Layerr Documentation

What is Layerr?

Layerr is a self-hosted orchestration runtime that sits between your AI coding agents and every LLM provider. It is not a router, it is an intelligence layer that classifies intent, analyses workloads, selects strategies, scores providers, and continuously learns from outcomes.

The Intelligence Layer

Layer	Purpose	Documentation
1	Intent Classification	What is the request asking for?
2	Workload Analysis	What language, stack, complexity?
3	Workspace Profiles	Per-workspace configs, budgets, policies
4	Strategy Engine	Cost, speed, quality, balanced
5	Provider Scoring	Score and rank every candidate
6	Execution Engine	Send, stream, retry, fallback
7	Explainability	Why was this model chosen?
8	Replay & Comparison	Record, replay, compare traces
9	Adaptive Learning	Learn from outcomes and improve
10	Quality Evaluation	Benchmark, calibrate, score quality
11	Provider Economics	Track costs, simulate alternatives
12	Entitlements & Security	Secrets, rotation, isolation, guardrails

By the Numbers

• 1,090 source files
• 135 API routes
• 715 auto-detected communities
• 21,978 symbols
• 35,702 relationships
• 300 execution processes
• 12 intelligence layers

Documentation Sections

Section	What You’ll Find
Overview	High-level architecture, routing, economics, evaluation, replay
Intelligence Layer	Deep-dive into every intelligence layer
API Reference	Complete API documentation for all 135 routes
Domains	Domain-specific deep-dives: providers, routing, tenant isolation

Quick Start

Send a request via OpenAI-compatible API

curl -X POST http://localhost:3000/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "layerr-auto",
    "messages": [{"role": "user", "content": "Write a React counter component"}]
  }'

Configure a workspace

curl -X POST http://localhost:3000/api/workspaces \
  -H "Authorization: Bearer YOUR_ADMIN_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "slug": "my-app",
    "name": "My Application",
    "strategy": "quality",
    "budget": {"monthly": 100}
  }'

---

Documentation generated from live codebase analysis via GitNexus. Last updated: May 30, 2026.