An intelligent orchestration layer for LLMs.

Devtor optimizes cost, performance, and reliability by dynamically managing prompts, models, context, and execution strategies — continuously improving from past interactions.

16orchestration capabilities
68%reduction in cost
CLIterminal & web workflows
The platform

A control plane between you and your LLMs

Devtor orchestrates prompts, models, context, and execution — optimizing cost, performance, and reliability. It picks how, when, and which model to run, learns from every session, and works via CLI, Locally Hosted Webportal, or IDE extensions.

Core promise

The right model, context, and execution strategy for every task.

  • Hybrid super-agent + cheap sub-agents
  • Granular plans · pre-run cost estimates
  • Smart context · latest prompt only
  • Cross-user learning · shared fixes
  • CLI + Locally Hosted Webportal + IDE extensions

Prompt optimization

Tune prompts per model tier. Cheaper models, production output.

Smart context

Relevant messages and files only. No full-history replay.

Cost control

Estimates, budgets, smart routing. Power models when needed.

Organizational learning

Resolved failures indexed org-wide. Same problem, instant fix.

Bring Your Model (BYOM)

Your Infrastructure. Your Models. Our Agent Orchestration.

Stop being locked into single AI vendors. Devtor is fully model-agnostic, giving you the power to mix local offline intelligence, specialized high-speed endpoints, and private enterprise deployments inside a unified routing layer.

Zero Provider Lock-In

Swap providers with a single config change. Connect commercial APIs, local nodes, or private instances.

Secure Local Workloads

Run offline tasks using Ollama, Llama.cpp, or vLLM. No external network request is ever sent for local workflows.

Unified Configuration Spec

A single standardized spec handles diverse model prompt templates, token limits, and fallback strategies behind the scenes.

Failover Resilience

Configure fallback lists. If your main model hits rate limits or experiences downtime, traffic transparently switches to your standby model.

Hybrid Local & Cloud

Most Popular

Run local open-source models for draft generation and security-critical files, and scale to premium cloud LLMs only when deep reasoning is needed.

Active Router Status

Claude 3.5 Sonnet

Anthropic API

Llama 3.1 8B

Ollama (Local)

DeepSeek-V3

DeepSeek API

Flow: Drafting, tests & simple refactors run 100% locally on your machine at zero cost. Multi-file plans automatically upgrade to Claude 3.5 Sonnet.

models.yaml
YAML Configuration
# ~/.config/devtor/models.yaml
providers:
  anthropic:
    api_key: env.ANTHROPIC_API_KEY
    models:
      - claude-3-5-sonnet-latest:
          tier: advanced
          routing: "reasoning, planning"

  ollama:
    host: "http://localhost:11434"
    models:
      - llama3.1:8b:
          tier: local
          routing: "drafting, refactoring, tests"
Compatible with standard OpenAI API specs and LiteLLM Proxy
End-to-end orchestration pipeline
See the three phases
01
InputCLI, Locally Hosted Webportal, or IDE extensions
02
PlanGranular plans · token estimates · budgets
03
ContextRelevant messages only · memory control
04
RouteSmart selection · prompt optimization · hybrid agents
05
ExecuteThink mode · model-aware · track spend
06
LearnCross-user fixes · repo rules · pattern cache
How it works

Orchestration in three phases

Plan, route, execute — Devtor picks the right model and learns every run.

Full walkthrough
Capabilities

Built for engineering teams who take AI seriously.

16 capabilities across five areas — routing, planning, context, execution, and learning.

All capabilities
Get started

CLI, Webportal & IDE Extensions. Ready when you are.

Terminal CLI, Locally Hosted Webportal, and IDE extensions. Switch between interfaces with your existing provider keys.

01

Install the CLI

yarn, npm, or homebrew

02

Add provider API keys

Reads from your .env

03

Run devtor init

Auto-detects your codebase

04

Run your first task

Natural language in terminal

  • Node.js 18+ · one LLM provider key
  • CLI, Webportal & IDE extensions
  • Pre-run estimates · token budgets
View installation guide
terminal — preview
# Get started with Devtor
$yarn global add devtor
→ coming soon
$devtor run "Ship the auth refactor"
Planning... complexity: medium
Routing to: claude-3-5-haiku ($0.006)
✓ Done · pattern cached
CLI coming soon