Mike
by Mike · Open-source legal AI platform firms can self-host
BenchRank score
Screenshots of Mike
Homepage
Overview
Mike is an open-source legal AI platform for law firms, used through a hosted cloud version or deployed from the source repo. A chat assistant reads documents uploaded into matter-scoped projects, gives grounded citations, researches case law and drafts contracts. Tabular review extracts fields across hundreds of documents in parallel, and saved prompts become reusable workflows.
- Best for
- Law firms that want to self-host a legal AI assistant and keep documents inside their own perimeter.
- Pricing
- No prices are shown: the platform is open source with zero licence cost and you pay your own model API costs, while the cloud version offers a free sign-up with no rates published.
- Runs on
- WebSelf-hosted
Strengths and trade-offs
Strengths
- Self-hostable, so documents stay inside the firm's perimeter
- No licence fee; you pay only the model API costs you incur
- Tabular review cites each cell back to a page and a quote
- Open code: prompt building, citation parsing and data flow
Trade-offs
- Still early: releases run v0.1.0 to v0.4.0 over four months
- Self-hosting puts deployment and maintenance on the firm
- Model API costs are separate and not included
- No price shown for the cloud-hosted version
How Mike markets itself
A structured read of the promise, proof and page design on Mike’s captured homepage.
Homepage capture
“Legal AI you can truly own.”
- Angle: Open source / ownership
- Hero: Illustration
Pricing
Published plans and prices from Mike’s own pricing page.
How this score is made up
Each dimension is scored out of 100 and combined into the headline score using fixed weights.
MCP support
Whether an agent can drive the product through the Model Context Protocol, and how much setup that takes.
Documentation
Publicly reachable docs — coverage, freshness, code samples and machine readability.
Agent friendliness
How readable the site is to an automated client: llms.txt, structured data, server-rendered content, crawler access.
Changelog
A public, dated record of what shipped and when — the clearest signal that a product is still alive.
Marketing site structure
Whether the site answers a buyer's questions: clear positioning, the pages that matter, and accessibility.
Page speed
How fast the site loads for real visitors: Chrome UX Report 75th-percentile LCP, INP and CLS, with a Lighthouse mobile run standing in where a site has too little traffic for field data.
Operational trust
Status page and incident history, security disclosure, compliance and data-processing documentation.
Measured, but not part of the score
Useful to know, but not a mark for or against the product — so these do not affect the ranking.
Openness
Source availability, self-hosting, data export and open standards. Scored and shown, but not part of the composite — paid SaaS is not worse for being paid SaaS.
Maintenance
Release cadence and repository activity. Scored and shown, but not part of the composite — it is only measurable for open repositories.
This doesn’t look right — report a problem with Mike’s score
Where this comes from
The Mike pages BenchRank reads when it scores the product — its documentation, release notes, status and security pages, and its repository where there is one.
Alternatives in Legal & Contracts
Ranked 1
45.3 — BenchRank score out of 100SimpleLegal
SimpleLegal · Enterprise legal management for eBilling, matters and vendors
Best for: Corporate legal departments tracking outside counsel spend, matters and vendors in one system
Ranked 2
43.7 — BenchRank score out of 100Wraft
Wraft · Open-source, self-hostable document lifecycle management
Best for: Teams wanting contract and document workflows they can self-host on their own infrastructure
Ranked 3
37.8 — BenchRank score out of 100Dioptra
Dioptra · AI contract redlining and playbook distillation in Microsoft Word
Best for: In-house legal and law firm teams redlining contracts against their own playbooks in Word.
Is this your product?
Claim Mike to manage its profile. Claiming lets you suggest edits to the descriptive fields — it never changes scores or rankings.