okfsmith 0.1.0__tar.gz

okfsmith-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 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 2026 The okfsmith Authors
+
+   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.

okfsmith-0.1.0/PKG-INFO

@@ -0,0 +1,171 @@
+Metadata-Version: 2.4
+Name: okfsmith
+Version: 0.1.0
+Summary: Documents → OKF knowledge bundles
+Author: okfsmith-team
+License-Expression: Apache-2.0
+Keywords: okf,knowledge,markdown,cli,knowledge-graph
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: typer>=0.12
+Requires-Dist: pyyaml>=6
+Requires-Dist: rich>=13
+Requires-Dist: httpx>=0.27
+Requires-Dist: liteparse>=2
+Requires-Dist: markitdown[docx,pptx,xlsx]>=0.1
+Provides-Extra: mcp
+Requires-Dist: fastmcp>=2.0; extra == "mcp"
+Provides-Extra: ocr
+Requires-Dist: docling; extra == "ocr"
+Provides-Extra: test
+Requires-Dist: pytest>=8; extra == "test"
+Dynamic: license-file
+
+# okfsmith
+
+[![PyPI](https://img.shields.io/pypi/v/okfsmith.svg)](https://pypi.org/project/okfsmith/)
+[![Python](https://img.shields.io/pypi/pyversions/okfsmith.svg)](https://pypi.org/project/okfsmith/)
+[![License](https://img.shields.io/github/license/Bilal-Junaid-Jiwani/okfsmith.svg)](https://github.com/Bilal-Junaid-Jiwani/okfsmith/blob/main/LICENSE)
+
+**Forge messy documents into Google's Open Knowledge Format (OKF) v0.2 knowledge bundles.**
+
+okfsmith is a Python CLI that ingests messy sources — PDFs, markdown, wiki dumps, Notion exports — and emits spec-conformant OKF v0.2 bundles: markdown files with YAML frontmatter, an `index.md`, and a `log.md`. Every concept carries provenance (`sources[]`), a trust tier, and lifecycle metadata, and every bundle is checked by a built-in §11 validator. Serve it to your agents with one MCP command.
+
+## 60-second quickstart
+
+```bash
+# install via pip, or run straight from uvx
+pip install okfsmith
+
+# start a bundle
+okfsmith init ./kb
+
+# ingest a messy PDF — local, free parsing; no API keys needed
+okfsmith ingest ./kb docs/quarterly-report.pdf
+
+# validate against OKF §11
+okfsmith validate ./kb
+# 42 concepts · 0 errors · 3 warnings
+
+# serve it to your agent over MCP (stdio)
+uvx okfsmith mcp --bundle ./kb
+```
+
+Point any MCP-capable agent at the stdio server — tools are `search`, `get`, `list`, `neighbors`, `index` — and every answer traces back to `sources[]` in the bundle.
+
+## Why okfsmith
+
+OKF is a clean, LLM-readable knowledge standard. But the tooling around it all starts from clean inputs:
+
+| Starting point | What exists | The gap |
+|---|---|---|
+| Clean markdown | `okf-cli` (markdown → bundle) | — |
+| Code repositories | code-graph tools | — |
+| **Messy PDFs, wikis, Notion exports** | **nothing** | **← okfsmith** |
+
+Real-world knowledge lives in 200-page PDFs with broken reading order, sprawling Notion exports, and wiki dumps. okfsmith is the ingestion-first CLI that forges those into first-class OKF bundles:
+
+**parse → section → extract → link → emit → validate → serve**
+
+## Features
+
+- **Tiered parsing, free first.** Tier 1 is local and keyless: LiteParse for PDFs, MarkItDown for everything else — born-digital documents never leave your machine. Optional Tier 2 (Docling sidecar) and Tier 3 (cloud OCR, opt-in) cover scanned or pathological pages.
+- **2-pass LLM extraction.** A cheap model drafts concept JSON with a contextual situating prefix (doc title + section path + doc summary) stamped into each concept; a critic pass verifies contradictions, claim fidelity, and stubs. Claims become `[^source-id]` footnotes feeding `sources[]` — provenance is structural, not decorative. Local Ollama by default; hosted models only via env vars.
+- **OKF v0.2 native.** Only `type` is required in frontmatter. okfsmith also emits `sources[]`/provenance, `generated`/`verified` trust metadata, and `status`/`stale_after` lifecycle fields.
+- **§11 validator.** Implements the spec's three hard conformance rules, plus advisory lints (orphans, dead links, stubs, missing recommended fields, legacy v0.1 fields). Broken links are warnings, never errors (spec §6).
+- **One-command MCP server.** `uvx okfsmith mcp --bundle ./kb` — FastMCP over stdio.
