Dshamir sketches Mike's path from prototype to platform

A set of planning documents lays out how this fork could grow from a single-server prototype into a scalable, extensible, optionally air-gapped system.

infrastructureintegration

These are strategy documents, not working code - but they're the clearest signal yet of where Dshamir wants to take Mike. The roadmap maps a deliberate move away from the single-server setup most forks start as, toward something built to run at scale and be extended by outside services and add-ons.

Two threads stand out for legal buyers. First, planned support for AI models that run entirely on local hardware - meaning a firm could deploy Mike fully air-gapped, with no client data ever leaving its own network. Second, a proposal to lift the heavy work - scanning and reading PDFs, generating reports, sending alerts - off the main application and onto a separate fleet of background workers that can grow with demand, so the system doesn't buckle under large document volumes.

So what Worth watching for anyone weighing whether this fork could mature into something that handles confidential matters on-premises and at real volume.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

4 commits from Dshamir/AI-Legal, oldest first. Source extracted verbatim from the harvested git log.

SHA	Subject	Author	Date
`6207adcd`	Add candidate PRD: distributed CPU workers for AI-Legal	007	2026-05-23	↗ GitHub
commit body Goal-oriented proposal to move long-running and CPU-heavy work (PDF/OCR ingest, embeddings, LLM calls, report gen, notifications, cleanup) off the backend HTTP container onto a BullMQ-based worker fleet. Reuses existing Redis/Postgres/MinIO/GlitchTip substrate. Three phases: same-host workers, separate-host distribution, eventual KEDA autoscaling. Precedent: Exp_dental Celery worker pattern.
`5983a195`	docs: flesh out ROADMAP with categories, priorities, and distributed workers proposal	Dshamir	2026-05-23	↗ GitHub
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`1a6da718`	docs: add Plugin & MCP Architecture foundation and LLM compute providers to roadmap	Dshamir	2026-05-23	↗ GitHub
commit body Introduces the architectural direction for extensibility: - MCP Server (Mike as provider), MCP Client (consuming external services) - Plugin system with 6 proposed plugins from proposed-upgrades/ - Local LLM support (Ollama/vLLM) for air-gapped deployments - AWS GPU compute (Bedrock, SageMaker, EC2) for cloud burst Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`92120e2f`	docs: add deployment progression to roadmap (k3s, Helm, KEDA, Terraform)	Dshamir	2026-05-23	↗ GitHub
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-528.md from inside the repo you want the changes in.

⬇ Download capture-thread-528.md