imgl 0.7.1__tar.gz

imgl-0.7.1/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 reasonable and customary use in 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 Additional Liability. 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 additional liability.
+
+   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 [yyyy] [name of copyright owner]
+
+   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.

imgl-0.7.1/PKG-INFO

@@ -0,0 +1,264 @@
+Metadata-Version: 2.4
+Name: imgl
+Version: 0.7.1
+Summary: Image to Layout — screenshot OCR and semantic UI reconstruction
+Author-email: Tom Sapletta <tom@sapletta.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/semcod/imgl
+Project-URL: Repository, https://github.com/semcod/imgl
+Project-URL: Issues, https://github.com/semcod/imgl/issues
+Keywords: screenshot,ocr,ui,layout,html,svg,vql
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pillow>=10.0
+Requires-Dist: pytesseract>=0.3.10
+Provides-Extra: capture
+Requires-Dist: mss>=9.0; extra == "capture"
+Provides-Extra: diagnose
+Requires-Dist: numpy>=1.24; extra == "diagnose"
+Provides-Extra: llm
+Requires-Dist: litellm>=1.30; extra == "llm"
+Requires-Dist: python-dotenv>=1.0; extra == "llm"
+Provides-Extra: full
+Requires-Dist: imgl[capture,dev,diagnose,llm]; extra == "full"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: goal>=2.1.0; extra == "dev"
+Requires-Dist: costs>=0.1.20; extra == "dev"
+Requires-Dist: pfix>=0.1.60; extra == "dev"
+Dynamic: license-file
+
+# imgl
+
+
+## AI Cost Tracking
+
+![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.7.1-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
+![AI Cost](https://img.shields.io/badge/AI%20Cost-$2.05-orange) ![Human Time](https://img.shields.io/badge/Human%20Time-2.0h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
+
+- 🤖 **LLM usage:** $2.0516 (2 commits)
+- 👤 **Human dev:** ~$200 (2.0h @ $100/h, 30min dedup)
+
+Generated on 2026-06-08 using [openrouter/qwen/qwen3-coder-next](https://openrouter.ai/qwen/qwen3-coder-next)
+
+---
+
+Image to Layout — convert screenshots into semantic UI models with OCR text and element bounding boxes.
+
+## Installation
+
+```bash
+pip install -e .              # from repo
+pip install -e ".[capture]"   # + screen capture (mss)
+pip install -e ".[diagnose]"   # numpy for img2nl (install img2nl locally)
+pip install -e ".[full]"      # capture + dev (no PyPI vql/img2vql)
+
+# Local siblings (not on PyPI):
+pip install -e ~/github/wronai/img2nl[analyze]
+pip install -e ~/github/oqlos/vql
+pip install -e ~/github/oqlos/vql/packages/img2vql
+```
+
+For `uri2vql adopt-imgl`, install imgl in the same venv as uri2vql:
+
+```bash
+pip install -e ~/github/semcod/imgl
+# or: pip install -e ~/github/oqlos/vql/packages/uri2vql[imgl]
+```
+
+System dependency for OCR:
+
+```bash
+# Debian/Ubuntu
+sudo apt install tesseract-ocr tesseract-ocr-pol
+
+# macOS
+brew install tesseract tesseract-lang
+```
+
+Development install:
+
+```bash
+pip install -e ".[dev]"
+```
+
+## Usage
+
+### Python API
+
+```python
+from imgl import analyze, scene_to_json
+
+scene = analyze("screen.png", lang="eng+pol")
+print(scene_to_json(scene))
+```
+
+### CLI
+
+```bash
+# Use an existing screenshot (recommended on GNOME/Wayland):
+imgl diagnose /tmp/screen.png
+imgl vql /tmp/screen.png -o layout.vql.json
+
+# Or capture (needs vql portal on Wayland — mss alone gives black screen):
+pip install -e ~/github/oqlos/vql   # portal/grim backends
+imgl capture --interactive -o screen.png
+imgl diagnose screen.png            # must show worth_analyzing: true
+
+# analyze / export (aborts on blank unless --allow-blank)
