28T04:08:41.683089+00:00)

## What it is
A collection of example applications and demo scripts built on top of Llama Stack, showing how to build agentic applications with Llama models. It demonstrates multi-step reasoning, tool use (built-in and zero-shot), and safety checks via Llama Guard against a running Llama Stack server.

## Use cases
- build agentic apps with llama models
- examples of tool calling with llama stack
- multi-step reasoning agent demos
- add safety checks with llama guard
- get started with llama stack client apps
- code interpreter and search tool examples

## When to choose
- you want working example code for building agents on Llama Stack
- you are learning how Llama Stack APIs fit together
- you need reference implementations of tool use and safety checks with Llama models

## When to avoid
- you need the Llama Stack server or SDK itself (use meta-llama/llama-stack)
- you want a production-ready agent framework rather than examples
- you use models or stacks other than Llama

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, llm-inference, rag, sdk
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, self-hosted, cross-platform
- tags: llama-stack, llama, agentic-apps, examples, meta, tool-use, llama-guard, safety, ai-agents

## Member repositories
- ogx-ai/llama-stack-apps (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:41.683089+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 2026-08-29T18:21:50.300458+00:00, confidence not recorded.
  - readme: https://github.com/ogx-ai/llama-stack-apps (fetched 2026-08-28T04:08:41.683089+00:00, sha a613d6f6cd3c)
- Data as of 2026-08-30T08:39:29.467469+00:00.