Install Jentic One Beta

Connect the Hoplite API to your agent

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

Create projects and bind them to GitHub repositories

Start agent threads and send them messages to run work

Open, inspect, and merge pull requests from a thread

Start managed previews and issue gateway access to them

Create and run managed automations on a project

GET STARTED

Start building with Hoplite API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Hoplite API for, with concrete tasks.

★ Agent-Built Pull Requests

Turn a task into a reviewable pull request produced by a managed agent, instead of running an agent loop and git plumbing yourself. The API starts a thread on a project, takes the task as a message, and opens a pull request from the thread's workspace. Engineering teams use this to let agents propose changes that still go through review.

POST /api/threads to start a thread on a project, POST /api/threads/{id}/messages with the task, then POST /api/threads/{id}/pr to open a pull request.

Managed Preview Review

Give reviewers a running preview of an agent's change before it merges, without standing up preview infrastructure. The API starts a managed preview for a thread and issues gateway access to reach it. Teams use this to validate changes in a live environment as part of review.

POST /api/threads/{id}/preview/start to launch the managed preview, then GET /api/threads/{id}/preview/access to issue gateway access.

Project Automation

Schedule recurring agent work on a project so routine changes run without a human kicking off each one. The API creates a managed automation on a project and runs it on demand, and it exposes recent executions. Platform teams use this to automate repetitive maintenance across repositories.

POST /api/projects/{id}/automations to create a managed automation, then POST /api/projects/{id}/automations/{automationId}/run to run it.

Agent-Driven Software Factory

An AI agent drives a full change from task to pull request inside your own application through one API. Through Jentic the agent discovers the thread and pull-request operations, loads their schemas, and chains them without bespoke orchestration code. This lets a build assistant produce reviewed code changes directly.

Search Jentic for 'open a pull request', create a thread with POST /api/threads, drive it with POST /api/threads/{id}/messages, and open the pull request with POST /api/threads/{id}/pr.

Key Endpoints

86 endpoints — the hoplite api composes managed agent execution into your own application: it runs agent threads in persistent workspaces, opens and merges pull requests, serves previews, and gates tool approvals, all behind one organization-scoped api.

METHOD

PATH

DESCRIPTION

POST

/api/projects

Create a project

GET

/api/threads

List threads

POST

/api/threads

Create a thread

POST

/api/threads/{id}/messages

Send a thread message

POST

/api/threads/{id}/pr

Create a pull request

POST

/api/threads/{id}/pr/merge

Merge or enqueue the pull request head

GET

/api/source-control/github/repositories

List repositories

POST

/api/projects/{id}/automations

Create a managed automation

POST

/api/projects

Create a project

GET

/api/threads

List threads

POST

/api/threads

Create a thread

POST

/api/threads/{id}/messages

Send a thread message

POST

/api/threads/{id}/pr

Create a pull request

POST

/api/threads/{id}/pr/merge

Merge or enqueue the pull request head

GET

/api/source-control/github/repositories

List repositories

POST

/api/projects/{id}/automations

Create a managed automation

Why Jentic?

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

Setup

Wiring Hoplite by hand means handling either its X-Api-Key header or a bearer token, binding repositories, and sequencing the thread, preview, and pull-request operations yourself. Through Jentic you install once, import Hoplite from the API Directory, store the credential once, and your agent calls those operations in order.

Permission scoping

Hoplite puts the project and thread id in the URL path, such as /api/projects/{id} and /api/threads/{id}, so a rule can pin your agent to one project or thread. You choose the operations it may call, so destructive ones like deleting a project or merging a pull request are not included unless you add them.

Credential isolation

Your Hoplite API key or bearer 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 'open a pull request' or 'start an agent thread', and Jentic returns the matching Hoplite operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Hoplite API through Jentic.

Is there a Hoplite MCP server?

You do not need an MCP server to give your agent the Hoplite API. Jentic connects it directly from the API Directory: import Hoplite, store your credential once, and your agent calls the project, thread, and pull-request endpoints. Operations are discovered on demand, so no extra server's tool definitions load into the agent's context.

What authentication does the Hoplite API use?

The Hoplite API authenticates with an API key in the X-Api-Key header or a bearer token in the Authorization header, per its OpenAPI spec, and a browser session cookie is also supported for signed-in use. Through Jentic the credential is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.

Can I open and merge pull requests with the Hoplite API?

Yes. POST /api/threads/{id}/pr opens a pull request from a thread, GET /api/threads/{id}/pr/status reads its checks and reviews, and POST /api/threads/{id}/pr/merge merges or enqueues the expected head. Projects are bound to GitHub repositories, which the source-control endpoints list.

What are the rate limits for the Hoplite API?

The OpenAPI spec does not publish numeric request rate limits; Hoplite exposes the effective organization plan and runtime limits through its billing endpoints. Check the Hoplite documentation at https://hoplite.sh/docs for the current limits that apply to your plan.

How do I open a pull request through Jentic?

Search Jentic with the query 'open a pull request', create a thread with POST /api/threads, drive it with POST /api/threads/{id}/messages, then execute POST /api/threads/{id}/pr. To run it on your own infrastructure, install Jentic One from its GitHub repo.

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

Yes. Write a rule that allows only the read and thread operations under one project, such as GET /api/threads and POST /api/threads/{id}/messages, so the agent can run work and read results but cannot merge pull requests, delete projects, or rotate service-account credentials, and every call it makes is logged. Because project and thread ids live in the URL path, you can confine it to a single project.

Hoplite Sh Hoplite API

AI ReadinessFoundational (C+)59/100

See full scorecard

Official vendor OpenAPI document · agent-readyDeveloper ToolsSource ControlapiKey, bearer86 EndpointsREST

For Agents

Run managed agent threads bound to GitHub repositories, open and merge pull requests, serve previews, gate tool approvals, and run automations through one organization-scoped API.

Use for: Create a project bound to a GitHub repository, Start a new agent thread on a project, Send a message to an existing thread, Open a pull request from this thread

Not supported: Does not host your production runtime, store secrets as a vault, or sell compute directly. Use for managed agent threads, pull requests, previews, and project automations only.

The Hoplite API composes managed agent execution into your own application: it runs agent threads in persistent workspaces, opens and merges pull requests, serves previews, and gates tool approvals, all behind one organization-scoped API. It binds projects to GitHub repositories, creates and runs automations, and exposes runs, checkpoints, and usage. Use it to build a software factory where agents produce reviewed code changes rather than wiring the orchestration yourself.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: DSignals: 4

85%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

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

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

22%

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

74%

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: D+Signals: 4

38%

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.

55%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: ASignals: 1

88%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: CSignals: 1

53%

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: B+Signals: 1

68%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Hoplite API to your agent

Capabilities

Start building with Hoplite API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Hoplite Sh Hoplite API

Jentic AI Readiness Score

Hoplite 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