Build with Kendr

Use Kendr through its API, CLI, SDK guidance, OAuth flows, model endpoints, connectors, and reusable skill and workflow formats.

Documentation index

Published guides
35
Documentation areas
8
Endpoint reference
https://kendr.org/docs/api-reference.html
OpenAPI description
https://kendr.org/docs/openapi.json
Live model catalog
https://kendr.org/api/public/models

Getting started

Create an account, install the desktop app, and finish a first task end to end.

  • Documentation home (https://kendr.org/docs/index.html) — Find the right guide for Kendr Cloud, Desktop, the developer API, billing, skills, and MCP. For everyone.
  • Your First Cited Answer (https://kendr.org/docs/first-cited-answer.html) — The shortest path from a new account to one research answer whose sources you can open and check. For new kendr users.
  • Getting started (https://kendr.org/docs/getting-started.html) — Sign up or log in, download Kendr Desktop, install it, sign in, and begin using Kendr. For new kendr users.

API essentials

Start with a key, choose a client, and make your first API call.

  • Developer documentation (https://kendr.org/docs/developer-api.html) — Learn the API one step at a time: client setup, model features, production guides, and worked projects. For developers.
  • API quickstart (https://kendr.org/docs/api-quickstart.html) — Create a scoped key, send your first request, and read the response. For developers.
  • HTTP, cURL and PowerShell (https://kendr.org/docs/api-http.html) — Make requests without an SDK and inspect response bodies and status codes. For developers.
  • OpenAI Python SDK (https://kendr.org/docs/api-openai-python.html) — Install the Python client, call Chat Completions and Responses, and pass Kendr-specific options. For developers.
  • OpenAI JavaScript SDK (https://kendr.org/docs/api-openai-javascript.html) — Call Kendr from Node.js or TypeScript with Responses, custom fields, and explicit error handling. For developers.
  • Other clients and migration (https://kendr.org/docs/api-compatible-clients.html) — Configure Anthropic clients, agent harnesses, Vercel AI SDK, and source-included helpers. For developers.
  • Authentication and SDKs (https://kendr.org/docs/auth-and-sdks.html) — API keys, sessions, OAuth, and the JavaScript and Python client kits. For developers.

Model features

Add routing, streaming, structured output, tools, and images.

  • Models and routing (https://kendr.org/docs/api-models.html) — Discover aliases and capabilities, choose a route, and inspect optimization receipts. For developers.
  • Streaming responses (https://kendr.org/docs/api-streaming.html) — Display partial text, distinguish stream formats, and recover interrupted requests. For developers.
  • Realtime Voice API (https://kendr.org/docs/api-voice.html) — Build spoken conversations over WebSockets with PCM audio, transcripts, explicit voices, and bounded session renewal. For developers.
  • Structured JSON output (https://kendr.org/docs/api-structured-output.html) — Constrain output to a schema and validate it before using it in application logic. For developers.
  • Tools and connected apps (https://kendr.org/docs/api-tools.html) — Choose web search, connected apps, or custom MCP and understand who executes tools. For developers.
  • Web search and grounding (https://kendr.org/docs/api-web-search.html) — Request current information and require grounded answers when sources are essential. For developers.
  • Attach MCP servers (https://kendr.org/docs/api-mcp.html) — Register a trusted server, restrict its tools, and attach it to a model request. For developers.
  • Image generation and editing (https://kendr.org/docs/api-images.html) — Generate images, send reference pictures, track progress, and retrieve private output. For developers.

Knowledge and production

Integrate knowledge, recover failures, and look up endpoint contracts.

  • Query API (https://kendr.org/docs/api-query.html) — Call Kendr surfaces with cURL, JavaScript, Python, C#, Java, and Go. For developers.
  • Cloud knowledge bases (https://kendr.org/docs/cloud-kb-api.html) — Hosted KB creation, staged indexing, sharing, retrieval testing, artifacts, and evaluations. For developers.
  • Hosted vector DB (https://kendr.org/docs/hosted-vector-db.html) — Managed vector storage: dimensions, retrieval scores, sharing, billing, and rebuild boundaries. For developers.
  • Errors, retries and usage (https://kendr.org/docs/api-production.html) — Handle failures, recover interrupted requests, and reconcile usage and credits. For developers.
  • API reference (https://kendr.org/docs/api-reference.html) — Endpoints, authentication modes, request fields, response contracts, and error behavior. For developers.

