mnemos-embedkit 0.1.0a1__tar.gz

mnemos_embedkit-0.1.0a1/.github/workflows/publish.yml

@@ -0,0 +1,42 @@
+# Publish mnemos-embedkit to PyPI via Trusted Publishing (OIDC — no API token).
+# PyPI pending-publisher must be configured as:
+#   owner: ncz-os | repo: mnemos-embedkit | workflow: publish.yml | environment: pypi
+name: publish
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+permissions: {}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Build sdist + wheel
+        run: |
+          python -m pip install --upgrade build twine
+          python -m build
+          python -m twine check dist/*
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write   # OIDC token for PyPI Trusted Publishing
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+      - uses: pypa/gh-action-pypi-publish@release/v1

mnemos_embedkit-0.1.0a1/.gitignore

@@ -0,0 +1,45 @@
+# Build artifacts
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+*.egg-info/
+build/
+dist/
+.eggs/
+*.whl
+
+# Environments
+.venv/
+venv/
+.env
+
+# Bench artifacts (raw JSONL kept out of git; summaries land in benches/results.md)
+benches/results/*.jsonl
+benches/results/*.log
+benches/corpora/*.json
+
+# Models — never commit
+*.gguf
+*.cix
+*.onnx
+*.safetensors
+*.rknn
+*.xdna
+benches/models/
+
+# Tooling
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+.coverage
+htmlcov/
+
+# OS
+.DS_Store
+Thumbs.db
+
+# IDE
+.vscode/
+.idea/
+*.swp

mnemos_embedkit-0.1.0a1/.gitlab-ci.yml

@@ -0,0 +1,18 @@
+# GitLab CI — Python "real errors" gate (ruff, high-signal rules only).
+# GitLab SaaS shared runners (free OSS minutes), no fleet CPU. Catches syntax
+# errors + undefined names (E9,F63,F7,F82); stylistic/style-of-imports rules
+# (E402/E501, unused imports) are intentionally NOT gated here — tighten per repo
+# later. Buildkite (ncz-os, hosted) owns heavy/native builds + release artifacts.
+stages:
+  - check
+
+ruff:
+  stage: check
+  image: python:3.12-slim
+  before_script:
+    - pip install --quiet ruff
+  script:
+    - ruff check --select E9,F63,F7,F82 --output-format=concise .
+  rules:
+    - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
+    - if: '$CI_PIPELINE_SOURCE == "push"'

mnemos_embedkit-0.1.0a1/LICENSE

@@ -0,0 +1,17 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   Copyright (c) 2026 Jason Perlow
+
+   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.

