OGX
[**Quick Start**](https://ogx-ai.github.io/docs/getting_started/quickstart) | [**Documentation**](https://ogx-ai.github.io/docs) | [**OpenAI API Compatibility**](https://ogx-ai.github.io/docs/api-openai) | [**Discord**](https://discord.gg/bUYRqEvK6)
> [!IMPORTANT]
> **Llama Stack is now OGX.** The name changed, and so did the mission — model-agnostic, multi-SDK, production-grade. [Read the full announcement →](https://ogx-ai.github.io/blog/from-llama-stack-to-ogx)
**Open-source agentic API server for building AI applications. OpenAI-compatible. Any model, any infrastructure.**
OGX is a drop-in replacement for the OpenAI API that you can run anywhere — your laptop, your datacenter, or the cloud. Use any OpenAI-compatible client or agentic framework. Swap between Llama, GPT, Gemini, Mistral, or any model without changing your application code.
```python
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8321/v1", api_key="fake")
response = client.chat.completions.create(
model="llama-3.3-70b",
messages=[{"role": "user", "content": "Hello"}],
)
```
## What you get
- **Chat Completions & Embeddings** — standard `/v1/chat/completions`, `/v1/completions`, and `/v1/embeddings` endpoints, compatible with any OpenAI client
- **Responses API** — server-side agentic orchestration with tool calling, MCP server integration, and built-in file search (RAG) in a single API call ([learn more](https://ogx-ai.github.io/docs/api-openai))
- **Vector Stores & Files** — `/v1/vector_stores` and `/v1/files` for managed document storage and search
- **Batches** — `/v1/batches` for offline batch processing
- **Skills** — `/v1alpha/skills` for managing versioned skill bundles (zip archives with SKILL.md manifests) that agents can invoke
- **[Open Responses](https://www.openresponses.org/) conformant** — the Responses API implementation passes the Open Responses conformance test suite
- **Multi-SDK support** — use the [Anthropic SDK](https://docs.anthropic.com/en/api/messages) (`/v1/messages`) or [Google GenAI SDK](https://ai.google.dev/gemini-api/docs/interactions) (`/v1alpha/interactions`) natively alongside the OpenAI API
## Use any model, use any infrastructure
OGX has a pluggable provider architecture. Develop locally with Ollama, deploy to production with vLLM, or connect to a managed service — the API stays the same.
See the [provider documentation](https://ogx-ai.github.io/docs/providers) for the full list.
## Get started
Install and run a OGX server:
```bash
# One-line install
curl -LsSf https://github.com/ogx-ai/ogx/raw/main/scripts/install.sh | bash
# Or install via uv
uv pip install ogx[starter]
# Start the server (uses the starter distribution with Ollama)
uv run ogx run starter
```
Then connect with any OpenAI, Anthropic, or Google GenAI client — [Python](https://github.com/openai/openai-python), [TypeScript](https://github.com/openai/openai-node), [curl](https://platform.openai.com/docs/api-reference), or any framework that speaks these APIs.
See the [Quick Start guide](https://ogx-ai.github.io/docs/getting_started/quickstart) for detailed setup.
## Resources
- [Documentation](https://ogx-ai.github.io/docs) — full reference
- [OpenAI API Compatibility](https://ogx-ai.github.io/docs/api-openai) — endpoint coverage and provider matrix
- [Getting Started Notebook](./docs/getting_started.ipynb) — text and vision inference walkthrough
- [Contributing](CONTRIBUTING.md) — how to contribute
**Client SDKs:**
OGX provides official client SDKs for Python and TypeScript:
| Language | SDK | Package |
| :----: | :----: | :----: |
| Python | [ogx-client-python](https://github.com/ogx-ai/ogx-client-python) | [](https://pypi.org/project/ogx_client/) |
| TypeScript | [ogx-client-typescript](https://github.com/ogx-ai/ogx-client-typescript) | [](https://npmjs.org/package/ogx-client) |
**Alternative Python SDK:**
For users who prefer an OpenAPI Generator-based SDK, an alternative Python client is available:
- **[ogx-open-client](https://pypi.org/project/ogx-open-client/)** — Auto-generated from OpenAPI spec, provides similar functionality with a different generation approach
- **[Usage Examples](client-sdks/openapi/USAGE_EXAMPLES.md)** — End-to-end code examples for all major features
- **[Strategy & Rationale](client-sdks/openapi/STRATEGY.md)** — Why two SDKs, when to use which, and long-term plans
The official `ogx_client` SDK is recommended for most use cases. The `ogx_open_client` package offers an alternative for teams with specific OpenAPI tooling requirements.
## Community
We hold regular community calls every Thursday at 09:00 AM PST — see the [Community Event on Discord](https://discord.gg/bUYRqEvK6) for details.
[](https://www.star-history.com/#ogx-ai/ogx&Date)
Thanks to all our amazing contributors!