+imgl analyze /tmp/screen.png --json
+imgl analyze screen.png -o screen.imgl.json --lang eng+pol
+imgl html screen.png -o screen.html --embed-image
+imgl svg screen.png --mode overlay -o screen.svg
+imgl svg screen.png --mode wireframe -o screen.svg
+imgl vql screen.png -o layout.vql.json --with-grid
+```
+
+### Interactive shell (pick action from catalog)
+
+```bash
+imgl interact /tmp/screen.png -o layout.vql.json
+# numer opcji, NL: "kliknij Save", "mapa", "lista", "quit"
+# obraz z numerami jak w shellu:
+imgl annotate screen.png --open
+imgl interact screen.png --annotate --open
+# lepsza lista (filtr szumu OCR):
+imgl interact screen.png
+# vision LLM (wymaga OPENROUTER_API_KEY + pip install -e ".[llm]"):
+imgl interact screen.png --llm --annotate --open
+# opcjonalnie wykonaj na pulpicie:
+imgl interact /tmp/screen.png --execute   # wymaga xdotool lub ydotool
+```
+
+URI DSL (`vql://window/imgl?action=...`):
+
+| action | opis |
+|--------|------|
+| `analyze` | OCR + layout → VQL JSON (domyślne) |
+| `list` | lista elementów interaktywnych |
+| `annotate` | PNG ze zrzutu + numerowane ramki |
+| `click` | `text=`, `element_id=`, `window=` |
+| `type` | `value=`, `label=`, `text=` |
+
+Via `uri2vql` (when installed):
+
+```bash
+uri2vql query 'vql://window/imgl?image=/tmp/screen.png&file=layout.vql.json&lang=eng'
+uri2vql query 'vql://window/imgl?image=/tmp/screen.png&file=layout.vql.json&action=list'
+uri2vql query 'vql://window/imgl?image=/tmp/screen.png&file=layout.vql.json&action=click&text=Save'
+# For Polish+English OCR in URI use encoded plus: lang=eng%2Bpol
+```
+
+NL → URI (`nlp2uri` / `imgl` built-in):
+
+```bash
+# w shellu imgl interact: "kliknij Save", "wpisz test w search", "2", "lista"
+```
+
+### HTML / SVG export
+
+```python
+from imgl import analyze, scene_to_html, scene_to_svg
+
+scene = analyze("screen.png")
+html = scene_to_html(scene, embed_image=True)
+svg = scene_to_svg(scene, mode="overlay", background="screen.png")
+```
+
+HTML uses absolutely positioned elements with `data-type`, `data-id`, `data-text` attributes
+for text-based automation (`button[data-text="Save"]`).
+
+SVG supports `wireframe` (flat debug view) and `overlay` (boxes on top of screenshot).
+
+## Output format
+
+`analyze()` returns a `Scene` with:
+
+- `windows` — detected UI windows/panels (local heuristics or optional `img2vql`)
+- `elements` — classified UI elements: `button`, `input`, `label`, `text`, `toolbar`
+- `ocr_boxes` — raw OCR word boxes with confidence scores
+
+Example JSON:
+
+```json
+{
+  "version": "1.0",
+  "scene": {"width": 800, "height": 600, "source_image": "screen.png"},
+  "windows": [{
+    "id": "win-screen",
+    "bbox": {"x": 0, "y": 0, "w": 800, "h": 600},
+    "title": null,
+    "z": 0,
+    "elements": [
+      {"id": "text-0", "type": "text", "text": "Save", "bbox": {"x": 100, "y": 50, "w": 40, "h": 16}}
+    ]
+  }],
+  "ocr_boxes": [],
+  "metadata": {"ocr_backend": "tesseract", "lang": "eng+pol"}
+}
+```
+
+## Configuration
+
+```python
+from imgl import ImglConfig, analyze
+
+scene = analyze("screen.png", config=ImglConfig(
+    lang="eng+pol",
+    use_img2vql=True,      # use img2vql when installed, else local detect
+    detect_inputs=True,
+    label_proximity_px=40,
+))
+```
+
+### VQL export
+
+```python
+from imgl import analyze, scene_to_vql, write_vql_program
+
+scene = analyze("screen.png")
+program = scene_to_vql(scene, include_grid=True, grid=12)
+write_vql_program(scene, "layout.vql.json")
+```
+
+Layers: `windows`, `ui_elements` (with OCR text in metadata), `text_regions`, optional `screen_regions`.