+- **SKILL.md pack.** Ship agent instructions alongside your bundle so assistants know how to read it.
+- **Graph visualization.** `okfsmith graph` renders `viz.html` to browse the concept graph in a browser.
+
+## CLI reference
+
+| Command | What it does |
+|---|---|
+| `okfsmith init ./kb` | Scaffold a new OKF v0.2 bundle |
+| `okfsmith ingest ./kb <source>…` | Parse sources → extract concepts → link → emit |
+| `okfsmith validate ./kb` | Check OKF §11 conformance (hard rules + advisory lints) |
+| `okfsmith list ./kb` | List concepts in the bundle |
+| `okfsmith read ./kb <concept>` | Print a concept with its frontmatter |
+| `okfsmith graph ./kb` | Render `viz.html` for the concept graph |
+| `okfsmith mcp --bundle ./kb` | Serve the bundle over MCP (stdio) |
+
+`okfsmith <command> --help` shows full options. See [docs/OVERVIEW.md](docs/OVERVIEW.md) for the pipeline each command drives.
+
+## How it compares
+
+| | **okfsmith** | okf-cli | Go / Rust OKF tools | Graphify-style tools |
+|---|---|---|---|---|
+| Language | Python | Python | Go / Rust | varies |
+| Starts from | messy PDFs, wikis, Notion exports | clean markdown | existing bundles | code repos |
+| Primary job | **ingestion → OKF** | markdown → bundle | validation / conversion | code graphs |
+| Trust tiers + provenance | yes, v0.2 native | — | varies | n/a |
+| MCP server | yes, one command | — | varies | — |
+
+Honest framing: clean markdown in → `okf-cli` is fine. Validating or converting existing bundles → the Go/Rust tools do that well. okfsmith is Python-first and ingestion-first — it exists for the messy documents nobody else handles.
+
+## Trust tiers
+
+Every concept carries a trust tier, derived from the pipeline — no manual bookkeeping:
+
+| Tier | Meaning | Set when |
+|---|---|---|
+| `unverified` | Extracted, not yet confirmed | after ingest (default) |
+| `machine-confirmed` | Passed the critic verification pass | after Pass 2 of extraction |
+| `human-reviewed` | A person signed off | `verified:` stamped on review |
+
+Extraction stamps `generated: {by: <tool>/<model>, at: <timestamp>}`; `verified:` is only set after review. Together with `status` and `stale_after`, every concept answers four questions: what it is, where it came from, how much to trust it, and when to re-check it.
+
+## Configuration
+
+Zero config to start — Tier 1 parsing is local and free. LLM features default to a local Ollama model; set these only if you want hosted models:
+
+| Variable | Purpose | Default |
+|---|---|---|
+| `OKFSMITH_MODEL` | Model for 2-pass extraction | local Ollama model |
+| `ANTHROPIC_API_KEY` | Optional: use Anthropic models | unset (local only) |
+| `OPENAI_API_KEY` | Optional: use OpenAI models | unset (local only) |
+
+Keys are read from the environment only — never from files, flags, or the repo.
+
+## Development
+
+```bash
+git clone https://github.com/Bilal-Junaid-Jiwani/okfsmith
+cd okfsmith
+pip install -e .
+pytest
+```
+
+`src/` layout: `core/` holds the business logic (parsing, extraction, linking, validation, bundle I/O); `cli/` is the thin Typer layer. Optional extras: `.[mcp]`, `.[ocr]`. Every slice ships with tests; nothing merges without review.
+
+## Roadmap
+
+On the way to 1.0: first PyPI release, wider Tier 2/3 coverage for hard scans, incremental re-ingest with LLM-adjudicated dedup, richer advisory lints.
+
+What v1 will **not** do — by design:
+
+- **No vector database.** Search stays lexical + graph-based. Your bundle is plain files: grep it, diff it, version-control it.
+- **No attestation runtime.** okfsmith records provenance; it does not execute attestations.
+
+## Contributing
+
+Issues and PRs are welcome at [github.com/Bilal-Junaid-Jiwani/okfsmith](https://github.com/Bilal-Junaid-Jiwani/okfsmith). Conventional commits, tests with every change, no secrets in the repo.
+
+## License
+
+Apache-2.0 — see [LICENSE](https://github.com/Bilal-Junaid-Jiwani/okfsmith/blob/main/LICENSE).
+
+## Acknowledgments
+
+- Google's [Open Knowledge Format](https://github.com/GoogleCloudPlatform/open-knowledge-format) spec (v0.2) — the standard okfsmith implements.
+- LiteParse (Apache-2.0) and MarkItDown (MIT) — the free, local parsing backbone.
+- FastMCP, Typer, and Ollama — the serving, CLI, and local-model layers.

