llama-stack

library0.7.2pypypiunverified

Open-source, OpenAI-compatible API server with pluggable providers for any model and any infrastructure. Current version 0.7.1, requires Python >=3.12. Released under a rapid cadence (multiple minor versions per month).

llm-agents ai-ml web-framework

pip install llama-stack

github ↗package ↗homepage ↗

INSTALL

IMPORT

SIG · LLAMA-STACK

llama-stack

llm-agentspythonv0.7.2

Install

17.1s avg

Import

2173ms

Disk

223MB

Pass rate

6/ 10

Env Coverage6 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.2.11 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✓ —

✓ 24.4s

py 3.11

✓ —

✓ 21.3s

py 3.12

1/2 runs

py 3.13

1/2 runs

py 3.9

✓ —

✓ 5.5s

223MB installed

● package 223MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

LlamaStackClient

✓ from llama_stack import LlamaStackClient

✗ from llama_stack_client import LlamaStackClient

Initialize the Llama Stack client and run a basic chat completion. Requires the server to be running.

import os from llama_stack_client import LlamaStackClient client = LlamaStackClient( base_url=os.environ.get("LLAMA_STACK_BASE_URL", "http://localhost:8321"), api_key=os.environ.get("LLAMA_STACK_API_KEY", "") ) # List available models models = client.models.list() print([m.identifier for m in models]) # Send a chat completion response = client.chat.completions.create( model_id="Meta-Llama-3.1-8B-Instruct", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"} ] ) print(response.choices[0].message.content)

llama --version

Debug

Known issues

breakingIn v0.7.0 the fine_tuning API was removed entirely. Any code using fine_tuning endpoints or client methods will break.

fix

Remove fine_tuning API usage; use external training libraries if needed.

affects: >=0.7.0

breakingIn v0.6.0 numerous post-training API endpoints were renamed/restructured for consistency. Old endpoint paths no longer work.

fix

Update API calls to match the new consistent naming scheme documented in the changelog.

affects: >=0.6.0

deprecatedThe Agents API is deprecated in favor of the new Responses API (introduced v0.5.0). The Agents endpoint may be removed in a future release.

fix

Migrate from Agents to Responses API as shown in the migration guide.

affects: >=0.5.0

gotchaThe llama-stack package and llama-stack-client are separate PyPI packages. Installing one does NOT install the other.

fix

Install both with: pip install llama-stack llama-stack-client

affects: all

Upgrade

Version history

0.7.2latest on PyPI · released May 28, 2026

Audit

Dependencies

llama-stack-clientoptionalOfficial client library for interacting with the server

Agent activity

13 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/llamastack/llama-stack ↗

packagehttps://pypi.org/project/llama-stack/ ↗

homepagehttps://llama-stack.io ↗