Devtor

LLM ORCHESTRATOR

Overview01 Plan First02 Route Intelligently03 Execute & Learn
Overview
Prompt Optimization LayerTune prompts so cheaper models match production quality.Hybrid Model ArchitectureExpensive orchestrator delegates to cheap sub-agents. No wasted spend on simple tasks.Smart Model SelectionAuto-picks the best model per prompt, using expensive models only when needed.Model Limitation AwarenessKnows model limits — escalates or reroutes instead of hallucinating.
Granular Plan ModeGenerates detailed step-by-step plans when needed, and skips planning for simple tasks.Pre-Execution Token EstimationSee token usage and projected cost before build commands run.Token Budgeting SystemSet token budgets per session, task, or team — enforced before compute runs.Structured Plan OutputOutputs interactive plan.html — reviewable decisions, not markdown walls.
Smart Context ManagementOnly pass context relevant to the latest prompt — not the full session history.Context & Memory ControlAdd or remove context and memory to control what the model sees.
Interactive Think ModePause, redirect, or correct the agent mid-run — no full restart.Skill BuilderBuild skills with test and evaluation modes to benchmark and fine-tune behavior.CLI + Local Web IDEProvides a terminal CLI and localhost web IDE with embedded chat.AI Collaboration ModeShared agent sessions and handoffs — break out of solo AI silos.
Cross-User LearningIndexes resolved failures org-wide, like Stack Overflow for AI agent runs.Automatic Repository RulesGenerates repo rules from your codebase patterns on init.
Install
About Devtor
Get started
How it works

How Devtor orchestrates every LLM task

Devtor sits between you and your models as a control plane — deciding how, when, and which model to use. Every prompt passes through planning, intelligent routing, and execution with learning.

01Plan First02Route Intelligently03Execute & Learn
How it works

Orchestration in three phases

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

01

Plan First

Analyze before you infer.

Analyzes task complexity, token usage, and execution path before any model runs.

terminal
$devtor run "Refactor auth module"
Analyzing task complexity...
→ Complexity: medium · planning required
→ Estimated tokens: 2,400 · budget: OK
Read full breakdown →
02

Route Intelligently

Right model. Right price.

Picks the cheapest capable model. Prompt tuning and hybrid sub-agents keep quality up, cost down.

terminal
Routing decision:
task: code refactoring (medium)
prompt: optimized for haiku tier
selected: claude-3-5-haiku
Read full breakdown →
03

Execute & Learn

Run once. Route smarter next time.

Runs the plan, tracks spend, caches patterns. Think mode lets you steer mid-run.

terminal
✓ Completed in 3.2s
✓ Tokens used: 1,847 / 2,400 · budget remaining: 62%
✓ Cost: $0.006
✓ Pattern cached · fix indexed for org
Read full breakdown →