okfsmith-0.1.0/README.md

@@ -0,0 +1,139 @@
+# okfsmith
+
+[![PyPI](https://img.shields.io/pypi/v/okfsmith.svg)](https://pypi.org/project/okfsmith/)
+[![Python](https://img.shields.io/pypi/pyversions/okfsmith.svg)](https://pypi.org/project/okfsmith/)
+[![License](https://img.shields.io/github/license/Bilal-Junaid-Jiwani/okfsmith.svg)](https://github.com/Bilal-Junaid-Jiwani/okfsmith/blob/main/LICENSE)
+
+**Forge messy documents into Google's Open Knowledge Format (OKF) v0.2 knowledge bundles.**
+
+okfsmith is a Python CLI that ingests messy sources — PDFs, markdown, wiki dumps, Notion exports — and emits spec-conformant OKF v0.2 bundles: markdown files with YAML frontmatter, an `index.md`, and a `log.md`. Every concept carries provenance (`sources[]`), a trust tier, and lifecycle metadata, and every bundle is checked by a built-in §11 validator. Serve it to your agents with one MCP command.
+
+## 60-second quickstart
+
+```bash
+# install via pip, or run straight from uvx
+pip install okfsmith
+
+# start a bundle
+okfsmith init ./kb
+
+# ingest a messy PDF — local, free parsing; no API keys needed
+okfsmith ingest ./kb docs/quarterly-report.pdf
+
+# validate against OKF §11
+okfsmith validate ./kb
+# 42 concepts · 0 errors · 3 warnings
+
+# serve it to your agent over MCP (stdio)
+uvx okfsmith mcp --bundle ./kb
+```
+
+Point any MCP-capable agent at the stdio server — tools are `search`, `get`, `list`, `neighbors`, `index` — and every answer traces back to `sources[]` in the bundle.
+
+## Why okfsmith
+
+OKF is a clean, LLM-readable knowledge standard. But the tooling around it all starts from clean inputs:
+
+| Starting point | What exists | The gap |
+|---|---|---|
+| Clean markdown | `okf-cli` (markdown → bundle) | — |
+| Code repositories | code-graph tools | — |
+| **Messy PDFs, wikis, Notion exports** | **nothing** | **← okfsmith** |
+
+Real-world knowledge lives in 200-page PDFs with broken reading order, sprawling Notion exports, and wiki dumps. okfsmith is the ingestion-first CLI that forges those into first-class OKF bundles:
+
+**parse → section → extract → link → emit → validate → serve**
+
+## Features
+
+- **Tiered parsing, free first.** Tier 1 is local and keyless: LiteParse for PDFs, MarkItDown for everything else — born-digital documents never leave your machine. Optional Tier 2 (Docling sidecar) and Tier 3 (cloud OCR, opt-in) cover scanned or pathological pages.
+- **2-pass LLM extraction.** A cheap model drafts concept JSON with a contextual situating prefix (doc title + section path + doc summary) stamped into each concept; a critic pass verifies contradictions, claim fidelity, and stubs. Claims become `[^source-id]` footnotes feeding `sources[]` — provenance is structural, not decorative. Local Ollama by default; hosted models only via env vars.
+- **OKF v0.2 native.** Only `type` is required in frontmatter. okfsmith also emits `sources[]`/provenance, `generated`/`verified` trust metadata, and `status`/`stale_after` lifecycle fields.
+- **§11 validator.** Implements the spec's three hard conformance rules, plus advisory lints (orphans, dead links, stubs, missing recommended fields, legacy v0.1 fields). Broken links are warnings, never errors (spec §6).
+- **One-command MCP server.** `uvx okfsmith mcp --bundle ./kb` — FastMCP over stdio.
+- **SKILL.md pack.** Ship agent instructions alongside your bundle so assistants know how to read it.
+- **Graph visualization.** `okfsmith graph` renders `viz.html` to browse the concept graph in a browser.
+
+## CLI reference
+
+| Command | What it does |
+|---|---|
+| `okfsmith init ./kb` | Scaffold a new OKF v0.2 bundle |
+| `okfsmith ingest ./kb <source>…` | Parse sources → extract concepts → link → emit |
+| `okfsmith validate ./kb` | Check OKF §11 conformance (hard rules + advisory lints) |