Case-study projects

Build and evaluate three practical integrations from complete Python examples.

  • Case-study projects (https://kendr.org/docs/api-projects.html) — Three worked Python projects with setup, source files, expected behavior, and evaluation steps. For developers.
  • Project: documentation assistant (https://kendr.org/docs/project-support-assistant.html) — Answer support questions using a registered read-only MCP documentation server. For developers.
  • Project: support-ticket triage (https://kendr.org/docs/project-ticket-triage.html) — Classify tickets with structured JSON and validate fields before routing them. For developers.
  • Project: product image studio (https://kendr.org/docs/project-image-studio.html) — Generate and edit product artwork, retrieve its private bytes, and retain usage receipts. For developers.

Desktop, skills & MCP

The workspace, the terminal client, skill packs, and trusted MCP servers.

  • Desktop and CLI (https://kendr.org/docs/desktop-and-cli.html) — Install and run Kendr locally through the desktop app, CLI, and shared runtime. For desktop and cli users.
  • Kendr Code Sandbox (https://kendr.org/docs/kendr-code-sandbox.html) — Configure and verify the Docker or Podman container required for autonomous Kendr Code permission modes. For kendr code users.
  • Chrome connector (https://kendr.org/docs/chrome-connector.html) — Install the optional Chrome extension and native messaging host for approved tab control. For desktop users.
  • Skills and MCP (https://kendr.org/docs/skills-and-mcp.html) — Install skill packs, connect remote MCP servers, and control tool access. For kendr users and developers.

Models & connectors

Kendr Cloud surfaces, the selectable model menu, and the supported app connectors.

  • Kendr overview (https://kendr.org/docs/platform-overview.html) — How Kendr Cloud, Desktop, API access, and one shared account fit together. For kendr users and developers.
  • Features and surfaces (https://kendr.org/docs/kendr-features.html) — Kendr capabilities, supported surface categories, and common product workflows. For kendr users and developers.
  • Models and app connectors (https://kendr.org/docs/connectors-and-models.html) — Choose available Kendr models and connect supported apps to your account. For kendr users and developers.

Credits & billing

Credit packages, the usage ledger, checkout, and purchase history.

  • Credits and billing (https://kendr.org/docs/credits-and-billing.html) — Credit packages, checkout, wallet balance, usage, purchase history, and billing questions. For kendr customers.

Frequently asked questions

How many Kendr documentation guides are published?

Kendr publishes 35 guides across 8 areas: Getting started (3), API essentials (7), Model features (8), Knowledge and production (5), Case-study projects (4), Desktop, skills & MCP (4), Models & connectors (3), Credits & billing (1). Every guide is linked from https://kendr.org/developers and from the sidebar on each documentation page.

Where does a new Kendr integration start?

Get one cited answer in five minutes: https://kendr.org/docs/first-cited-answer.html · Install Kendr and finish a first task: https://kendr.org/docs/getting-started.html · Your first OpenAI-compatible API call: https://kendr.org/docs/api-quickstart.html · Create and scope an API key: https://kendr.org/docs/auth-and-sdks.html · Pick a model and read its live quote: https://kendr.org/models · Run local models through the CLI: https://kendr.org/docs/desktop-and-cli.html · Install a skill pack or MCP server: https://kendr.org/docs/skills-and-mcp.html · Build a case-study project: https://kendr.org/docs/api-projects.html

Is the Kendr API OpenAI-compatible?

Yes. Kendr serves OpenAI-compatible Chat Completions and Responses endpoints at https://api.kendr.org/v1, so an existing OpenAI SDK application usually migrates by changing the base URL, the key, and the model value. The endpoint reference and the OpenAPI description document the exact request and response contracts.