+
+### Text-based actions
+
+```python
+from imgl import analyze, actions
+
+scene = analyze("screen.png")
+ui = actions(scene)
+
+ui.click("button", text="Save")
+# {"action": "click", "x": 310, "y": 206, ...}
+
+ui.type_into("alice", label="Username")
+# {"action": "type", "x": 245, "y": 99, "text": "alice", ...}
+```
+
+CLI:
+
+```bash
+imgl find screen.png --type button --text Save --click
+imgl find screen.png --label Username --type-into alice
+imgl find screen.png --list
+```
+
+## Roadmap
+
+- `nlp2uri` phrases for `vql://window/imgl`
+- koru desktop bridge for action execution
+
+## License
+
+Licensed under Apache-2.0.

imgl-0.7.1/README.md

@@ -0,0 +1,226 @@
+# imgl
+
+
+## AI Cost Tracking
+
+![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.7.1-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
+![AI Cost](https://img.shields.io/badge/AI%20Cost-$2.05-orange) ![Human Time](https://img.shields.io/badge/Human%20Time-2.0h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
+
+- 🤖 **LLM usage:** $2.0516 (2 commits)
+- 👤 **Human dev:** ~$200 (2.0h @ $100/h, 30min dedup)
+
+Generated on 2026-06-08 using [openrouter/qwen/qwen3-coder-next](https://openrouter.ai/qwen/qwen3-coder-next)
+
+---
+
+Image to Layout — convert screenshots into semantic UI models with OCR text and element bounding boxes.
+
+## Installation
+
+```bash
+pip install -e .              # from repo
+pip install -e ".[capture]"   # + screen capture (mss)
+pip install -e ".[diagnose]"   # numpy for img2nl (install img2nl locally)
+pip install -e ".[full]"      # capture + dev (no PyPI vql/img2vql)
+
+# Local siblings (not on PyPI):
+pip install -e ~/github/wronai/img2nl[analyze]
+pip install -e ~/github/oqlos/vql
+pip install -e ~/github/oqlos/vql/packages/img2vql
+```
+
+For `uri2vql adopt-imgl`, install imgl in the same venv as uri2vql:
+
+```bash
+pip install -e ~/github/semcod/imgl
+# or: pip install -e ~/github/oqlos/vql/packages/uri2vql[imgl]
+```
+
+System dependency for OCR:
+
+```bash
+# Debian/Ubuntu
+sudo apt install tesseract-ocr tesseract-ocr-pol
+
+# macOS
+brew install tesseract tesseract-lang
+```
+
+Development install:
+
+```bash
+pip install -e ".[dev]"
+```
+
+## Usage
+
+### Python API
+
+```python
+from imgl import analyze, scene_to_json
+
+scene = analyze("screen.png", lang="eng+pol")
+print(scene_to_json(scene))
+```
+
+### CLI
+
+```bash
+# Use an existing screenshot (recommended on GNOME/Wayland):
+imgl diagnose /tmp/screen.png
+imgl vql /tmp/screen.png -o layout.vql.json
+
+# Or capture (needs vql portal on Wayland — mss alone gives black screen):
+pip install -e ~/github/oqlos/vql   # portal/grim backends
+imgl capture --interactive -o screen.png
+imgl diagnose screen.png            # must show worth_analyzing: true
+
+# analyze / export (aborts on blank unless --allow-blank)
+imgl analyze /tmp/screen.png --json
+imgl analyze screen.png -o screen.imgl.json --lang eng+pol
+imgl html screen.png -o screen.html --embed-image
+imgl svg screen.png --mode overlay -o screen.svg
+imgl svg screen.png --mode wireframe -o screen.svg
+imgl vql screen.png -o layout.vql.json --with-grid
+```
+
+### Interactive shell (pick action from catalog)
+
+```bash
+imgl interact /tmp/screen.png -o layout.vql.json
+# numer opcji, NL: "kliknij Save", "mapa", "lista", "quit"
+# obraz z numerami jak w shellu:
+imgl annotate screen.png --open
+imgl interact screen.png --annotate --open
+# lepsza lista (filtr szumu OCR):
+imgl interact screen.png
+# vision LLM (wymaga OPENROUTER_API_KEY + pip install -e ".[llm]"):