+| `okfsmith list ./kb` | List concepts in the bundle |
+| `okfsmith read ./kb <concept>` | Print a concept with its frontmatter |
+| `okfsmith graph ./kb` | Render `viz.html` for the concept graph |
+| `okfsmith mcp --bundle ./kb` | Serve the bundle over MCP (stdio) |
+
+`okfsmith <command> --help` shows full options. See [docs/OVERVIEW.md](docs/OVERVIEW.md) for the pipeline each command drives.
+
+## How it compares
+
+| | **okfsmith** | okf-cli | Go / Rust OKF tools | Graphify-style tools |
+|---|---|---|---|---|
+| Language | Python | Python | Go / Rust | varies |
+| Starts from | messy PDFs, wikis, Notion exports | clean markdown | existing bundles | code repos |
+| Primary job | **ingestion → OKF** | markdown → bundle | validation / conversion | code graphs |
+| Trust tiers + provenance | yes, v0.2 native | — | varies | n/a |
+| MCP server | yes, one command | — | varies | — |
+
+Honest framing: clean markdown in → `okf-cli` is fine. Validating or converting existing bundles → the Go/Rust tools do that well. okfsmith is Python-first and ingestion-first — it exists for the messy documents nobody else handles.
+
+## Trust tiers
+
+Every concept carries a trust tier, derived from the pipeline — no manual bookkeeping:
+
+| Tier | Meaning | Set when |
+|---|---|---|
+| `unverified` | Extracted, not yet confirmed | after ingest (default) |
+| `machine-confirmed` | Passed the critic verification pass | after Pass 2 of extraction |
+| `human-reviewed` | A person signed off | `verified:` stamped on review |
+
+Extraction stamps `generated: {by: <tool>/<model>, at: <timestamp>}`; `verified:` is only set after review. Together with `status` and `stale_after`, every concept answers four questions: what it is, where it came from, how much to trust it, and when to re-check it.
+
+## Configuration
+
+Zero config to start — Tier 1 parsing is local and free. LLM features default to a local Ollama model; set these only if you want hosted models:
+
+| Variable | Purpose | Default |
+|---|---|---|
+| `OKFSMITH_MODEL` | Model for 2-pass extraction | local Ollama model |
+| `ANTHROPIC_API_KEY` | Optional: use Anthropic models | unset (local only) |
+| `OPENAI_API_KEY` | Optional: use OpenAI models | unset (local only) |
+
+Keys are read from the environment only — never from files, flags, or the repo.
+
+## Development
+
+```bash
+git clone https://github.com/Bilal-Junaid-Jiwani/okfsmith
+cd okfsmith
+pip install -e .
+pytest
+```
+
+`src/` layout: `core/` holds the business logic (parsing, extraction, linking, validation, bundle I/O); `cli/` is the thin Typer layer. Optional extras: `.[mcp]`, `.[ocr]`. Every slice ships with tests; nothing merges without review.
+
+## Roadmap
+
+On the way to 1.0: first PyPI release, wider Tier 2/3 coverage for hard scans, incremental re-ingest with LLM-adjudicated dedup, richer advisory lints.
+
+What v1 will **not** do — by design:
+
+- **No vector database.** Search stays lexical + graph-based. Your bundle is plain files: grep it, diff it, version-control it.
+- **No attestation runtime.** okfsmith records provenance; it does not execute attestations.
+
+## Contributing
+
+Issues and PRs are welcome at [github.com/Bilal-Junaid-Jiwani/okfsmith](https://github.com/Bilal-Junaid-Jiwani/okfsmith). Conventional commits, tests with every change, no secrets in the repo.
+
+## License
+
+Apache-2.0 — see [LICENSE](https://github.com/Bilal-Junaid-Jiwani/okfsmith/blob/main/LICENSE).
+
+## Acknowledgments
+
+- Google's [Open Knowledge Format](https://github.com/GoogleCloudPlatform/open-knowledge-format) spec (v0.2) — the standard okfsmith implements.
+- LiteParse (Apache-2.0) and MarkItDown (MIT) — the free, local parsing backbone.
+- FastMCP, Typer, and Ollama — the serving, CLI, and local-model layers.

