Agent Zero AI framework
Add oMLX local provider support
Alessandro045009811761
diff --git a/conf/model_providers.yaml b/conf/model_providers.yamlindex 95ca2bf8e..0743a6512 100644--- a/conf/model_providers.yaml+++ b/conf/model_providers.yaml@@ -112,6 +112,15 @@ chat:default_base: "http://host.docker.internal:11434"kwargs:api_base: "http://host.docker.internal:11434"+ omlx:+ name: oMLX+ litellm_provider: hosted_vllm+ models_list:+ endpoint_url: "/v1/models"+ default_base: "http://host.docker.internal:8000"+ kwargs:+ api_base: "http://host.docker.internal:8000/v1"+ api_key: "omlx"ollama_cloud:name: Ollama Cloudlitellm_provider: openai@@ -202,6 +211,12 @@ embedding:litellm_provider: ollamakwargs:api_base: "http://host.docker.internal:11434"+ omlx:+ name: oMLX+ litellm_provider: hosted_vllm+ kwargs:+ api_base: "http://host.docker.internal:8000/v1"+ api_key: "omlx"openai:name: OpenAIlitellm_provider: openaidiff --git a/docs/setup/installation.md b/docs/setup/installation.mdindex b6688d22f..57c0b76b9 100644--- a/docs/setup/installation.md+++ b/docs/setup/installation.md@@ -438,6 +438,7 @@ Use the naming format required by your selected provider:| OpenAI | Model name only | `claude-sonnet-4-5` || OpenRouter | Provider prefix mostly required | `anthropic/claude-sonnet-4-5` || Ollama | Model name only | `gpt-oss:20b` |+| oMLX | API-visible model name from `/v1/models` | `Qwen3-0.6B-4bit` |> [!TIP]> If you see "Invalid model ID," verify the provider and naming format on the provider website, or search the web for "<name-of-ai-model> model naming".@@ -461,6 +462,48 @@ Use the naming format required by your selected provider:---+## Installing and Using oMLX (Apple Silicon Local Models)++oMLX is a local inference server for Apple Silicon Macs. It serves MLX models through an OpenAI-compatible API and supports chat, embeddings, and model listing endpoints.++> [!NOTE]+> oMLX requires Apple Silicon and macOS 15+. On 16 GB machines, start with small quantized MLX models.++### macOS oMLX Installation++**Using Homebrew:**++```bash+brew tap jundot/omlx https://github.com/jundot/omlx+brew install omlx+omlx start+```++**Using the macOS App:**++Download the oMLX app from the [official website](https://omlx.ai/) and follow the welcome flow to choose a model directory, start the server, and download or discover models.++By default, oMLX serves its OpenAI-compatible API at `http://localhost:8000/v1`.++To run a foreground server with oMLX's paged SSD cache enabled:++```bash+omlx serve --model-dir ~/.omlx/models --paged-ssd-cache-dir ~/.omlx/cache+```++### Configuring oMLX in Agent Zero++1. Start oMLX and make sure at least one model is available in the oMLX dashboard or model directory.+2. In Agent Zero Settings, choose **oMLX** as the Chat model, Utility model, or Embedding model provider.+3. Use the model name shown by oMLX's model list or dashboard.+4. Agent Zero includes Docker-friendly defaults for oMLX on the host at `http://host.docker.internal:8000/v1`. Override the API base URL only if your oMLX server runs somewhere else.+5. Click `Save` to confirm your settings.++> [!NOTE]+> If Agent Zero runs in Docker and oMLX runs on the Mac host, ensure port **8000** is reachable from the container. The shipped Docker Compose file maps `host.docker.internal` to the host gateway for Linux Docker. Docker Desktop for macOS provides this hostname automatically.++---+## Installing and Using Ollama (Local Models)Ollama is a powerful tool that allows you to run various large language models locally.diff --git a/plugins/_browser/helpers/connector_runtime.py b/plugins/_browser/helpers/connector_runtime.pyindex 82107aa7b..28c54b5fe 100644--- a/plugins/_browser/helpers/connector_runtime.py+++ b/plugins/_browser/helpers/connector_runtime.py@@ -58,7 +58,7 @@ HOST_BROWSER_PROFILE_MODE_KEY = getattr("host_browser_profile_mode",)get_browser_config = browser_config.get_browser_config-_LOCAL_PROVIDERS = {"ollama", "lm_studio"}+_LOCAL_PROVIDERS = {"ollama", "lm_studio", "omlx"}_LOCAL_HOSTS = {"localhost", "127.0.0.1", "::1", "host.docker.internal"}_SENSITIVE_ACTIONS = {"content", "detail", "evaluate", "screenshot", "screenshot_file"}_KEY_ALIASES = {diff --git a/plugins/_model_config/api/model_search.py b/plugins/_model_config/api/model_search.pyindex 83a7deeda..ec5f50d24 100644--- a/plugins/_model_config/api/model_search.py+++ b/plugins/_model_config/api/model_search.py@@ -179,7 +179,7 @@ class ModelSearch(ApiHandler):elif provider == "azure":if has_key:headers["api-key"] = api_key- elif provider not in ("ollama", "lm_studio"):+ elif provider not in ("ollama", "lm_studio", "omlx"):if has_key:headers["Authorization"] = f"Bearer {api_key}"diff --git a/plugins/_model_config/extensions/python/banners/_20_missing_api_key.py b/plugins/_model_config/extensions/python/banners/_20_missing_api_key.pyindex 0028a93fc..a3fc48301 100644--- a/plugins/_model_config/extensions/python/banners/_20_missing_api_key.py+++ b/plugins/_model_config/extensions/python/banners/_20_missing_api_key.py@@ -6,7 +6,7 @@ from plugins._model_config.helpers import model_configclass MissingApiKeyCheck(Extension):"""Check if API keys are configured for selected model providers."""- LOCAL_PROVIDERS = {"ollama", "lm_studio"}+ LOCAL_PROVIDERS = {"ollama", "lm_studio", "omlx"}CONFIGURE_MODEL_SETTINGS_LINK = ("""<div class="onboarding-banner-btn-container" style="margin-top: 12px;">""""""<button class="btn btn-ok" onclick="window.openModal('/plugins/_onboarding/webui/onboarding.html');return false;">"""diff --git a/plugins/_model_config/helpers/model_config.py b/plugins/_model_config/helpers/model_config.pyindex 045e915c8..08b834ce2 100644--- a/plugins/_model_config/helpers/model_config.py+++ b/plugins/_model_config/helpers/model_config.py@@ -32,7 +32,7 @@ IMPLICIT_PRESET_SLOT_DEFAULTS = {"kwargs": {},},}-LOCAL_PROVIDERS = {"ollama", "lm_studio"}+LOCAL_PROVIDERS = {"ollama", "lm_studio", "omlx"}LOCAL_EMBEDDING = {"huggingface"}_PROVIDER_METADATA_CACHE: dict | None = Nonediff --git a/plugins/_model_config/provider_metadata.yaml b/plugins/_model_config/provider_metadata.yamlindex 1fcd1d6f4..d6dc5bfc3 100644--- a/plugins/_model_config/provider_metadata.yaml+++ b/plugins/_model_config/provider_metadata.yaml@@ -3,6 +3,8 @@ chat:api_key_mode: noneollama:api_key_mode: none+ omlx:+ api_key_mode: noneother:api_key_mode: optional@@ -13,5 +15,7 @@ embedding:api_key_mode: noneollama:api_key_mode: none+ omlx:+ api_key_mode: noneother:api_key_mode: optionaldiff --git a/plugins/_onboarding/webui/assets/provider-logos/omlx.svg b/plugins/_onboarding/webui/assets/provider-logos/omlx.svgnew file mode 100644index 000000000..7bd64b1b0--- /dev/null+++ b/plugins/_onboarding/webui/assets/provider-logos/omlx.svg@@ -0,0 +1,19 @@+<svg xmlns="http://www.w3.org/2000/svg" width="160" height="160" viewBox="0 0 160 160" role="img" aria-labelledby="omlx-title">+ <title id="omlx-title">oMLX</title>+ <!-- Source: oMLX project icon, Apache-2.0. -->+ <defs>+ <filter id="omlx-shadow" x="-10%" y="-10%" width="130%" height="130%">+ <feDropShadow dx="0" dy="2" stdDeviation="6" flood-color="#000" flood-opacity="0.3"/>+ </filter>+ <linearGradient id="omlx-bg" x1="0" y1="0" x2="0" y2="1">+ <stop offset="0%" stop-color="#2d2d2d"/>+ <stop offset="100%" stop-color="#1a1a1a"/>+ </linearGradient>+ </defs>+ <rect x="10" y="10" width="140" height="140" rx="32" fill="url(#omlx-bg)" filter="url(#omlx-shadow)"/>+ <g transform="translate(25, 25) scale(0.0221)">+ <g transform="translate(0,4970) scale(1,-1)" fill="#fff" stroke="none">+ <path d="M2275 4349c-408-39-769-207-1056-492-196-194-333-428-418-715-47-158-67-281-101-617-66-662-116-944-245-1387-102-352-271-774-420-1051-19-35-35-70-35-76 0-8 50-11 163-11h164l80 168c168 348 303 739 408 1175 73 307 109 532 155 982 52 500 72 627 122 785 162 507 570 860 1096 951 155 26 389 26 544 0 221-38 440-129 620-258 45-32 152-126 237-209 86-82 178-165 204-183 106-72 312-150 495-186l32-7-86-54c-110-69-170-117-267-212-93-91-143-154-191-243-105-191-130-406-75-623 29-115 81-239 217-516 234-480 343-769 411-1091 36-172 48-252 57-381l7-98h158 158l-4 28c-2 15-6 66-9 113-14 218-95 560-201 849-81 220-165 407-363 810-120 245-147 320-161 443-38 338 202 621 766 906 131 65 166 126 106 183-33 31-86 47-288 88-177 36-274 61-370 97-140 52-190 88-377 270-140 137-202 189-300 254-378 250-782 351-1233 308zM3050 3391c-57-11-122-53-154-99-41-57-49-158-18-218 29-56 66-92 120-117 153-69 323 37 325 203 1 147-131 259-273 231zM1985 1391c-68-31-70-40-66-271 1-114-2-243-9-290-40-307-124-555-255-754-25-38-45-71-45-72 0-2 79-4 176-4h175l54 113c117 247 182 512 201 812 7 126-9 319-32 374-26 63-86 111-136 111-13 0-41-9-63-19z"/>+ </g>+ </g>+</svg>diff --git a/plugins/_onboarding/webui/onboarding-providers.js b/plugins/_onboarding/webui/onboarding-providers.jsindex 55e45090a..7680db5f2 100644--- a/plugins/_onboarding/webui/onboarding-providers.js+++ b/plugins/_onboarding/webui/onboarding-providers.js@@ -25,7 +25,7 @@ export const MORE_CLOUD_PROVIDER_IDS = ["other",];-export const LOCAL_PROVIDER_IDS = ["ollama", "lm_studio", "other"];+export const LOCAL_PROVIDER_IDS = ["ollama", "lm_studio", "omlx", "other"];export const ONBOARDING_PROVIDER_OVERRIDES = {a0_venice: {@@ -172,6 +172,15 @@ export const ONBOARDING_PROVIDER_OVERRIDES = {model_list_autoload: true,short_description: "Ollama cloud models through a hosted endpoint.",},+ omlx: {+ logo: "/plugins/_onboarding/webui/assets/provider-logos/omlx.svg",+ setup_url: "https://omlx.ai/",+ docs_url: "https://github.com/jundot/omlx#readme",+ default_api_base: "http://host.docker.internal:8000/v1",+ api_key_mode: "none",+ model_list_autoload: true,+ short_description: "Apple Silicon local inference with MLX.",+ },openai: {logo: "https://openai.com/favicon.ico",setup_url: "https://platform.openai.com/",diff --git a/tests/test_model_config_api_keys.py b/tests/test_model_config_api_keys.pyindex fa212a54b..0ec597de8 100644--- a/tests/test_model_config_api_keys.py+++ b/tests/test_model_config_api_keys.py@@ -274,8 +274,10 @@ def test_provider_key_modes_for_local_and_ollama_cloud():assert model_config.provider_requires_api_key("ollama") is Falseassert model_config.provider_requires_api_key("lm_studio") is False+ assert model_config.provider_requires_api_key("omlx") is Falseassert model_config.provider_requires_api_key("other") is Falseassert model_config.provider_requires_api_key("ollama_cloud") is True+ assert "omlx" in missing_key_banner.MissingApiKeyCheck.LOCAL_PROVIDERSdef test_local_provider_defaults_are_docker_friendly():@@ -297,6 +299,15 @@ def test_local_provider_defaults_are_docker_friendly():assert provider_config["chat"]["ollama"]["models_list"]["default_base"] == ("http://host.docker.internal:11434")+ assert provider_config["chat"]["omlx"]["litellm_provider"] == "hosted_vllm"+ assert provider_config["chat"]["omlx"]["kwargs"]["api_base"] == (+ "http://host.docker.internal:8000/v1"+ )+ assert provider_config["chat"]["omlx"]["kwargs"]["api_key"] == "omlx"+ assert provider_config["chat"]["omlx"]["models_list"]["default_base"] == (+ "http://host.docker.internal:8000"+ )+ assert provider_config["chat"]["omlx"]["models_list"]["endpoint_url"] == "/v1/models"assert provider_config["embedding"]["lm_studio"]["kwargs"]["api_base"] == ("http://host.docker.internal:1234/v1")@@ -304,6 +315,11 @@ def test_local_provider_defaults_are_docker_friendly():assert provider_config["embedding"]["ollama"]["kwargs"]["api_base"] == ("http://host.docker.internal:11434")+ assert