mnemos_embedkit-0.1.0a1/PKG-INFO

@@ -0,0 +1,200 @@
+Metadata-Version: 2.4
+Name: mnemos-embedkit
+Version: 0.1.0a1
+Summary: Open embedding devkit — same API across NPU / GPU / CPU silicon (Cix, NVIDIA, AMD, Intel, Apple, Rockchip, MediaTek)
+Project-URL: Homepage, https://github.com/ncz-os/mnemos-embedkit
+Project-URL: Repository, https://github.com/ncz-os/mnemos-embedkit
+Project-URL: Issues, https://github.com/ncz-os/mnemos-embedkit/issues
+Author-email: Jason Perlow <jperlow@gmail.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.11
+Requires-Dist: numpy>=1.26
+Requires-Dist: transformers>=4.40
+Provides-Extra: all
+Requires-Dist: llama-cpp-python>=0.3; extra == 'all'
+Requires-Dist: mlx-lm>=0.18; extra == 'all'
+Requires-Dist: mlx>=0.19; extra == 'all'
+Requires-Dist: onnxruntime-gpu>=1.18; extra == 'all'
+Requires-Dist: onnxruntime-rocm>=1.18; extra == 'all'
+Requires-Dist: onnxruntime-vitisai>=1.18; extra == 'all'
+Requires-Dist: openvino>=2026.0; extra == 'all'
+Requires-Dist: rknn-toolkit2>=2.0; extra == 'all'
+Requires-Dist: sentence-transformers>=3.0; extra == 'all'
+Provides-Extra: all-apple
+Requires-Dist: llama-cpp-python>=0.3; extra == 'all-apple'
+Requires-Dist: mlx-lm>=0.18; extra == 'all-apple'
+Requires-Dist: mlx>=0.19; extra == 'all-apple'
+Requires-Dist: sentence-transformers>=3.0; extra == 'all-apple'
+Provides-Extra: all-arm-cix
+Requires-Dist: llama-cpp-python>=0.3; extra == 'all-arm-cix'
+Provides-Extra: all-arm-rockchip
+Requires-Dist: llama-cpp-python>=0.3; extra == 'all-arm-rockchip'
+Requires-Dist: rknn-toolkit2>=2.0; extra == 'all-arm-rockchip'
+Provides-Extra: all-cpu
+Requires-Dist: llama-cpp-python>=0.3; extra == 'all-cpu'
+Requires-Dist: sentence-transformers>=3.0; extra == 'all-cpu'
+Provides-Extra: all-x86-cuda
+Requires-Dist: llama-cpp-python>=0.3; extra == 'all-x86-cuda'
+Requires-Dist: onnxruntime-gpu>=1.18; extra == 'all-x86-cuda'
+Provides-Extra: all-x86-intel
+Requires-Dist: llama-cpp-python>=0.3; extra == 'all-x86-intel'
+Requires-Dist: openvino>=2026.0; extra == 'all-x86-intel'
+Provides-Extra: all-x86-rocm
+Requires-Dist: llama-cpp-python>=0.3; extra == 'all-x86-rocm'
+Requires-Dist: onnxruntime-rocm>=1.18; extra == 'all-x86-rocm'
+Requires-Dist: onnxruntime-vitisai>=1.18; extra == 'all-x86-rocm'
+Provides-Extra: cpu-llamacpp
+Requires-Dist: llama-cpp-python>=0.3; extra == 'cpu-llamacpp'
+Provides-Extra: cpu-sbert
+Requires-Dist: sentence-transformers>=3.0; extra == 'cpu-sbert'
+Provides-Extra: dev
+Requires-Dist: mypy>=1.10; extra == 'dev'
+Requires-Dist: pytest>=8; extra == 'dev'
+Requires-Dist: ruff>=0.6; extra == 'dev'
+Provides-Extra: gpu-amd-rocm
+Requires-Dist: onnxruntime-rocm>=1.18; extra == 'gpu-amd-rocm'
+Provides-Extra: gpu-apple-mlx
+Requires-Dist: mlx-lm>=0.18; extra == 'gpu-apple-mlx'
+Requires-Dist: mlx>=0.19; extra == 'gpu-apple-mlx'
+Provides-Extra: gpu-intel-igpu
+Requires-Dist: openvino>=2026.0; extra == 'gpu-intel-igpu'
+Provides-Extra: gpu-nvidia-cuda
