Platform

The platform behind the migration.

How Forgestus plans, builds, verifies and records every change — and the stacks and AI models it runs on. This page is for the engineers who will work with it.

The migration engine

Under the hood: assess, pin, migrate, prove.

No big-bang rewrite. Forgestus modernizes your monolith slice by slice — and proves each slice behaves identically before it ships. Every step durable, every retry idempotent, every cost in the ledger.

Assess

A read-only scan maps your architecture and business rules, ranks risk by churn × complexity × coverage, and produces a dependency-ordered strangler plan with difficulty scores. Nothing is written to your code.

Pin the baseline

Before touching anything, Forgestus runs your existing tests on the old .NET Framework runtime and pins the result — the behavior every migrated slice will be measured against.

Migrate a slice

Agents port the slice to modern .NET on a Windows runner — applying recipes like CoreWCF where they fit, and flagging anything non-portable for a human instead of guessing.

Prove parity & cut over

A green parity report — new runtime vs the pinned baseline — gates the merge. The cutover board moves the slice monolith → shadow → live. Repeat until the monolith is modern.

Every slice lands with a green parity report as its receipt — book a demo →

Why Forgestus

Six things engineering and procurement both ask for.

11 production stacks

Node, modern .NET, classic .NET Framework on Windows Fargate, React, Next.js, Angular, Blazor, Flutter, Unity, WinForms/WPF, SSDT. The enterprise long tail, first-class.

Deterministic state machine

Every transition durable in DynamoDB. Every retry idempotent. When an agent crashes, the orchestrator recovers without losing work. Crash-safe by construction.

Permanent audit ledger

Every model call, every retry, every dollar — written to AUDIT# rows that never expire. CSV export, regulator-ready (SIEM connectors on the roadmap).

Self-healing recovery

Stuck epics auto-diagnose and fix themselves where safe. When an agent hits a target that doesn't exist, it pauses and asks instead of burning its budget — you /answer and it resumes. Every blocker surfaces a one-glance diagnosis with the exact fix command. No "wedged forever" mode, no log spelunking.

HIPAA + HITRUST as config

Add compliance: [hipaa] to forge.yaml — every agent inherits the coding controls. Enforced by the runtime, audited by the reviewers.

Bring your own key

Anthropic, AWS Bedrock, OpenAI, or Vertex — your contract, your rate, your data-handling. We run the infrastructure; the flat platform fee covers it. Model tokens are the only usage cost, billed to you by your vendor — no bundled credits, no markups.

Stack reach

From Blazor to Unity. One platform.

Classic .NET Framework 4.x on a Windows Fargate runner. Lambda dotnet10 on Linux. Flutter, Unity, Angular, Next.js — every stack with a first-class agent prompt and a deterministic QA runner.

Node.jsjest · tsx
.NET 10xunit · sdk-style
.NET Frameworkmsbuild · vstest
Reactjest · vitest
Next.jsapp-router · ssr
Angularkarma · jasmine
Blazorbunit
Flutterflutter test
Unityeditmode · playmode
WPF / WinFormsxaml · winui
Windows Servicebackground
SSDTtsqlt · dacpac · LocalDB
C# CDK.NET infra-as-code
MCP serversaws-docs · cloudwatch
Custom agentsyour prompts · your steps
Multi-modelAnthropic · Bedrock · OpenAI · Vertex · Meta
Model-agnostic by design

New models ship every month. Never bet your migration on one.

Forgestus routes every agent to the model you choose — bring your own keys and switch anytime, per agent, per project. Run reviews on the strongest model you trust and bulk work on the fastest one you like; when a better model ships next month, it's a config change, not a re-procurement. Model tokens are billed to you by your vendor at your contract rate.

AnthropicClaude Opus 5.5 · Sonnet 5.5 · Haiku 5.5 · Fable 5.1
AWS BedrockClaude · Nova · Llama · Mistral · your VPC
OpenAIGPT-6 Astra · GPT-6 Luna
Google VertexGemini 3.8 Flash · Gemini 2.5 Pro
MetaMuse Wonder (preview) · Muse Spark 1.3
Per-agent routingplanner · builders · reviewers — each its own model

Anthropic keys on every plan; AWS Bedrock on Business+; OpenAI, Vertex, and Meta on Enterprise. Every model call — whoever serves it — lands in the same audit ledger with tokens and cost itemized.

Beyond migration

Once it's modern, keep shipping.

The same deterministic agents that migrated your monolith deliver your everyday epics — across 11 stacks, with the same audit ledger and adversarial review gates. File a GitHub issue, type /proceed, and the pipeline ships it.

File the epic

Open a GitHub issue. Describe the work in plain language. Forgestus's planner agent breaks it into stories, posts a plan, and waits for your /proceed.

Build in parallel

Architect, backend, web, and mobile agents work on isolated story branches at the same time — each with full repo context, each running the right toolchain for the right stack.

Adversarial review

Reviewer agents audit every PR on the strongest model you allow. halt verdicts trigger auto-retry of the implementing agent. advisory verdicts get logged. approve moves the epic forward.

Deploy and validate

Forgestus merges to develop, runs your deploy workflow, smoke-tests the deployed routes, and advances to the test environment on green. Failures route to devops-fix with the actual error in scope.

The Business plan, in numbers

An agent team for under $25 an hour.

$4,000 a month puts a full delivery team of agents on your backlog, working in parallel across up to 15 repos, with every change reviewed and recorded in the audit ledger.

≈ $23/ hour

$4,000 across a 173-hour work month

≈ $53/ epic

75 epics included every month, each planned, built, reviewed and opened as a PR

< $20/ hour

With annual billing, 15% off

Plus model tokens, billed by your AI vendor at your own rate. Every plan runs on your own AI key.

plannerarchitectbackendwebmobilemigrationreviewersQAdevops

Platform fee shown. Windows-runner epics count as two.

Next step

See it on a system like yours.

Book a free 30-minute demo. We’ll walk through a sample migration, then look at your system together.