Knwler is an enterprise document intelligence platform that extracts structured knowledge graphs from documents using Large Language Models. It identifies entities, relationships, and topics from PDFs, text files, and Markdown — producing interactive reports and exports for graph analytics platforms.

Can Knwler run fully on-premise?

Yes. Knwler supports fully air-gapped operation via Ollama with open-weight models. No data leaves your infrastructure, making it suitable for classified and regulated environments with strict data sovereignty requirements.

What languages does Knwler support?

Knwler auto-detects document language and supports English, German, French, Spanish, and Dutch out of the box. Additional languages can be added by extending a single configuration file.

What export formats are available?

Knwler exports to JSON, GML, GraphML, and interactive HTML. These can be imported directly into Neo4j, Gephi, yEd, Memgraph, SurrealDB, or used to generate vector embeddings for semantic search.

How much does it cost to process a document?

Using cloud LLMs (OpenAI GPT-4o), processing costs approximately $0.20 per 20-page document. Running on-premise with local models is completely free after initial setup. Intelligent caching means re-runs cost nothing.

n8n

Knwler can easily be integrated into n8n but you need to ensure the following:

install Knwler as a pipx app via pipx install knwler
add the pipx path to the n8n env variabels since the execution node does not load the zsh context (or whatever shell env you use)
run the execution node with knwler ... in the command

On Mac OS you need to add /Users/<user>/.local/bin to the path. For example, to run n8n as a service you would put the plist below into ~/Library/LaunchAgents/com.<user>.n8n.plist and load/start the service with

launchctl load ~/Library/LaunchAgents/com.<user>.n8n.plist

To stop/unload the service:

launchctl unload ~/Library/LaunchAgents/com.<user>.n8n.plist

Checking the status with launchctl list | grep n8n and view logs with tail -f ~/n8n/logs/n8n.log or tail -f ~/n8n/logs/n8n.error.log

The import part is the path /Users/<user>/.local/bin where the pipx knwler command resides:

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
    <dict>
        <key>Label</key>
        <string>com.<user>.n8n</string>

        <key>ProgramArguments</key>
        <array>
            <string>/Users/<user>/.nvm/versions/node/v22.16.0/bin/node</string>
            <string>/Users/<user>/.nvm/versions/node/v22.16.0/bin/n8n</string>
        </array>

        <key>EnvironmentVariables</key>
        <dict>
            <key>PATH</key>
            <string>
                /Users/<user>/.nvm/versions/node/v22.16.0/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin:/Users/<user>/conda/bin:/Users/<user>/.local/bin</string>
            <key>DB_TYPE</key>
            <string>postgresdb</string>
            <key>DB_POSTGRESDB_HOST</key>
            <string>localhost</string>
            <key>DB_POSTGRESDB_PORT</key>
            <string>5432</string>
            <key>DB_POSTGRESDB_DATABASE</key>
            <string>n8n</string>
            <key>DB_POSTGRESDB_USER</key>
            <string><user></string>
            <key>DB_POSTGRESDB_PASSWORD</key>
            <string>som3-passw0rd</string>
            <key>N8N_PORT</key>
            <string>13000</string>
            <key>N8N_USER_FOLDER</key>
            <string>/Users/<user>/n8n</string>
            <key>N8N_CUSTOM_EXTENSIONS</key>
            <string>/Users/<user>/n8n/custom</string>
            <key>N8N_RESTRICT_FILE_ACCESS_TO</key>
            <string></string>
            <key>N8N_ALLOW_EXECUTE_COMMAND</key>
            <string>true</string>
            <key>NODES_EXCLUDE</key>
            <string>[]</string>
            <key>N8N_ENABLE_NODE_DEV</key>
            <string>true</string>
            <key>N8N_DIAGNOSTICS_ENABLED</key>
            <string>false</string>
            <key>EXECUTIONS_DATA_PRUNE</key>
            <string>true</string>
            <key>EXECUTIONS_DATA_MAX_AGE</key>
            <string>1</string>
            <key>EXECUTIONS_DATA_MAX_COUNT</key>
            <string>1</string>
        </dict>

        <key>RunAtLoad</key>
        <true />

        <key>KeepAlive</key>
        <true />

        <key>StandardOutPath</key>
        <string>/Users/<user>/n8n/logs/n8n.log</string>

        <key>StandardErrorPath</key>
        <string>/Users/<user>/n8n/logs/n8n.error.log</string>

        <key>WorkingDirectory</key>
        <string>/Users/<user>/n8n</string>
    </dict>
</plist>