Dshamir is publishing the blueprint before laying a brick

A set of detailed roadmap documents lays out exactly where this fork's plumbing is headed - no code yet, but enough specificity to know what's coming.

infrastructureintegration

Dshamir hasn't shipped this work - these are planning documents - but they're concrete enough to read as a commitment. The core idea is splitting heavy jobs (scanning documents, generating search indexes, calling the AI) onto separate background workers, so the app stays responsive even when dozens of document-scans are running at once, and a crash in one job never takes the whole system down.

The plans also sketch a plugin system and a way for Mike to connect to outside tools - credential vaults, legal databases, enterprise systems - plus the option to run AI models on your own hardware rather than a third-party cloud, which matters for cost and for keeping sensitive matter data in-house. There's a phased rollout described, from single-machine to fully auto-scaling.

So what Worth a look for anyone weighing whether this fork can grow from a demo into something that survives real caseload and on-premise privacy demands.

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