kgmd 0.1.0__tar.gz

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

@@ -0,0 +1,33 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[dev]"
+
+      - name: Lint
+        run: ruff check .
+
+      - name: Test
+        run: pytest -v

kgmd-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,30 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  id-token: write
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - 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

kgmd-0.1.0/.gitignore

@@ -0,0 +1,11 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+dist/
+build/
+.venv/
+.env
+*.db
+*.db-shm
+*.db-wal
+.kgmd/

kgmd-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 2Lines Software
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

kgmd-0.1.0/Makefile

@@ -0,0 +1,21 @@
+.PHONY: install test lint format build clean
+
+install:
+	pip install -e ".[dev]"
+
+test:
+	python -m pytest tests/ -v
+
+lint:
+	ruff check kgmd/ tests/
+
+format:
+	ruff format kgmd/ tests/
+	ruff check --fix kgmd/ tests/
+
+build:
+	python -m build
+
+clean:
+	rm -rf dist/ build/ *.egg-info
+	find . -type d -name __pycache__ -exec rm -rf {} +

kgmd-0.1.0/PKG-INFO

@@ -0,0 +1,202 @@
+Metadata-Version: 2.4
+Name: kgmd
+Version: 0.1.0
+Summary: A CLI that builds a knowledge graph from markdown files and exposes it via MCP
+Project-URL: Homepage, https://github.com/johncarpenter/kgmd
+Project-URL: Repository, https://github.com/johncarpenter/kgmd
+Project-URL: Issues, https://github.com/johncarpenter/kgmd/issues
+License-Expression: MIT
+License-File: LICENSE
+Keywords: entity-extraction,knowledge-graph,llm,markdown,mcp,rag,sqlite
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+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
+Classifier: Topic :: Database
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: click>=8.1
+Requires-Dist: fastembed>=0.4
+Requires-Dist: litellm>=1.50
+Requires-Dist: mcp>=1.0
+Requires-Dist: networkx>=3.2
+Requires-Dist: platformdirs>=4.0
+Requires-Dist: pydantic>=2.6
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rich>=13.7
+Requires-Dist: sqlite-vec>=0.1.6
+Provides-Extra: dev
+Requires-Dist: pytest-mock>=3.10; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: ruff>=0.4; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# kgmd
+
+A CLI that builds a knowledge graph from a directory of markdown files and exposes it via MCP.
+
+- Extracts entities and relations using any LLM (via [litellm](https://github.com/BerriAI/litellm))
+- Resolves duplicate entities using local embeddings + LLM verification
+- Induces a typed schema from the extracted data
+- Stores everything in a single SQLite file (powered by [sqlite-vec](https://github.com/asg017/sqlite-vec))
+- Exposes the graph via CLI queries and an [MCP](https://modelcontextprotocol.io/) server
+
+## Install
+
+```bash
+pip install kgmd
+```
+
+Or with [uv](https://github.com/astral-sh/uv):
+
+```bash
+uv tool install kgmd
+```
+
+### Requirements
+
+- Python 3.10+
+- An API key for any LLM provider supported by litellm (OpenRouter, OpenAI, Anthropic, etc.)
+- Embeddings run locally by default via [fastembed](https://github.com/qdrant/fastembed) (no API key needed)
+
+## Quickstart
+
+```bash
+# Initialize a corpus
+cd my-notes/
+kgmd init
+
+# Set your LLM API key
+export OPENROUTER_API_KEY="sk-..."
+
+# Build the knowledge graph (extract -> resolve -> induce)
