asiai-inference-server 0.1.0__tar.gz

asiai_inference_server-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,68 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    name: "Python ${{ matrix.python-version }} / macOS ${{ matrix.macos-version }}"
+    runs-on: ${{ matrix.macos-version }}
+    timeout-minutes: 15
+    strategy:
+      fail-fast: false
+      matrix:
+        # macOS 13 (Ventura) runners no longer available on GH Actions hosted pool
+        # as of May 2026 — jobs queue indefinitely and get cancelled at 24h. Only
+        # support macOS 14 (Sonoma) and 15 (Sequoia) — covers Apple Silicon current.
+        python-version: ["3.11", "3.12", "3.13"]
+        macos-version: ["macos-14", "macos-15"]
+
+    steps:
+      - uses: actions/checkout@v5
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install package (editable)
+        run: pip install -e ".[dev]"
+
+      - name: Lint (ruff)
+        run: ruff check src/ tests/
+
+      - name: Tests
+        run: pytest tests/ -v --tb=short
+
+  contract-test:
+    name: "Plugin contract test (entry-point + RegistrationContext)"
+    runs-on: macos-14
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v5
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.12"
+
+      - name: Install both packages
+        run: |
+          pip install -e ".[dev]"
+          # Verify entry-point is discoverable by importlib.metadata
+          python -c "
+          from importlib.metadata import entry_points
+          eps = list(entry_points(group='asiai.subcommands'))
+          assert eps, 'No asiai.subcommands entry points found'
+          ep = eps[0]
+          register = ep.load()
+          import argparse
+          p = argparse.ArgumentParser()
+          sub = p.add_subparsers()
+          cmds = {}
+          register(sub, cmds)
+          assert 'engine' in cmds, f'engine not in commands: {list(cmds)}'
+          print(f'Contract test passed — entry point: {ep.name}, commands: {list(cmds)}')
+          "

asiai_inference_server-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,39 @@
+name: Release to PyPI
+
+on:
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: write
+  id-token: write
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    environment: pypi
+    steps:
+      - uses: actions/checkout@v6
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.13"
+
+      - name: Install build tools
+        run: pip install build
+
+      - name: Build package
+        run: python -m build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+      - name: Create GitHub Release
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          TAG_NAME: ${{ github.ref_name }}
+        run: |
+          gh release create "$TAG_NAME" dist/* \
+            --title "$TAG_NAME" \
+            --generate-notes

asiai_inference_server-0.1.0/.gitignore

@@ -0,0 +1,54 @@
+# Build artefacts
+build/
+dist/
+*.egg-info/
+*.egg
+.eggs/
+wheels/
+share/python-wheels/
+MANIFEST
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+.python-version
+
+# Virtual environments
+.venv/
+venv/
+ENV/
+env/
+
+# Caches
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+.tox/
+.coverage
+.coverage.*
+htmlcov/
+coverage.xml
+*.cover
+.hypothesis/
+
+# IDEs
+.idea/
+.vscode/
+*.swp
+*.swo
+.DS_Store
+
+# Local dev
+*.local
+*.bak
+.env
+.env.*
+!.env.example
+
+# asiai-inference-server runtime state (never commit)
+~/.config/asiai-inference-server/
+agent.token
+profile-current

asiai_inference_server-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for describing the origin of the Work and
+      reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Support. While redistributing the Work or
+      Derivative Works thereof, You may choose to offer, and charge a
+      fee for, acceptance of support, warranty, indemnity, or other
+      liability obligations and/or rights consistent with this License.
+      However, in accepting such obligations, You may act only on Your
+      own behalf and on Your sole responsibility, not on behalf of any
+      other Contributor, and only if You agree to indemnify, defend, and
+      hold each Contributor harmless for any liability incurred by, or
+      claims asserted against, such Contributor by reason of your
+      accepting any such warranty or support.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed" page as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Jean-Marc Nahlovsky
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

