DocMeld
Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, and AI-enriched metadata from research papers and books. Generate PRDs, workflows, topic clusters, and Claude Code skills from PDFs. No OCR required.
File Explorer
Download Latest Version (.zip)- speckit.analyze.md
- speckit.checklist.md
- speckit.clarify.md
- speckit.constitution.md
- speckit.implement.md
- speckit.plan.md
- speckit.specify.md
- speckit.tasks.md
- speckit.taskstoissues.md
- bug_report.yml
- feature_request.yml
- lint.yml
- publish.yml
- test.yml
- dependabot.yml
- PULL_REQUEST_TEMPLATE.md
- speckit.analyze.md
- speckit.checklist.md
- speckit.clarify.md
- speckit.constitution.md
- speckit.implement.md
- speckit.plan.md
- speckit.specify.md
- speckit.tasks.md
- speckit.taskstoissues.md
- package-lock.json
- constitution.md
- check-prerequisites.sh
- common.sh
- create-new-feature.sh
- setup-plan.sh
- update-agent-context.sh
- agent-file-template.md
- checklist-template.md
- plan-template.md
- spec-template.md
- tasks-template.md
- banner.png
- __init__.py
- docling_backend.py
- pptx_backend.py
- pymupdf_backend.py
- soffice_backend.py
- __init__.py
- element_extractor.py
- element_types.py
- filename_sanitizer.py
- processor.py
- __init__.py
- aggregator.py
- categorizer.py
- index_writer.py
- models.py
- reorganizer.py
- __init__.py
- deepseek_client.py
- metadata_extractor.py
- processor.py
- provider.py
- __init__.py
- generator.py
- models.py
- __init__.py
- markdown_renderer.py
- page_aggregator.py
- page_models.py
- processor.py
- title_tracker.py
- __init__.py
- generator.py
- models.py
- __init__.py
- content.py
- env_loader.py
- logging.py
- progress.py
- silver_io.py
- text.py
- __init__.py
- generator.py
- models.py
- __init__.py
- cli.py
- parser.py
- py.typed
- batch_bronze_silver.py
- batch_pipeline.py
- fix_summaries.py
- run_loop_prompts.py
- summarize.py
- summarize_bschool.py
- summarize_rl.py
- test_categories_schema.py
- test_element_schema.py
- generate_fixtures.py
- sample_complex.pdf
- sample_simple.pdf
- test_bronze_batch.py
- test_bronze_pipeline.py
- test_cli.py
- test_end_to_end.py
- test_gold_pipeline.py
- test_silver_pipeline.py
- test_aggregator.py
- test_categorizer.py
- test_deepseek_client.py
- test_docling_backend.py
- test_element_extractor.py
- test_element_types.py
- test_env_loader.py
- test_filename_sanitizer.py
- test_index_writer.py
- test_logging.py
- test_markdown_renderer.py
- test_parser.py
- test_pptx_backend.py
- test_prd_generator.py
- test_progress.py
- test_provider.py
- test_pymupdf_backend.py
- test_reorganizer.py
- test_skills_generator.py
- test_soffice_backend.py
- test_title_tracker.py
- test_workflow_generator.py
- conftest.py
- .env.local.example
- .gitignore
- CHANGELOG.md
- CONTRIBUTING.md
- LICENSE
- pyproject.toml
- README.md
- harness_coding.md
- pdf-engines.md
- PRD.md
- use-cases.md
- market-analysis.md
- requirements.md
- element-schema.json
- data-model.md
- evaluation.md
- optimization-plan.md
- plan.md
- quickstart.md
- research.md
- spec.md
- tasks.md
- requirements.md
- categories-schema.json
- data-model.md
- plan.md
- quickstart.md
- research.md
- spec.md
- tasks.md
- plan.md
- spec.md
- spec.md
- spec.md
- requirements.md
- element-schema.json
- data-model.md
- plan.md
- quickstart.md
- research.md
- spec.md
- tasks.md
- requirements.md
- element-schema.json
- data-model.md
- plan.md
- quickstart.md
- research.md
- spec.md
- tasks.md
- llm-provider.md
- audit-findings.md
- data-model.md
- plan.md
- research.md
- spec.md
- tasks.md
- .env.local.template
- .gitignore
- .pre-commit-config.yaml
- AGENTS.md
- CITATION.cff
- CLAUDE.md
- CODE_OF_CONDUCT.md
- README.md
- SECURITY.md
# Installation Guide
git clone https://github.com/agentii-ai/DocMeld
Downloads the entire project code from GitHub to your computer.
cd DocMeld
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- Python 3 Python is required to use pip.
pip install docmeld
Installs the package published on PyPI directly — no need to clone the source.
pip install docmeld[docling] # Docling backend (DOCX + advanced PDF)
Installs the package published on PyPI directly — no need to clone the source.
pip install docmeld[pptx] # PowerPoint (.pptx) via python-pptx
Installs the package published on PyPI directly — no need to clone the source.
pip install docmeld[office] # Everything: Docling + python-pptx
Installs the package published on PyPI directly — no need to clone the source.
Pulled directly from this repo's README.
3. Python
Easypip install docmeld
Installs the package published on PyPI directly — no need to clone the source.
pip install docmeld[docling] # Docling backend (DOCX + advanced PDF)
Installs the package published on PyPI directly — no need to clone the source.
pip install docmeld[pptx] # PowerPoint (.pptx) via python-pptx
Installs the package published on PyPI directly — no need to clone the source.
pip install docmeld[office] # Everything: Docling + python-pptx
Installs the package published on PyPI directly — no need to clone the source.
python3 -m venv venv
Runs the Python script (or module).
Pulled directly from this repo's README.