okfsmith-0.1.0/pyproject.toml

@@ -0,0 +1,52 @@
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "okfsmith"
+version = "0.1.0"
+description = "Documents → OKF knowledge bundles"
+readme = "README.md"
+requires-python = ">=3.10"
+# PEP 639 SPDX license expression (audit-4: the old {text=...} form is deprecated).
+license = "Apache-2.0"
+license-files = ["LICENSE*"]
+authors = [{ name = "okfsmith-team" }]
+keywords = ["okf", "knowledge", "markdown", "cli", "knowledge-graph"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Text Processing :: Markup :: Markdown",
+]
+dependencies = [
+    "typer>=0.12",
+    "pyyaml>=6",
+    "rich>=13",
+    "httpx>=0.27",
+    # Tier-1 PDF parsing: liteparse (run-llama, Apache-2.0, prebuilt wheels).
+    # Fully offline: constructed with ocr_enabled=False, never calls paid OCR APIs.
+    # PyMuPDF deliberately avoided (AGPL).
+    "liteparse>=2",
+    # Office/misc formats (MIT). The docx/pptx/xlsx extras are needed for
+    # DOCX/PPTX/XLSX support (mammoth, python-pptx, openpyxl).
+    "markitdown[docx,pptx,xlsx]>=0.1",
+]
+
+[project.scripts]
+okfsmith = "okfsmith.cli.app:app"
+
+[project.optional-dependencies]
+mcp = ["fastmcp>=2.0"]
+ocr = ["docling"]
+test = ["pytest>=8"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

okfsmith-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

okfsmith-0.1.0/src/okfsmith/__init__.py

@@ -0,0 +1,8 @@
+"""okfsmith — Documents → OKF knowledge bundles.
+
+Converts messy documents (PDFs, markdown, wikis, exports) into Google's
+Open Knowledge Format (OKF) v0.2 knowledge bundles: markdown files with
+YAML frontmatter, plus reserved ``index.md`` / ``log.md`` files.
+"""
+
+__version__ = "0.1.0"

okfsmith-0.1.0/src/okfsmith/cli/__init__.py

@@ -0,0 +1,5 @@
+"""okfsmith CLI package."""
+
+# Importing commands registers them on the Typer app defined in
+# ``okfsmith.cli.app`` (the app module itself stays command-free).
+from okfsmith.cli import commands  # noqa: F401

okfsmith-0.1.0/src/okfsmith/cli/app.py

@@ -0,0 +1,36 @@
+"""okfsmith command-line interface.
+
+Minimal Typer app: only the ``--version`` callback lives here for now.
+The CLI engineer adds commands later — do not add commands in this module.
+"""
+
+from __future__ import annotations
+
+import typer
+
+from okfsmith import __version__
+
+app = typer.Typer(
+    help="Convert messy documents into OKF v0.2 knowledge bundles.",
+    add_completion=False,
+)
+
+
+def _version_callback(value: bool) -> None:
+    """Print the version and exit when ``--version`` is passed."""
+    if value:
+        typer.echo(f"okfsmith {__version__}")
+        raise typer.Exit()
+
+
+@app.callback()
+def main(
+    version: bool | None = typer.Option(
+        None,
+        "--version",
+        callback=_version_callback,
+        is_eager=True,
+        help="Show the okfsmith version and exit.",
+    ),
+) -> None:
+    """okfsmith — Documents → OKF knowledge bundles."""