asiai_inference_server-0.1.0/PKG-INFO

@@ -0,0 +1,102 @@
+Metadata-Version: 2.4
+Name: asiai-inference-server
+Version: 0.1.0
+Summary: Fleet manager for local LLM inference engines on Apple Silicon
+Project-URL: Homepage, https://asiai.dev
+Project-URL: Documentation, https://asiai.dev/inference-server/
+Project-URL: Repository, https://github.com/druide67/asiai-inference-server
+Project-URL: Issues, https://github.com/druide67/asiai-inference-server/issues
+Author-email: Jean-Marc Nahlovsky <druide67@free.fr>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: apple-silicon,fleet,inference,llm,lmstudio,macos,mcp,mlx,ollama
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Environment :: MacOS X
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: System :: Systems Administration
+Requires-Python: >=3.11
+Requires-Dist: asiai>=1.8.0
+Provides-Extra: dev
+Requires-Dist: pytest-cov>=5.0; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: ruff>=0.6; extra == 'dev'
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.12; extra == 'mcp'
+Description-Content-Type: text/markdown
+
+# asiai-inference-server
+
+Fleet manager for local LLM inference engines on Apple Silicon.
+
+> **Status: v0.0.1 pre-alpha — skeleton only.** Not yet functional. See the
+> roadmap below.
+
+`asiai-inference-server` is the **control plane** companion to
+[`asiai`](https://asiai.dev) (the observability/benchmark CLI). Where `asiai`
+*observes* what's running on your Mac, this project *manages* it: install,
+start, stop, unload, and orchestrate inference engines (llama.cpp,
+Ollama, LM Studio, oMLX, TurboQuant, mlx-lm, vMLX, …) across one or
+several Apple Silicon machines.
+
+It also fixes the long-standing macOS pain point: **engine memory that never
+gets freed** because of the unified-memory compressor. Killing a process
+doesn't release the VRAM. This tool combines per-engine unload APIs, full
+LaunchDaemon restart, and `sudo purge` to reclaim memory deterministically —
+and reports the actual delta measured, not a marketing promise.
+
+## Why
+
+After a year of running multi-engine LLM inference on Apple Silicon
+(MacBook M1 Max, Mac Mini M4 Pro, MacBook M5 Max), the operational gap
+became obvious:
+
+- **Install/uninstall** an engine should not require chasing brews, plists
+  and firewall rules across READMEs.
+- **Switching profiles** ("coding agent on Qwen-Coder 32B" → "70B chat on
+  TurboQuant") should be a single command, not five.
+- **Memory unload** should actually free the VRAM, not let the macOS
+  compressor sit on it.
+- **A fleet of Macs** should be a single dashboard, not three SSH sessions.
+- **AI agents** (Claude Code, Cursor, Windsurf) should be able to manage
+  the fleet via MCP, not just observe it.
+
+`asiai-inference-server` ships these one at a time, building on the
+`asiai` observability stack.
+
+## Roadmap
+
+| Version | Scope | Status |
+|---------|-------|--------|
+| v0.0 | Repo skeleton + packaging | in progress |
+| v0.1 | Install/uninstall/start/stop + **unload + purge memory** | next |
+| v0.2 | Profile switching (TOML profiles, apply/rollback) | planned |
+| v0.3 | Fleet manager (multi-Mac inventory, SSH dispatch) | planned |
+| v0.4 | Web cockpit + optional HTTP agent | planned |
+| v1.0 | MCP write tools + PyPI/Homebrew release | planned |
+
+## Architecture (high level)
+
+- **CLI**: `aisctl <command>` (standalone) or `asiai engine <command>`
+  (auto-injected sub-CLI when `asiai-inference-server` is installed
+  alongside `asiai`).
+- **Python stdlib only** for the core (cohérent avec asiai). Optional
+  extras: `mcp` (for v1.0 write tools).
+- **macOS Apple Silicon only**. We rely on `launchctl`, `vm_stat`,
+  `sudo purge`, `pfctl`, `iogpu.wired_limit_mb`.
+- **SSH-first** for fleet operations. Optional HTTP agent in v0.4 for
+  agent-to-agent orchestration.
+- **TOML** for human-edited files (engine manifests, profiles, fleet
+  inventory). JSON for runtime state.
+
+The full design rationale (architecture diagram, sequencing, file map,
+risk mitigations) lives in the validated plan at
+`~/.claude/plans/iterative-wiggling-crystal.md`.
+
+## License
+
+Apache-2.0 © 2026 Jean-Marc Nahlovsky