provider_config["embedding"]["omlx"]["litellm_provider"] == "hosted_vllm"+ assert provider_config["embedding"]["omlx"]["kwargs"]["api_base"] == (+ "http://host.docker.internal:8000/v1"+ )+ assert provider_config["embedding"]["omlx"]["kwargs"]["api_key"] == "omlx"def test_local_provider_runtime_defaults_and_overrides(monkeypatch):@@ -333,6 +349,25 @@ def test_local_provider_runtime_defaults_and_overrides(monkeypatch):assert ollama_embedding.kwargs["api_base"] == "http://host.docker.internal:11434"assert "api_key" not in ollama_embedding.kwargs+ omlx_chat = models.get_chat_model("omlx", "local-chat-model")+ assert omlx_chat.model_name == "hosted_vllm/local-chat-model"+ assert omlx_chat.kwargs["api_base"] == "http://host.docker.internal:8000/v1"+ assert omlx_chat.kwargs["api_key"] == "omlx"++ omlx_embedding = models.get_embedding_model("omlx", "local-embedding-model")+ assert omlx_embedding.model_name == "hosted_vllm/local-embedding-model"+ assert omlx_embedding.kwargs["api_base"] == "http://host.docker.internal:8000/v1"+ assert omlx_embedding.kwargs["api_key"] == "omlx"++ custom_omlx_chat = models.get_chat_model(+ "omlx",+ "local-chat-model",+ api_base="http://127.0.0.1:8000/v1",+ api_key="real-local-key",+ )+ assert custom_omlx_chat.kwargs["api_base"] == "http://127.0.0.1:8000/v1"+ assert custom_omlx_chat.kwargs["api_key"] == "real-local-key"+def test_docker_compose_maps_host_docker_internal_for_local_models():import yamldiff --git a/tests/test_model_search.py b/tests/test_model_search.pyindex 7540b7342..a90c12ce5 100644--- a/tests/test_model_search.py+++ b/tests/test_model_search.py@@ -66,6 +66,12 @@ def test_model_search_resolves_v1_base_without_duplicate_v1():assert fmt == "openai"+def test_model_search_omits_auth_header_for_omlx_placeholder_key():+ handler = _handler()++ assert handler._build_headers("omlx", "omlx", {}) == {}++def test_model_search_filters_non_chat_models():handler = _handler()diff --git a/tests/test_onboarding_static.py b/tests/test_onboarding_static.pyindex dab37a691..41abe7341 100644--- a/tests/test_onboarding_static.py+++ b/tests/test_onboarding_static.py@@ -65,11 +65,16 @@ def test_onboarding_provider_grid_names_are_present_in_metadata():assert 'docs_url: "https://docs.venice.ai/guides/getting-started/generating-api-key"' in provider_uiassert 'docs_url: "https://docs.tokenfactory.nebius.com/api-reference/introduction"' in provider_uiassert 'docs_url: "https://lmstudio.ai/docs/developer/core/authentication"' in provider_ui+ assert 'logo: "/plugins/_onboarding/webui/assets/provider-logos/omlx.svg"' in provider_ui+ assert 'docs_url: "https://github.com/jundot/omlx#readme"' in provider_ui+ assert 'default_api_base: "http://host.docker.internal:8000/v1"' in provider_uiassert 'docs_url: ""' in provider_uiassert "api_key_mode: none" in model_metadataassert "api_key_mode: optional" in model_metadataassert "Ollama Cloud" in provider_yamlassert "https://ollama.com/v1" in provider_yaml+ assert "oMLX" in provider_yaml+ assert "http://host.docker.internal:8000/v1" in provider_yamlassert "Nebius Token Factory" in provider_yamlassert "https://api.tokenfactory.nebius.com/v1" in provider_yamlassert not (PROJECT_ROOT / "plugins/_model_config/conf/model_providers.yaml").exists()@@ -87,6 +92,7 @@ def test_onboarding_provider_grid_names_are_present_in_metadata():"Z.AI","Mistral AI","Azure OpenAI",+ "oMLX",]:assert name in provider_yaml + provider_ui@@ -117,9 +123,12 @@ def test_onboarding_provider_grid_names_are_present_in_metadata():"cometapi.ico","github-copilot.svg","zai-logo.svg",+ "omlx.svg",]:assert logo in provider_ui+ assert (PROJECT_ROOT / "plugins/_onboarding/webui/assets/provider-logos/omlx.svg").exists()+def test_nebius_provider_config_uses_openai_compatible_token_factory_endpoint():provider_path = PROJECT_ROOT / "conf/model_providers.yaml"