Install Jentic One Beta

Connect the Getosh API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Getosh 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%2Fgetosh.today%2Fgetosh" | sh

Step 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%2Fgetosh.today%2Fgetosh" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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.

Capabilities

What an agent can do with Getosh API.

Search the task list to find work to pick up

Update a task with scraped data once a worker has processed it

Append log entries to a task to record progress

Attach files to a task such as screenshots or exported results

Tie logs and output files to the task that produced them

GET STARTED

Start building with Getosh API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Getosh API for, with concrete tasks.

★ Agent-driven task worker

An AI agent acting as a worker can call the Getosh API through Jentic to search for a task to process, update it with the scraped data once done, and attach any output files. Jentic returns the task operations from a natural-language query, so the agent drives the queue without reading the Getosh reference first.

Search for an available task, update it with the scraped data once processed, and attach the result file to the same task.

Progress logging on a task

Append log entries to a task as a worker makes progress so an operator can follow what happened without re-running the job. The log operation records each step against the task, giving a timeline from pickup to completion.

Add a log entry to the task recording the step just completed, then confirm the entry is attached to that task.

Artifact attachment

Attach files such as screenshots or exported data to the task that produced them, keeping the output alongside the record of the work. Pipelines use this so every task carries its evidence rather than storing artifacts in a separate system.

Attach the exported result file to the completed task and confirm it is linked to that task.

Key Endpoints

4 endpoints — the getosh api tracks tasks and attaches the work done against them.

METHOD

PATH

DESCRIPTION

GET

/tasks

Search tasks

PUT

/tasks/{id}

Update a task with scraped data

POST

/tasks/{id}/log

Add a log entry to a task

POST

/tasks/{id}/files

Attach a file to a task

GET

/tasks

Search tasks

PUT

/tasks/{id}

Update a task with scraped data

POST

/tasks/{id}/log

Add a log entry to a task

POST

/tasks/{id}/files

Attach a file to a task

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring the Getosh API by hand means handling its bearer token and coding the task search, update, log, and file calls yourself. Through Jentic you install once, import the API from the API Directory, store the token once, and your agent calls it.

Permission scoping

Getosh puts the task id in the URL path, so a rule can pin your agent to one task and the operations you pick, such as searching and appending logs. You choose which operations it may call, so the update and file operations are not included unless you add them.

Credential isolation

Your Getosh token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'update a scraper task' or 'attach a file to a task', and Jentic returns the matching Getosh operation with its input schema so the agent calls the right endpoint without reading the reference docs.

FAQs

Specific to using Getosh API through Jentic.

Is there a Getosh API MCP server?

You do not need an MCP server to give your agent the Getosh API. Jentic connects it directly from the API Directory: import the API, store your token once, and your agent calls the task search, update, log, and file operations. Operations are discovered on demand, so no extra server definitions load into the agent's context.

What authentication does the Getosh API use?

The API authenticates with a bearer token per its OpenAPI spec, sent in the Authorization header on every task call. Through Jentic the token is stored encrypted in your own Jentic One instance and supplied only when an allowed call runs, so it never reaches the agent's context.

Can I attach files to a task with the Getosh API?

Yes. The file operation attaches a file such as a screenshot or exported result to a specific task by its id, and a separate log operation appends progress entries to the same task. Both keep the output tied to the task that produced it.

What are the rate limits for the Getosh API?

The OpenAPI spec does not specify rate limits. The surface is small and worker-oriented, so confirm the request limits that apply to your account in the Getosh documentation at https://app.getosh.today.

Can I limit what my agent is allowed to do with the Getosh API?

Yes. Getosh puts the task id in the URL path, so a rule can scope the agent to one task and the operations you pick, such as searching and appending logs, while leaving the update and file operations out of the allowed set, with every call logged.

How do I update a task with the Getosh API through Jentic?

Search Jentic for 'update a scraper task' to surface the task update operation, load its input schema, pass the task id and scraped data, and execute, then attach any result file. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Getosh Today Getosh API

AI ReadinessFoundational (D+)48/100

See full scorecard

Community OpenAPI document · agent-readyProductivityTask Managementbearer4 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Coordinate work through tasks: search the task list, update a task with scraped data, append log entries, and attach files such as screenshots or exported results.

Use for: Search for tasks that are ready to process, Update a task with the data I scraped, Add a log entry recording what a task did, Attach a screenshot file to a task

Not supported: Does not handle scheduling, billing, or user management. Use for retrieving and updating scraper tasks with logs and files only.

The Getosh API tracks tasks and attaches the work done against them. It searches the task list, updates a task with scraped data once a worker has processed it, appends log entries to a task to record progress, and attaches files to a task such as screenshots or exported results. The task is the unit of work that ties a request to its logs and outputs, so an automation can claim a task, record what it found, and hand back artifacts. It is aimed at scraping and worker pipelines that coordinate units of work through a shared task queue.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

100

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

99%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: A-Signals: 4

55%

Example Density

How richly the API is illustrated with examples.

94%

Example Validity

Percentage of examples that conform to their schemas.

50%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: DSignals: 4

34%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

50%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: A-Signals: 1

75%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: FSignals: 1

12%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Getosh API to your agent

Capabilities

Start building with Getosh API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Getosh Today Getosh API

Jentic AI Readiness Score

Getosh API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness