Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Radix Gateway API - Babylon, 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%2Fradixdlt.com%2Fradixdlt" | 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%2Fradixdlt.com%2Fradixdlt" | 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 Radix Gateway API - Babylon API.
Get Gateway Status
Preview Transaction
Submit Transaction
Access Radix Gateway API - Babylon payments resources via REST API
Patterns agents use Radix Gateway API - Babylon API for, with concrete tasks.
GET STARTED
★ Payments Operations
Use the Radix Gateway API - Babylon to perform payments operations programmatically. The API provides 36 endpoints covering core functionality including get gateway status, get network configuration, get construction metadata.
Call POST /status/gateway-status to get gateway status
Automated SubAPIs Management
Automate subapis operations by combining multiple Radix Gateway API - Babylon endpoints. Agents can get network configuration and then get construction metadata in a single workflow.
Call POST /status/network-configuration to get network configuration, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Radix Gateway API - Babylon 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 none tokens manually.
Search Jentic for 'get gateway status', load the operation schema, and execute with Jentic-managed credentials
36 endpoints — this api is exposed by the babylon radix gateway to enable clients to efficiently query current and historic state on the radixdlt ledger, and intelligently handle transaction submission.
METHOD
PATH
DESCRIPTION
/status/gateway-status
Get Gateway Status
/status/network-configuration
Get Network Configuration
/transaction/construction
Get Construction Metadata
/transaction/preview
Preview Transaction
/transaction/preview-v2
Preview Transaction V2
/transaction/submit
Submit Transaction
/transaction/committed-details
Get Committed Transaction Details
/transaction/status
Get Transaction Status
/status/gateway-status
Get Gateway Status
/status/network-configuration
Get Network Configuration
/transaction/construction
Get Construction Metadata
/transaction/preview
Preview Transaction
/transaction/preview-v2
Preview Transaction V2
/transaction/submit
Submit Transaction
/transaction/committed-details
Get Committed Transaction Details
/transaction/status
Get Transaction Status
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Radix Gateway API by hand means choosing between the mainnet.radixdlt.com and stokenet.radixdlt.com hosts and handling retries across its POST transaction and status operations yourself, even though it needs no auth. Through Jentic you install once, import Radix Gateway from the API Directory, and your agent calls it without wiring the request bodies.
Permission scoping
The Radix Gateway API carries its transaction and status targets in the request body rather than a resource id in the path, so limit the agent to the operations it needs, such as previewing a transaction or reading transaction status. You choose which operations are allowed, so a submit is not included unless you add it.
Credential isolation
Radix Gateway needs no credential, so there is nothing to store: your own Jentic One instance still runs the call without exposing any secret to the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'preview a Radix transaction' or 'check transaction status', and Jentic returns the matching Radix Gateway 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.
Stripe
Alternative payments API
Choose Stripe when you need a different approach to payments operations
Specific to using Radix Gateway API - Babylon API through Jentic.
What authentication does the Radix Gateway API - Babylon use?
The Radix Gateway API - Babylon uses no authentication. 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 get gateway status with the Radix Gateway API - Babylon?
Yes. Use the POST /status/gateway-status endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Radix Gateway API - Babylon?
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 get gateway status through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'get gateway status'. Jentic returns the matching Radix Gateway API - Babylon operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Radix Gateway API - Babylon have?
The Radix Gateway API - Babylon exposes 36 endpoints covering subapis, concepts, architecture operations.
Can I limit what my agent is allowed to do with the Radix Gateway API - Babylon?
Yes. Because you run your own self-hosted Jentic One instance, your own rules decide which Radix Gateway operations the agent may call, and the API carries its transaction and status targets in the request body rather than a path id, so you scope access at the operation level. You can allow read-only work such as previewing a transaction or checking transaction status while leaving out POST /transaction/submit, which is not included unless you explicitly add it. The agent can only invoke the operations you have permitted.
For Agents
Programmatically get gateway status, get network configuration. Covers 36 operations.
Use for: I need to gateway status, I want to network configuration, Search for construction metadata, Find all preview transaction
Not supported: Does not handle communications, crm, or developer tools - use for payments only.
This API is exposed by the Babylon Radix Gateway to enable clients to efficiently query current and historic state on the RadixDLT ledger, and intelligently handle transaction submission. It is designed for use by wallets and explorers, and for light queries from front-end dApps. For exchange/asset integrations, back-end dApp integrations, or simple use cases, you should consider using the Core AP. The API exposes 36 endpoints.
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>