+imgl interact screen.png --llm --annotate --open
+# opcjonalnie wykonaj na pulpicie:
+imgl interact /tmp/screen.png --execute   # wymaga xdotool lub ydotool
+```
+
+URI DSL (`vql://window/imgl?action=...`):
+
+| action | opis |
+|--------|------|
+| `analyze` | OCR + layout → VQL JSON (domyślne) |
+| `list` | lista elementów interaktywnych |
+| `annotate` | PNG ze zrzutu + numerowane ramki |
+| `click` | `text=`, `element_id=`, `window=` |
+| `type` | `value=`, `label=`, `text=` |
+
+Via `uri2vql` (when installed):
+
+```bash
+uri2vql query 'vql://window/imgl?image=/tmp/screen.png&file=layout.vql.json&lang=eng'
+uri2vql query 'vql://window/imgl?image=/tmp/screen.png&file=layout.vql.json&action=list'
+uri2vql query 'vql://window/imgl?image=/tmp/screen.png&file=layout.vql.json&action=click&text=Save'
+# For Polish+English OCR in URI use encoded plus: lang=eng%2Bpol
+```
+
+NL → URI (`nlp2uri` / `imgl` built-in):
+
+```bash
+# w shellu imgl interact: "kliknij Save", "wpisz test w search", "2", "lista"
+```
+
+### HTML / SVG export
+
+```python
+from imgl import analyze, scene_to_html, scene_to_svg
+
+scene = analyze("screen.png")
+html = scene_to_html(scene, embed_image=True)
+svg = scene_to_svg(scene, mode="overlay", background="screen.png")
+```
+
+HTML uses absolutely positioned elements with `data-type`, `data-id`, `data-text` attributes
+for text-based automation (`button[data-text="Save"]`).
+
+SVG supports `wireframe` (flat debug view) and `overlay` (boxes on top of screenshot).
+
+## Output format
+
+`analyze()` returns a `Scene` with:
+
+- `windows` — detected UI windows/panels (local heuristics or optional `img2vql`)
+- `elements` — classified UI elements: `button`, `input`, `label`, `text`, `toolbar`
+- `ocr_boxes` — raw OCR word boxes with confidence scores
+
+Example JSON:
+
+```json
+{
+  "version": "1.0",
+  "scene": {"width": 800, "height": 600, "source_image": "screen.png"},
+  "windows": [{
+    "id": "win-screen",
+    "bbox": {"x": 0, "y": 0, "w": 800, "h": 600},
+    "title": null,
+    "z": 0,
+    "elements": [
+      {"id": "text-0", "type": "text", "text": "Save", "bbox": {"x": 100, "y": 50, "w": 40, "h": 16}}
+    ]
+  }],
+  "ocr_boxes": [],
+  "metadata": {"ocr_backend": "tesseract", "lang": "eng+pol"}
+}
+```
+
+## Configuration
+
+```python
+from imgl import ImglConfig, analyze
+
+scene = analyze("screen.png", config=ImglConfig(
+    lang="eng+pol",
+    use_img2vql=True,      # use img2vql when installed, else local detect
+    detect_inputs=True,
+    label_proximity_px=40,
+))
+```
+
+### VQL export
+
+```python
+from imgl import analyze, scene_to_vql, write_vql_program
+
+scene = analyze("screen.png")
+program = scene_to_vql(scene, include_grid=True, grid=12)
+write_vql_program(scene, "layout.vql.json")
+```
+
+Layers: `windows`, `ui_elements` (with OCR text in metadata), `text_regions`, optional `screen_regions`.
+
+### Text-based actions
+
+```python
+from imgl import analyze, actions
+
+scene = analyze("screen.png")
+ui = actions(scene)
+
+ui.click("button", text="Save")
+# {"action": "click", "x": 310, "y": 206, ...}
+
+ui.type_into("alice", label="Username")
+# {"action": "type", "x": 245, "y": 99, "text": "alice", ...}
+```
+
+CLI:
+
+```bash
+imgl find screen.png --type button --text Save --click
+imgl find screen.png --label Username --type-into alice
+imgl find screen.png --list
+```
+
+## Roadmap
+
+- `nlp2uri` phrases for `vql://window/imgl`
+- koru desktop bridge for action execution
+
+## License
+
+Licensed under Apache-2.0.