asiai_inference_server-0.1.0/README.md

@@ -0,0 +1,71 @@
+# asiai-inference-server
+
+Fleet manager for local LLM inference engines on Apple Silicon.
+
+> **Status: v0.0.1 pre-alpha — skeleton only.** Not yet functional. See the
+> roadmap below.
+
+`asiai-inference-server` is the **control plane** companion to
+[`asiai`](https://asiai.dev) (the observability/benchmark CLI). Where `asiai`
+*observes* what's running on your Mac, this project *manages* it: install,
+start, stop, unload, and orchestrate inference engines (llama.cpp,
+Ollama, LM Studio, oMLX, TurboQuant, mlx-lm, vMLX, …) across one or
+several Apple Silicon machines.
+
+It also fixes the long-standing macOS pain point: **engine memory that never
+gets freed** because of the unified-memory compressor. Killing a process
+doesn't release the VRAM. This tool combines per-engine unload APIs, full
+LaunchDaemon restart, and `sudo purge` to reclaim memory deterministically —
+and reports the actual delta measured, not a marketing promise.
+
+## Why
+
+After a year of running multi-engine LLM inference on Apple Silicon
+(MacBook M1 Max, Mac Mini M4 Pro, MacBook M5 Max), the operational gap
+became obvious:
+
+- **Install/uninstall** an engine should not require chasing brews, plists
+  and firewall rules across READMEs.
+- **Switching profiles** ("coding agent on Qwen-Coder 32B" → "70B chat on
+  TurboQuant") should be a single command, not five.
+- **Memory unload** should actually free the VRAM, not let the macOS
+  compressor sit on it.
+- **A fleet of Macs** should be a single dashboard, not three SSH sessions.
+- **AI agents** (Claude Code, Cursor, Windsurf) should be able to manage
+  the fleet via MCP, not just observe it.
+
+`asiai-inference-server` ships these one at a time, building on the
+`asiai` observability stack.
+
+## Roadmap
+
+| Version | Scope | Status |
+|---------|-------|--------|
+| v0.0 | Repo skeleton + packaging | in progress |
+| v0.1 | Install/uninstall/start/stop + **unload + purge memory** | next |
+| v0.2 | Profile switching (TOML profiles, apply/rollback) | planned |
+| v0.3 | Fleet manager (multi-Mac inventory, SSH dispatch) | planned |
+| v0.4 | Web cockpit + optional HTTP agent | planned |
+| v1.0 | MCP write tools + PyPI/Homebrew release | planned |
+
+## Architecture (high level)
+
+- **CLI**: `aisctl <command>` (standalone) or `asiai engine <command>`
+  (auto-injected sub-CLI when `asiai-inference-server` is installed
+  alongside `asiai`).
+- **Python stdlib only** for the core (cohérent avec asiai). Optional
+  extras: `mcp` (for v1.0 write tools).
+- **macOS Apple Silicon only**. We rely on `launchctl`, `vm_stat`,
+  `sudo purge`, `pfctl`, `iogpu.wired_limit_mb`.
+- **SSH-first** for fleet operations. Optional HTTP agent in v0.4 for
+  agent-to-agent orchestration.
+- **TOML** for human-edited files (engine manifests, profiles, fleet
+  inventory). JSON for runtime state.
+
+The full design rationale (architecture diagram, sequencing, file map,
+risk mitigations) lives in the validated plan at
+`~/.claude/plans/iterative-wiggling-crystal.md`.
+
+## License
+
+Apache-2.0 © 2026 Jean-Marc Nahlovsky

asiai_inference_server-0.1.0/contrib/mlx-lm/wrapper-start.sh.tpl

@@ -0,0 +1,72 @@
+#!/usr/bin/env bash
+# =============================================================================
+# mlx-lm headless server startup script
+# Installed at /usr/local/bin/mlx-lm-server-start from this template.
+# =============================================================================
+#
+# mlx-lm has no native CLI binary — the OpenAI-compatible server is a
+# Python module (``python -m mlx_lm.server``). This wrapper:
+#   1. Ensures ``~/.cache/huggingface/hub`` exists (mlx-lm crashes on
+#      ``scan_cache_dir()`` when it does not).
+#   2. Discovers the venv python (env override > known paths).
+#   3. Execs ``python -m mlx_lm.server`` with the configured args.
+#
+# Override via environment variables (set in the LaunchDaemon plist):
+#   MLXLM_PYTHON  path to the venv python (skips auto-discovery)
+#   MLXLM_MODEL   model path or HF repo id passed to ``--model``
+#   MLXLM_PORT    listening port (default 8000)
+#   MLXLM_HOST    bind address (default 0.0.0.0)
+#
+# Recommended install:  ``uv tool install mlx-lm``
+# =============================================================================
+
+set -euo pipefail
+
+# HuggingFace cache directory must exist before mlx-lm starts.
+export HF_HUB_CACHE="${HF_HUB_CACHE:-${HOME}/.cache/huggingface/hub}"
+mkdir -p "${HF_HUB_CACHE}"
+
+# Resolve the venv python: explicit env override wins, otherwise probe a
+# short list of conventional install layouts.
+PY="${MLXLM_PYTHON:-}"
+if [[ -z "${PY}" ]]; then
+    for candidate in \
+        "${HOME}/.local/share/uv/tools/mlx-lm/bin/python" \
+        "${HOME}/.local/pipx/venvs/mlx-lm/bin/python" \
+        "${HOME}/.local/share/pipx/venvs/mlx-lm/bin/python" \
+        "${HOME}/.venvs/mlx-lm/bin/python" \
+        "/opt/homebrew/bin/python3" \
+        "/usr/local/bin/python3"
+    do
+        if [[ -x "${candidate}" ]]; then
+            PY="${candidate}"
+            break
+        fi
+    done
+fi
+
+if [[ -z "${PY}" || ! -x "${PY}" ]]; then
+    echo "ERROR: no mlx-lm python interpreter found." >&2
+    echo "Hint: install via 'uv tool install mlx-lm' or set MLXLM_PYTHON." >&2
+    exit 1
+fi
+
+# Sanity-check: the chosen interpreter must import mlx_lm.
+if ! "${PY}" -c "import mlx_lm" >/dev/null 2>&1; then
+    echo "ERROR: interpreter ${PY} cannot import mlx_lm." >&2
+    echo "Hint: ensure mlx-lm is installed in that environment." >&2
+    exit 1
+fi
+
+MODEL_PATH="${MLXLM_MODEL:-${HOME}/llms/mlx/active}"
+# Expand a leading ~ to $HOME since launchd does not pre-expand env vars
+# and quoted bash parameters skip tilde expansion. mlx-lm receives the
+# argument literally and would fail to find the model directory.
+MODEL_PATH="${MODEL_PATH/#\~/${HOME}}"
+PORT="${MLXLM_PORT:-8000}"
+HOST="${MLXLM_HOST:-0.0.0.0}"
+
+exec "${PY}" -m mlx_lm.server \
+    --model "${MODEL_PATH}" \
+    --host "${HOST}" \
+    --port "${PORT}"