+kgmd build
+
+# Query
+kgmd entities
+kgmd relations
+kgmd find "machine learning"
+kgmd entity "Brian Anderson"
+kgmd neighbors "Brian Anderson" --depth 2
+kgmd path "Brian Anderson" "Acme Corp"
+
+# Export
+kgmd export --format graphml --output graph.graphml
+
+# View induced schema
+kgmd schema
+
+# Corpus statistics
+kgmd stats
+```
+
+## How it works
+
+`kgmd build` runs three stages:
+
+1. **Extract** -- Each markdown file is chunked and sent to an LLM, which returns structured JSON with entities (people, organizations, projects, etc.) and relations between them.
+2. **Resolve** -- Entity mentions are embedded locally, clustered by cosine similarity, and duplicate clusters are verified by the LLM before merging.
+3. **Induce** -- Aggregate statistics about entity types and relation predicates are sent to the LLM, which produces a typed YAML schema with hierarchies.
+
+All state lives in `.kgmd/graph.db`, a single SQLite file. Re-running `kgmd build` is incremental -- unchanged files are skipped.
+
+## MCP Server
+
+`kgmd mcp` launches an MCP server over stdio, exposing 7 tools:
+
+| Tool | Description |
+|---|---|
+| `search` | Semantic search over chunks |
+| `get_entity` | Full entity record with mentions and relations |
+| `list_entities` | List entities, optionally filtered by type |
+| `get_neighbors` | Subgraph traversal around an entity |
+| `find_path` | Shortest path between two entities |
+| `list_relations` | List relations with optional filters |
+| `get_schema` | The current induced schema |
+
+### Claude Desktop setup
+
+Add to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):
+
+```json
+{
+  "mcpServers": {
+    "kgmd": {
+      "command": "kgmd",
+      "args": ["mcp"],
+      "cwd": "/path/to/your/corpus"
+    }
+  }
+}
+```
+
+## Configuration
+
+Per-corpus config lives in `.kgmd/config.yaml`. Global defaults in `~/.config/kgmd/config.yaml` (or the platform equivalent). Corpus config overrides global.
+
+```yaml
+embedding:
+  backend: fastembed                    # or "litellm" for API embeddings
+  model: BAAI/bge-small-en-v1.5
+
+llm:
+  model: openrouter/anthropic/claude-sonnet-4-5
+  temperature: 0.0
+  max_tokens: 4096
+  timeout_seconds: 120
+
+chunking:
+  max_chars: 4000
+  overlap_chars: 200
+  split_on: paragraph                   # or "heading", "fixed"
+
+extraction:
+  max_entities_per_chunk: 30
+  max_relations_per_chunk: 30
+  retry_on_parse_failure: 2
+
+resolution:
+  similarity_threshold: 0.85
+  llm_verify_clusters: true
+  max_cluster_size: 10
+
+induction:
+  include_attribute_summary: true
+  hierarchy_depth: 3
+```
+
+## Export formats
+
+```bash
+kgmd export --format jsonld   # JSON-LD with schema.org context
+kgmd export --format cypher   # Cypher CREATE statements (Neo4j)
+kgmd export --format graphml  # GraphML (Gephi, yEd)
+```
+
+## Development
+
+```bash
+git clone https://github.com/2lines/kgmd.git
+cd kgmd
+pip install -e .
+make test    # run tests
+make lint    # ruff check
+make format  # ruff format
+```
+
+**Note:** Your Python must be built with SQLite extension loading enabled. If using pyenv:
+
+```bash
+LDFLAGS="-L$(brew --prefix sqlite)/lib" \
+CPPFLAGS="-I$(brew --prefix sqlite)/include -DSQLITE_ENABLE_LOAD_EXTENSION" \
+PYTHON_CONFIGURE_OPTS="--enable-loadable-sqlite-extensions" \
+pyenv install 3.12
+```
+
+## License
+
+[MIT](LICENSE)

