MandGet started
Build a small streaming chat app
List your available models, send one message, stream the reply, and keep a local conversation using the OpenAI-compatible MandAPI endpoint.
MandAPI Cookbook
Build something useful with MandAPI
Start with a chat app, connect your coding tools, or import a customer-support workflow. Every recipe includes a readable guide and a setup prompt.
Get started
Move an OpenAI-compatible chat integration to MandAPI
Change the chat connection boundary while preserving the application's existing messages, response handling and interface.
Coding tools
Connect Claude Code to MandAPI
Configure the Anthropic-compatible endpoint, choose a supported model and check your first coding session.
Coding tools
Configure Claude Desktop with a MandAPI gateway
Use Claude Desktop's third-party inference panel with an Anthropic-compatible MandAPI connection.
Coding tools
Review a selected code diff with MandAPI
Preview a small staged diff, then request a second opinion without changing or committing code.
Coding tools
Use Codex CLI with MandAPI
Add a custom Responses provider with an environment-based key, while keeping existing project settings.
Coding tools
Start a coding session in MandAPI Connect
Use the Windows desktop app to open Claude Code or Codex CLI with your MandAPI account.
Coding tools
Use MandAPI for chat in Cursor
Set the OpenAI-compatible endpoint in Cursor and start with a supported chat model.
Coding tools
Connect Hermes Agent to MandAPI
Add MandAPI as a custom Chat Completions endpoint in Hermes.
Coding tools
Create a MandAPI model profile for Junie CLI
Use Junie's custom JSON profiles with a complete Chat Completions request URL.
Coding tools
Use an MCP tool with a MandAPI-backed coding session
Keep model inference in MandAPI while Claude Code connects to an MCP server locally.
Coding tools
Add MandAPI as an OpenClaw model provider
Register a custom provider, select a real model and check a local chat before connecting channels.
Coding tools
Add MandAPI to OpenCode v1
Configure an OpenAI-compatible provider and select your MandAPI model in OpenCode v1.
Integrations and templates
Build an FAQ support chat in n8n
Download a small workflow, connect a MandAPI credential, and answer support questions from an editable business FAQ.
Integrations and templates
Describe objects in an image with MandAPI
Send a local image to a current Vision-capable model through Chat Completions.
Build application workflows
Build a small terminal interface for your agent
Expose progress, reference reads, and resumable steps with a portable Python terminal interface.
Build application workflows
Summarize an older conversation while keeping recent turns
Compact application-managed message history without promoting a summary to an instruction.
Build application workflows
Draft with one model and review with another
Coordinate two ordinary chat requests in your own application.
Build application workflows
Stop repeated tool calls and runaway agent loops
Enforce a step limit and detect identical calls using application trace data.
Build application workflows
Build a headless agent with read-only tools
Create a Python worker with local action validation, JSON events, saved state, and bounded chat requests.
Build application workflows
Require human approval before an action
Keep a model's proposed action separate from permission to execute it.
Build application workflows
Resume longer tasks from local checkpoints
Keep progress across runs without resetting attempt limits or treating saved text as system instructions.
Evaluate and improve
Classify supplied support messages into a fixed set of labels
Ask a chat model for JSON, then validate the result in your application.
Evaluate and improve
Prepare reviewed examples for a smaller-model experiment
Build a local JSONL dataset and holdout set without assuming a MandAPI training service.
Evaluate and improve
Extract and validate fields from invoice text
Turn supplied invoice text into a small validated record using ordinary chat output.
Evaluate and improve
Build multilingual RAG with local retrieval and MandAPI
Compute neural embeddings and reranking locally, then let MandAPI answer from the selected passages.
Evaluate and improve
Check the boundaries of your own FAQ application
Run harmless local cases for unknown questions, policy overrides and fabricated actions.
Keys and usage
Export your application's usage events as CSV
Turn your own JSONL records into a minimal spreadsheet report without treating it as a platform bill.
Keys and usage
Review the API keys in your account
Build a useful key inventory, identify unused connections and reduce the impact of a lost or exposed key.
Keys and usage
Replace an API key without losing track of active applications
Create a replacement, update each consumer, verify the connection and revoke the old credential.
Keys and usage
Read token usage and reconcile it with your dashboard
Capture the usage returned by a chat response and compare it with the actual request and credit records in your own account.
Keys and usage
Record application usage by anonymous user
Add your own request identifiers and minimal usage events without assuming a MandAPI analytics API.