Use Nanonets from Claude
Add the Nanonets connection to a Space that runs Claude, then use it from every channel in that Space.
Connect Nanonets once, then control which Spaces can use its approved tools and data without pasting credentials into prompts or threads.
Add the Nanonets connection to a Space that runs Claude, then use it from every channel in that Space.
Add the Nanonets connection to a Space that runs Codex, then use it from every channel in that Space.
Connect your own OpenClaw to Sidekick while type.com provides the conversations, permissions, connections, skills, and automations.
Nanonets extracts structured data from documents like invoices and receipts using trained OCR and classification models. In a type.com Space, an operations team can ask Claude to check which models exist, review predictions pulled from a batch of scanned files, or retire a model that's no longer used.
Connect Nanonets once, then decide which Spaces can use it in threads, skills, automations, and coding work.
List every OCR and classification model in the account, with its accuracy and extractable fields, before deciding whether to train a new one.
List all Nanonets models we have and tell me which ones are set up for invoice extraction.
Pull the prediction files for a model to see the extracted text and field values from documents that have already been processed.
Get the prediction files for our receipts model in Nanonets from this week's uploads.
Create a new model with a starting list of categories before uploading training images, so a new document type can be processed.
Create a new Nanonets model for processing shipping labels with categories for sender, recipient, and tracking number.
Initializes a new OCR or classification model with a starting list of categories, before training images are uploaded.
Permanently removes a trained OCR model and its training data, so use it only once the model is no longer needed.
Lists every model in the account with its type, status, accuracy, and extractable fields.
Returns documents already processed by a model, including extracted text, field values, and file links.
Returns full metadata for one OCR model by its ID.
Nanonets provides intelligent document processing APIs for extracting structured data from unstructured documents. Integrations can upload files, run OCR/extraction models, classify documents, retrieve parsed fields, automate approvals, and connect invoices, receipts, forms, IDs, and enterprise document workflows.
Yes. With a Nanonets connection shared to a type.com Space, Claude can list models, pull predictions from processed documents, and check model details, all from a thread.
Nanonets uses an API key, added once by an admin when creating the connection. Spaces that need document processing can use it without handling the key.
Yes. A recurring check, like pulling the day's processed invoices for review, can be set up as a type.com automation.
Not exactly. type.com uses connectors and connections to give selected Spaces access to approved app tools and data. Some connectors use hosted MCP, while others use OAuth, API keys, service accounts, or custom APIs.
Connect Google Ads to Claude in type.com with OAuth or a service account so your team can pull Ads account data and run campaign reporting in threads.
Connect Google Analytics to Claude in type.com to pull GA4 traffic and conversion numbers for a property from a shared marketing thread.
Connect PostHog to Claude in type.com to add people to static cohorts, share dashboards with collaborators, and assign project and organization roles.
Connect PostgreSQL to Claude in type.com so your team can query production data, inspect schemas, and review results without a separate SQL client.