asiai_inference_server-0.1.0/contrib/rapid-mlx/wrapper-start.sh.tpl

@@ -0,0 +1,60 @@
+#!/usr/bin/env bash
+# =============================================================================
+# Rapid-MLX headless server startup script
+# Installed at /usr/local/bin/rapid-mlx-server-start from this template.
+# =============================================================================
+#
+# Rapid-MLX (github.com/raullenchai/Rapid-MLX) is a Python entry-point
+# distributed via pip / brew. This wrapper:
+#   1. Ensures ``~/.cache/huggingface/hub`` exists (MLX engines crash on
+#      ``scan_cache_dir()`` when it does not).
+#   2. Discovers the ``rapid-mlx`` binary (env override > brew > pip).
+#   3. Execs ``rapid-mlx serve <model> --host H --port P``.
+#
+# Override via environment variables (set in the LaunchDaemon plist):
+#   RAPIDMLX_BIN    path to the rapid-mlx binary (skips auto-discovery)
+#   RAPIDMLX_MODEL  model alias or HF repo id passed positionally
+#   RAPIDMLX_PORT   listening port (default 8004)
+#   RAPIDMLX_HOST   bind address (default 0.0.0.0)
+#
+# Recommended install:  ``brew install raullenchai/rapid-mlx/rapid-mlx``
+# Alternative:          ``pip install rapid-mlx`` (then export RAPIDMLX_BIN
+#                       to the pip-installed entry point if not in PATH)
+# =============================================================================
+
+set -euo pipefail
+
+# HuggingFace cache directory must exist before MLX engines start.
+export HF_HUB_CACHE="${HF_HUB_CACHE:-${HOME}/.cache/huggingface/hub}"
+mkdir -p "${HF_HUB_CACHE}"
+
+# Resolve the rapid-mlx binary: explicit env override wins, otherwise probe
+# a short list of conventional install layouts.
+BIN="${RAPIDMLX_BIN:-}"
+if [[ -z "${BIN}" ]]; then
+    for candidate in \
+        "/opt/homebrew/bin/rapid-mlx" \
+        "/usr/local/bin/rapid-mlx" \
+        "${HOME}/.local/bin/rapid-mlx" \
+        "${HOME}/.local/share/uv/tools/rapid-mlx/bin/rapid-mlx"
+    do
+        if [[ -x "${candidate}" ]]; then
+            BIN="${candidate}"
+            break
+        fi
+    done
+fi
+
+if [[ -z "${BIN}" || ! -x "${BIN}" ]]; then
+    echo "ERROR: rapid-mlx binary not found." >&2
+    echo "Hint: install via 'brew install raullenchai/rapid-mlx/rapid-mlx' or set RAPIDMLX_BIN." >&2
+    exit 1
+fi
+
+MODEL="${RAPIDMLX_MODEL:-qwen3.6-27b-ud}"
+PORT="${RAPIDMLX_PORT:-8004}"
+HOST="${RAPIDMLX_HOST:-0.0.0.0}"
+
+exec "${BIN}" serve "${MODEL}" \
+    --host "${HOST}" \
+    --port "${PORT}"