Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Sellsy API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fsellsy.com%2Fsellsy" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fsellsy.com%2Fsellsy" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Sellsy API.
Create a comment
Comments List
Get comment details
Update a comment
Delete a comment
GET STARTED
Search comments
Patterns agents use Sellsy API for, with concrete tasks.
★ Communications Operations
Use the Sellsy API to perform communications operations programmatically. The API provides 351 endpoints covering core functionality including create a comment, comments list, get comment details.
Call POST /comments to create a comment
Automated Invoices Management
Automate invoices operations by combining multiple Sellsy API endpoints. Agents can comments list and then get comment details in a single workflow.
Call GET /comments to comments list, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Sellsy API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle oauth2 tokens manually.
Search Jentic for 'create a comment', load the operation schema, and execute with Jentic-managed credentials
351 endpoints — find out the [postman collections](dist/postman/collectionsapiv2.
METHOD
PATH
DESCRIPTION
/comments
Create a comment
/comments
Comments List
/comments/{id}
Get comment details
/comments/{id}
Update a comment
/comments/{id}
Delete a comment
/comments/search
Search comments
/companies
Create a company
/companies
Companies List
/comments
Create a comment
/comments
Comments List
/comments/{id}
Get comment details
/comments/{id}
Update a comment
/comments/{id}
Delete a comment
/comments/search
Search comments
/companies
Create a company
/companies
Companies List
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Sellsy API by hand means running its OAuth2 flow, choosing between the authorization-code and client-credentials grants, refreshing tokens, and building each request across a large surface yourself. Through Jentic you install once, import Sellsy from the API Directory, store the OAuth credentials once, and your agent calls it.
Permission scoping
The Sellsy API puts the comment and company ids in the URL path (/comments/{id} and /companies/{id}), so a rule can pin your agent to one comment: it can read and update that comment and nothing else. You choose the operations it may call, so destructive ones like deleting a comment are not included unless you add them.
Credential isolation
Your Sellsy OAuth credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'create a comment' or 'search companies', and Jentic returns the matching Sellsy operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Sellsy API through Jentic.
What authentication does the Sellsy API use?
The Sellsy API uses OAuth 2.0 for authorization. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I create a comment with the Sellsy API?
Yes. Use the POST /comments endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Sellsy API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I create a comment through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'create a comment'. Jentic returns the matching Sellsy API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Sellsy API have?
The Sellsy API exposes 351 endpoints covering invoices, opportunities, credit notes operations.
Can I limit what my agent is allowed to do with the Sellsy API?
Yes. Because you run Jentic One yourself, your own rules decide which Sellsy operations and OAuth credentials the agent may use. Since the Sellsy API carries the comment and company ids in the URL path, such as /comments/{id} and /companies/{id}, a rule can pin the agent to a single comment or company so it only reads and updates that record. You also choose exactly which operations are exposed, so destructive calls like DELETE /comments/{id} stay unavailable unless you add them.
For Agents
Programmatically create a comment, comments list. Covers 351 operations with oauth2 authentication.
Use for: I need to a comment, I want to comments list, Search for comment details, Find all a comment
Not supported: Does not handle payments, crm, or developer tools - use for communications only.
Find out the [Postman collections](dist/postman/CollectionsApiV2.json) with the required [environment variables](dist/postman/Environment.json) Find out the [Changelog](changelog.html) Errors The errors are returned in JSON with the following format: The `details` field can contain an object that details the error. It is used in particular during validation to return the invalid fields | HTTP Code. The API exposes 351 endpoints secured with oauth2 authentication.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>