kgmd-0.1.0/README.md

@@ -0,0 +1,165 @@
+# kgmd
+
+A CLI that builds a knowledge graph from a directory of markdown files and exposes it via MCP.
+
+- Extracts entities and relations using any LLM (via [litellm](https://github.com/BerriAI/litellm))
+- Resolves duplicate entities using local embeddings + LLM verification
+- Induces a typed schema from the extracted data
+- Stores everything in a single SQLite file (powered by [sqlite-vec](https://github.com/asg017/sqlite-vec))
+- Exposes the graph via CLI queries and an [MCP](https://modelcontextprotocol.io/) server
+
+## Install
+
+```bash
+pip install kgmd
+```
+
+Or with [uv](https://github.com/astral-sh/uv):
+
+```bash
+uv tool install kgmd
+```
+
+### Requirements
+
+- Python 3.10+
+- An API key for any LLM provider supported by litellm (OpenRouter, OpenAI, Anthropic, etc.)
+- Embeddings run locally by default via [fastembed](https://github.com/qdrant/fastembed) (no API key needed)
+
+## Quickstart
+
+```bash
+# Initialize a corpus
+cd my-notes/
+kgmd init
+
+# Set your LLM API key
+export OPENROUTER_API_KEY="sk-..."
+
+# Build the knowledge graph (extract -> resolve -> induce)
+kgmd build
+
+# Query
+kgmd entities
+kgmd relations
+kgmd find "machine learning"
+kgmd entity "Brian Anderson"
+kgmd neighbors "Brian Anderson" --depth 2
+kgmd path "Brian Anderson" "Acme Corp"
+
+# Export
+kgmd export --format graphml --output graph.graphml
+
+# View induced schema
+kgmd schema
+
+# Corpus statistics
+kgmd stats
+```
+
+## How it works
+
+`kgmd build` runs three stages:
+
+1. **Extract** -- Each markdown file is chunked and sent to an LLM, which returns structured JSON with entities (people, organizations, projects, etc.) and relations between them.
+2. **Resolve** -- Entity mentions are embedded locally, clustered by cosine similarity, and duplicate clusters are verified by the LLM before merging.
+3. **Induce** -- Aggregate statistics about entity types and relation predicates are sent to the LLM, which produces a typed YAML schema with hierarchies.
+
+All state lives in `.kgmd/graph.db`, a single SQLite file. Re-running `kgmd build` is incremental -- unchanged files are skipped.
+
+## MCP Server
+
+`kgmd mcp` launches an MCP server over stdio, exposing 7 tools:
+
+| Tool | Description |
+|---|---|
+| `search` | Semantic search over chunks |
+| `get_entity` | Full entity record with mentions and relations |
+| `list_entities` | List entities, optionally filtered by type |
+| `get_neighbors` | Subgraph traversal around an entity |
+| `find_path` | Shortest path between two entities |
+| `list_relations` | List relations with optional filters |
+| `get_schema` | The current induced schema |
+
+### Claude Desktop setup
+
+Add to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):
+
+```json
+{
+  "mcpServers": {
+    "kgmd": {
+      "command": "kgmd",
+      "args": ["mcp"],
+      "cwd": "/path/to/your/corpus"
+    }
+  }
+}
+```
+
+## Configuration
+
+Per-corpus config lives in `.kgmd/config.yaml`. Global defaults in `~/.config/kgmd/config.yaml` (or the platform equivalent). Corpus config overrides global.
+
+```yaml
+embedding:
+  backend: fastembed                    # or "litellm" for API embeddings
+  model: BAAI/bge-small-en-v1.5
+
+llm:
+  model: openrouter/anthropic/claude-sonnet-4-5
+  temperature: 0.0
+  max_tokens: 4096
+  timeout_seconds: 120
+
+chunking:
+  max_chars: 4000
+  overlap_chars: 200
+  split_on: paragraph                   # or "heading", "fixed"
+
+extraction:
+  max_entities_per_chunk: 30
+  max_relations_per_chunk: 30
+  retry_on_parse_failure: 2
+
+resolution:
+  similarity_threshold: 0.85
+  llm_verify_clusters: true
+  max_cluster_size: 10
+
+induction:
+  include_attribute_summary: true
+  hierarchy_depth: 3
+```
+
+## Export formats
+
+```bash
+kgmd export --format jsonld   # JSON-LD with schema.org context
+kgmd export --format cypher   # Cypher CREATE statements (Neo4j)
+kgmd export --format graphml  # GraphML (Gephi, yEd)
+```
+
+## Development
+
+```bash
+git clone https://github.com/2lines/kgmd.git
+cd kgmd
+pip install -e .
+make test    # run tests
+make lint    # ruff check
+make format  # ruff format
+```
+
+**Note:** Your Python must be built with SQLite extension loading enabled. If using pyenv:
+
+```bash
+LDFLAGS="-L$(brew --prefix sqlite)/lib" \
+CPPFLAGS="-I$(brew --prefix sqlite)/include -DSQLITE_ENABLE_LOAD_EXTENSION" \
+PYTHON_CONFIGURE_OPTS="--enable-loadable-sqlite-extensions" \
+pyenv install 3.12
+```
+
+## License
+
+[MIT](LICENSE)

kgmd-0.1.0/kgmd/__init__.py

@@ -0,0 +1,3 @@
+"""kgmd — Knowledge graph from markdown files."""
+
+__version__ = "0.1.0"