Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Framekeep Public 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%2Fframekeep.com%2Fframekeep" | 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%2Fframekeep.com%2Fframekeep" | 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 Framekeep Public API.
Retrieve the public API index of stable discovery endpoints and documentation links
Check Framekeep service health and read-only availability
Fetch the reviewed public product overview with canonical documentation links
Patterns agents use Framekeep Public API for, with concrete tasks.
★ Agent Service Discovery
An AI agent connected through Jentic can read Framekeep's public API index, confirm the service is healthy, and fetch the product overview before taking further action, without a developer wiring the Framekeep API by hand. Every operation is read-only and needs no credential.
GET STARTED
Fetch the public API index and confirm the service health status is healthy
Health Monitoring
Operators poll a lightweight endpoint to confirm a service is up. Framekeep's health check returns the current service status, and the index advertises the stable endpoints so a monitor knows what to watch.
Poll the Framekeep health endpoint and record whether the service is healthy
Product Metadata Lookup
Catalog and directory tools display a product overview and its documentation links. Framekeep returns the reviewed public product overview, its review date, and canonical resource links as structured metadata.
Fetch the public product overview and extract its documentation links
3 endpoints — the framekeep public api exposes a versioned, read-only discovery surface for framekeep, returning the public api index of stable endpoints, a service health check, and the reviewed public product overview with canonical documentation links.
METHOD
PATH
DESCRIPTION
/api/v1
Get the public API index
/api/v1/health
Check service health
/api/v1/product
Get public product metadata
/api/v1
Get the public API index
/api/v1/health
Check service health
/api/v1/product
Get public product metadata
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Framekeep Public API by hand still means discovering its endpoints, reading the index, and handling its versioning and deprecation headers yourself. Through Jentic you install once, import Framekeep from the API Directory, and your agent calls its read-only operations with nothing to configure.
Permission scoping
Framekeep's public API is read-only with three operations, so a rule can allow only the index, health, and product reads. You choose the operations the agent may call, and because none of them write, its reach is limited to reading public metadata.
Credential isolation
Framekeep's public endpoints need no credential, so there is nothing to store. When you connect a credentialed API through Jentic, its key is stored encrypted by your own Jentic One instance and injected at execution time, never entering the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get the API index' or 'check service health', and Jentic returns the matching Framekeep operation with its output shape so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Framekeep Public API through Jentic.
What authentication does the Framekeep Public API use?
The Framekeep Public API is read-only and public: its discovery, health, and product endpoints need no credential, per its OpenAPI spec. The spec declares a studio session cookie, but that is a human browser session for studio administration and is not accepted by the public v1 endpoints. Through Jentic you import and call the public endpoints with no key to store.
Can I check the Framekeep service health?
Yes. The health operation returns the current service status, and the API index lists the stable public endpoints so a monitor knows what to poll.
Can I limit what my agent is allowed to do with the Framekeep Public API?
Yes. The public API is read-only with three operations, so a rule can allow only the index, health, and product-metadata reads, and because there are no write operations, the agent cannot change anything. Every call it makes is logged.
Is there a Framekeep MCP server?
You do not need an MCP server to give your agent the Framekeep Public API. Jentic connects it directly from the API Directory: import Framekeep, and the agent calls its read-only operations by intent without loading another server's tool definitions into its context.
What are the rate limits for the Framekeep Public API?
The Framekeep Public API returns standard IETF RateLimit headers describing the current quota and reset time, but the OpenAPI spec does not state a fixed numeric ceiling. Check the Framekeep documentation at https://framekeep.com for current limits.
How do I read Framekeep product metadata through Jentic?
Search Jentic for an intent like 'get product metadata', and it returns Framekeep's product operation with its output shape so your agent can read the overview and its documentation links. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Read Framekeep's public API index of stable endpoints, check service health, and fetch the reviewed public product overview with documentation links. Read-only and public, with no gallery or account data exposed.
Use for: Get the Framekeep public API index, Check whether the Framekeep service is healthy, Fetch the public product overview for Framekeep, Find the canonical documentation links for Framekeep
Not supported: Does not expose galleries, accounts, tokens, or any mutating operation. Use for reading Framekeep's public API index, service health, and product metadata only.
The Framekeep Public API exposes a versioned, read-only discovery surface for Framekeep, returning the public API index of stable endpoints, a service health check, and the reviewed public product overview with canonical documentation links. It never returns gallery, account, or token-bearing data. The v1 contract is backward compatible, and deprecations are announced with Deprecation, Sunset, and successor-version Link headers before removal.
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>