+Requires-Dist: onnxruntime-gpu>=1.18; extra == 'gpu-nvidia-cuda'
+Provides-Extra: gpu-nvidia-trt
+Requires-Dist: onnxruntime-gpu>=1.18; extra == 'gpu-nvidia-trt'
+Requires-Dist: tensorrt>=10.0; extra == 'gpu-nvidia-trt'
+Provides-Extra: gpu-vulkan
+Requires-Dist: llama-cpp-python>=0.3; extra == 'gpu-vulkan'
+Provides-Extra: npu-amd-xdna
+Requires-Dist: onnxruntime-vitisai>=1.18; extra == 'npu-amd-xdna'
+Provides-Extra: npu-cix
+Provides-Extra: npu-intel
+Requires-Dist: openvino>=2026.0; extra == 'npu-intel'
+Provides-Extra: npu-mediatek-apu
+Requires-Dist: mtk-genio-apu>=0.1; extra == 'npu-mediatek-apu'
+Provides-Extra: npu-rockchip
+Requires-Dist: rknn-toolkit2>=2.0; extra == 'npu-rockchip'
+Description-Content-Type: text/markdown
+
+> # 📍 Moved to GitLab
+> **The canonical, authoritative home of this project is GitLab — always:**
+> ## 👉 https://gitlab.com/ncz-os/mnemos-embedkit
+>
+> This GitHub repository is a **frozen, read-only mirror**. All development, issues, and releases happen on GitLab. Please open issues and merge requests there. The full history of this stub is preserved on GitLab.
+
+---
+
+# mnemos-embedkit
+
+> Open embedding devkit. Same API, every silicon.
+
+`embedkit` lets you embed text once and run it on whatever hardware your box has — Cix Sky1 NPU, Apple Silicon Metal/MLX, NVIDIA CUDA/TensorRT, AMD ROCm/XDNA, Intel iGPU/NPU via OpenVINO, MediaTek APU, Rockchip RKNN, or just the CPU. The kit detects what's installed and picks the fastest adapter at runtime. **No vendor preference.**
+
+## Quick start
+
+```python
+import embedkit
+
+eng = embedkit.Engine.auto()              # picks the fastest adapter on this host
+vec = eng.embed("Hello world")            # -> List[float]
+vecs = eng.embed_batch(["a", "b", "c"])   # -> List[List[float]]
+
+eng.info()
+# {"adapter": "cix-npu", "model": "bge-small-zh-v1.5_256.cix",
+#  "embed_dim": 512, "max_tokens": 256, "throughput_baseline": 55.0}
+```
+
+Explicit adapter pick:
+
+```python
+eng = embedkit.Engine(adapter="cix-npu",      model="bge-small-zh-v1.5")
+eng = embedkit.Engine(adapter="nvidia-cuda",  model="nomic-embed-text-v1.5")
+eng = embedkit.Engine(adapter="amd-rocm",     model="bge-large-en-v1.5")
+eng = embedkit.Engine(adapter="apple-mlx",    model="mxbai-embed-large-v1")
+eng = embedkit.Engine(adapter="cpu-llamacpp", model="bge-small-zh-v1.5")
+```
+
+## What the kit is
+
+A pure-Python adapter layer over vendor-specific embedding runtimes, plus a uniform `Engine.embed*` API and a canonical bench harness. **The kit does not bundle drivers or kernel modules.** It detects what the host OS already provides and binds to it:
+
+| Host has | Kit picks via |
+|---|---|
+| `cix-noe-umd 2.0.2` + `libnoe` (NCZ Magnetar / cixtech apt) | `npu-cix` adapter |
+| `onnxruntime-gpu` (CUDA driver from Linux distro) | `nvidia-cuda` adapter |
+| `tensorrt` python (NVIDIA tar/apt) | `nvidia-trt` adapter |
+| `onnxruntime-rocm` (AMD ROCm dkms) | `amd-rocm` adapter |
+| `onnxruntime-vitisai` (XDNA driver) | `amd-xdna` adapter |
+| `openvino` (Intel CPU/iGPU/NPU) | `intel-igpu` / `intel-npu` adapter |
+| `mlx` (Apple Silicon, macOS only) | `apple-mlx` adapter |
+| llama-cpp-python with Metal | `cpu-llamacpp` adapter (auto-detects Metal at runtime) |
+| llama-cpp-python with `-DGGML_VULKAN=1` | `gpu-vulkan` adapter |
+| `rknn-toolkit2` (Rockchip RK3588 / RK3576) | `rockchip-rknn` adapter |
+| `mtk-genio-apu` (MediaTek Genio) | `mediatek-apu` adapter |
+| nothing else | `cpu-llamacpp` (CPU baseline, ships GGUF) |
+
+## Install
+
+```bash
+# Pick the form-factor bundle that matches your host:
+pip install embedkit[all-cpu]                 # baseline, CPU only
+pip install embedkit[all-x86-cuda]            # CPU + NVIDIA CUDA
+pip install embedkit[all-x86-rocm]            # CPU + AMD ROCm + XDNA
+pip install embedkit[all-x86-intel]           # CPU + Intel iGPU + NPU via OpenVINO
+pip install embedkit[all-arm-cix]             # CPU + Cix NPU + Mali Vulkan
+pip install embedkit[all-arm-rockchip]        # CPU + Rockchip RKNN + Mali Vulkan
+pip install embedkit[all-apple]               # CPU + Apple MLX + Metal
+pip install embedkit[all]                     # everything
+```
+
+The kit pulls vendor *python bindings* from PyPI. Vendor *drivers* are managed by your OS package manager (cix-noe-umd via apt, nvidia-driver via ubuntu-drivers, rocm-dkms via amdgpu-install, intel-npu-driver via apt, etc.).
+
+## Reference bench
+
+The canonical multi-platform bench is in `benches/`. Run on your host:
+
+```bash
+embedkit-bench --corpus benches/corpora/mnemos-8038.json --engines auto
+```
+
+See `benches/results.md` for the cross-platform numbers we have today (Cix Sky1 NPU, Apple Silicon Metal, NVIDIA CUDA, x86 + ARM CPU, Pi 5, Pi 4).
+
+## Reference implementation consumer
+
+`ncz-os/mnemos` (the canonical MNEMOS memory layer) is the reference embedkit consumer. The plan is to migrate MNEMOS's embedding helper to call `embedkit.Engine(...)` directly. See `docs/mnemos-integration.md`.
+
+## License
+
+Apache-2.0.
+
+## Status
+
+**Bootstrap.** Design + cross-platform bench data exist. Adapter implementations are queued (Codex handoff prompt at `docs/CODEX-ADAPTER-HANDOFF.md`).
+
+See `docs/DESIGN.md` for the full architecture.
+
+
+## Build infrastructure & partners
+
+Continuous integration and package distribution for this project are generously
+supported by our open-source infrastructure partners:
+
+- **[GitLab](https://gitlab.com/)** — canonical source hosting and CI pipelines
+  (format / lint / test gates), via the
+  [GitLab for Open Source](https://about.gitlab.com/solutions/open-source/) program.
+- **[Buildkite](https://buildkite.com/)** — CI/CD orchestration with hosted macOS
+  and Linux agents, and our APT package registry host
+  (`packages.buildkite.com/ncz-os/ncz`), via the
+  [Buildkite Open Source](https://buildkite.com/pricing) program.
+
+Thank you to both for backing open-source software.

mnemos_embedkit-0.1.0a1/README.md

@@ -0,0 +1,112 @@
+> # 📍 Moved to GitLab
+> **The canonical, authoritative home of this project is GitLab — always:**
+> ## 👉 https://gitlab.com/ncz-os/mnemos-embedkit
+>
+> This GitHub repository is a **frozen, read-only mirror**. All development, issues, and releases happen on GitLab. Please open issues and merge requests there. The full history of this stub is preserved on GitLab.
+
+---
+
+# mnemos-embedkit
+
+> Open embedding devkit. Same API, every silicon.
+
+`embedkit` lets you embed text once and run it on whatever hardware your box has — Cix Sky1 NPU, Apple Silicon Metal/MLX, NVIDIA CUDA/TensorRT, AMD ROCm/XDNA, Intel iGPU/NPU via OpenVINO, MediaTek APU, Rockchip RKNN, or just the CPU. The kit detects what's installed and picks the fastest adapter at runtime. **No vendor preference.**
+
+## Quick start
+
+```python
+import embedkit
+
+eng = embedkit.Engine.auto()              # picks the fastest adapter on this host
+vec = eng.embed("Hello world")            # -> List[float]
+vecs = eng.embed_batch(["a", "b", "c"])   # -> List[List[float]]
+
+eng.info()
+# {"adapter": "cix-npu", "model": "bge-small-zh-v1.5_256.cix",
+#  "embed_dim": 512, "max_tokens": 256, "throughput_baseline": 55.0}
+```
+
+Explicit adapter pick:
+
+```python
+eng = embedkit.Engine(adapter="cix-npu",      model="bge-small-zh-v1.5")
+eng = embedkit.Engine(adapter="nvidia-cuda",  model="nomic-embed-text-v1.5")
+eng = embedkit.Engine(adapter="amd-rocm",     model="bge-large-en-v1.5")
+eng = embedkit.Engine(adapter="apple-mlx",    model="mxbai-embed-large-v1")
+eng = embedkit.Engine(adapter="cpu-llamacpp", model="bge-small-zh-v1.5")
+```
+
+## What the kit is
+
+A pure-Python adapter layer over vendor-specific embedding runtimes, plus a uniform `Engine.embed*` API and a canonical bench harness. **The kit does not bundle drivers or kernel modules.** It detects what the host OS already provides and binds to it:
+
+| Host has | Kit picks via |
+|---|---|
+| `cix-noe-umd 2.0.2` + `libnoe` (NCZ Magnetar / cixtech apt) | `npu-cix` adapter |
+| `onnxruntime-gpu` (CUDA driver from Linux distro) | `nvidia-cuda` adapter |
+| `tensorrt` python (NVIDIA tar/apt) | `nvidia-trt` adapter |
+| `onnxruntime-rocm` (AMD ROCm dkms) | `amd-rocm` adapter |
+| `onnxruntime-vitisai` (XDNA driver) | `amd-xdna` adapter |
+| `openvino` (Intel CPU/iGPU/NPU) | `intel-igpu` / `intel-npu` adapter |
+| `mlx` (Apple Silicon, macOS only) | `apple-mlx` adapter |
+| llama-cpp-python with Metal | `cpu-llamacpp` adapter (auto-detects Metal at runtime) |
+| llama-cpp-python with `-DGGML_VULKAN=1` | `gpu-vulkan` adapter |
+| `rknn-toolkit2` (Rockchip RK3588 / RK3576) | `rockchip-rknn` adapter |
+| `mtk-genio-apu` (MediaTek Genio) | `mediatek-apu` adapter |
+| nothing else | `cpu-llamacpp` (CPU baseline, ships GGUF) |
+
+## Install
+
+```bash
+# Pick the form-factor bundle that matches your host:
+pip install embedkit[all-cpu]                 # baseline, CPU only
+pip install embedkit[all-x86-cuda]            # CPU + NVIDIA CUDA
+pip install embedkit[all-x86-rocm]            # CPU + AMD ROCm + XDNA
+pip install embedkit[all-x86-intel]           # CPU + Intel iGPU + NPU via OpenVINO
+pip install embedkit[all-arm-cix]             # CPU + Cix NPU + Mali Vulkan
+pip install embedkit[all-arm-rockchip]        # CPU + Rockchip RKNN + Mali Vulkan
+pip install embedkit[all-apple]               # CPU + Apple MLX + Metal
+pip install embedkit[all]                     # everything
+```
+
+The kit pulls vendor *python bindings* from PyPI. Vendor *drivers* are managed by your OS package manager (cix-noe-umd via apt, nvidia-driver via ubuntu-drivers, rocm-dkms via amdgpu-install, intel-npu-driver via apt, etc.).
+
+## Reference bench
+
+The canonical multi-platform bench is in `benches/`. Run on your host:
+
+```bash
+embedkit-bench --corpus benches/corpora/mnemos-8038.json --engines auto
+```
+
+See `benches/results.md` for the cross-platform numbers we have today (Cix Sky1 NPU, Apple Silicon Metal, NVIDIA CUDA, x86 + ARM CPU, Pi 5, Pi 4).
+
+## Reference implementation consumer
+
+`ncz-os/mnemos` (the canonical MNEMOS memory layer) is the reference embedkit consumer. The plan is to migrate MNEMOS's embedding helper to call `embedkit.Engine(...)` directly. See `docs/mnemos-integration.md`.
+
+## License
+
+Apache-2.0.
+
+## Status
+
+**Bootstrap.** Design + cross-platform bench data exist. Adapter implementations are queued (Codex handoff prompt at `docs/CODEX-ADAPTER-HANDOFF.md`).
+
+See `docs/DESIGN.md` for the full architecture.
+
+
+## Build infrastructure & partners
+
+Continuous integration and package distribution for this project are generously
+supported by our open-source infrastructure partners:
+
+- **[GitLab](https://gitlab.com/)** — canonical source hosting and CI pipelines
+  (format / lint / test gates), via the
+  [GitLab for Open Source](https://about.gitlab.com/solutions/open-source/) program.
+- **[Buildkite](https://buildkite.com/)** — CI/CD orchestration with hosted macOS
+  and Linux agents, and our APT package registry host
+  (`packages.buildkite.com/ncz-os/ncz`), via the
+  [Buildkite Open Source](https://buildkite.com/pricing) program.
+
+Thank you to both for backing open-source software.