Built for machines first.
Readable by humans too.
A layered discovery stack that lets any AI agent find, understand, and
operate BrainstormRouter without human help. From
llms.txt to self-awareness endpoints
— every surface is machine-optimized.
Progressive disclosure, machine-first.
From a static text file to a live authenticated self-awareness endpoint. Every agent starts at the top and drills down.
GET /llms.txt
Concise site map
Plain-text, under 16 KB. Includes a 3-step agent-bootstrap sequence.
GET /llms-full.txt
Complete API reference
Every endpoint, parameter, and response schema. Auto-generated on every build.
GET /llms-agent-playbook.txt
Agent playbook
Step-by-step operational guide. Registration → auth → model selection → memory → MCP.
/.well-known/agents.json
Agent capability manifest
Protocols, auth methods, and tool namespaces declared as a single JSON.
/.well-known/ai-plugin.json
OpenAI plugin manifest
Compatible with ChatGPT plugins, Copilot, and plugin-aware agents.
GET /v1/discovery
Live capability discovery
Authenticated endpoint. Returns API topology: routes, model count, MCP tool count, auth methods, feature flags.
GET /v1/self
Self-awareness endpoint
Returns the caller's identity, health, budget remaining, configuration, and actionable suggestions. "Who am I? What can I do right now?"
Six calls, zero humans.
- 01
Fetch
llms.txtto read the site map and bootstrap info. - 02
Register via
POST /v1/registerto receive an API key and tenant ID. - 03
Call
GET /v1/selfto learn identity and budget. - 04
Call
GET /v1/discoveryto map full API topology. - 05
Connect MCP for 107 governed tools.
- 06
Operate via
/v1/chat/completions. RFC 8631 Link headers point back to the stack.
Read the agent playbook.
The complete operational guide for AI agents integrating with BrainstormRouter.