multi

tom@tomrochette.com (Tom Rochette) — Fri, 16 Oct 2026 00:00:00 +0000

multi is an MIT-licensed CLI and Claude Code/Codex plugin from a solo maintainer that runs one review through several model backends in parallel over a frozen snapshot, then merges their findings into a single report sorted by how many model families corroborated each one.

What it is
#

The bet is that the most informative output of several reviewers is where they disagree, so the report buckets findings instead of flattening them. Every backend in your profile reads the same snapshot of the change (not the live tree), in parallel, and the merged report marks each finding corroborated (two model families saw it), single-source (one saw it, checked against the code), disagreed (the part the README tells you to read), or dropped with a reason. Backends are Claude sub-agents, Codex, OpenCode, Kilo Code, Gemini, GitHub Copilot, or headless Claude Code pointed at any Anthropic-compatible endpoint (OpenRouter, z.ai, DeepSeek), composed in a TOML profile, with a depth knob (lite, normal, ultra) separate from who reviews. It ships as a Claude Code and Codex plugin (marketplace install), reviews a diff, branch, files, a function, or a whole repository, and refuses to run at all with only one model configured, because a one-model review wearing a multi-model label is worse than none. The only mode that edits your tree is the opt-in loop (fix, re-review, repeat until clean or three rounds); everything else is read-only over the snapshot. It is Shell and Python from szarkans, first published July 5, 2026, with 125 commits and 24 tagged releases (v1.17.2 latest).

Status
#

Active, small, and solo: 23 stars, 2 forks, pushed October 8, 2026 as of 2026-10-16.

Independent coverage exists but is thin, and I state that as a finding: OpenAgentSkill, a third-party skill registry, published a review of it on August 28, 2026 (“disagreement as signal”, conclusion: track it, it is unproven) and carries an audit page flagging its shell and credential surface, and a Hacker News search on 2026-10-16 returned zero threads. The repo was renamed from szarkans/multi-code-review to szarkans/multi (the old URL redirects), so third-party citations under either name resolve to one project.

Strengths
#

Disagreement becomes an interface, not noise: the corroborated/single-source/disagreed buckets answer the question single-report reviewers never pose, which findings would a second model contest.
The vendor ships measurements with the protocol in the open: a 13-bug corpus gated red-green (revert the fix, watch its own test fail), blind majority grading, and a published list of the ways its own numbers could mislead.
Its measured claim is specific and falsifiable: on 12 cases, the multi-model review found 29 findings against the built-in single-model review’s 14, at roughly equal Claude cost but roughly double the wall time.
A per-backend training-use disclosure table (yes, no, or unknown per endpoint) and a no-train switch that drops every uncertain backend from the roster, a privacy knob no other reviewer in this category exposes.
Budget profiles compose free tiers (OpenCode free models, OpenRouter free endpoints) into a working zero-cost review team.

Cautions
#

The eval is vendor-run on the author’s own bugs: the corpus stays private because it is client code, so no independent replication of the 29-versus-14 claim exists as of 2026-10-16.
Reviews take roughly twice as long as a single-model pass (about 19 versus 10 minutes per case in the author’s own table) and produce roughly twice the findings to read, which is the cost of the signal.
No forge integration: nothing posts to a pull request, so it is a pre-merge instrument you run, not a reviewer your repository hosts.
The name is unsearchable (“multi” collides with everything), and third-party citations split across the old multi-code-review name and the new one.
23 stars and zero Hacker News threads mean the community footprint is a registry listing and one blog post, and the registry’s own audit flags the plugin’s shell-execution and credential surface for review before install.

Pricing
#

Does not apply: multi is free under MIT and bills nothing itself; costs are your own model subscriptions and API keys (the author’s table puts a normal-depth review at about $3.50 of Claude usage per case plus cents for the external backends).

Compared to
#

roborev: the other bring-your-own-agents reviewer; roborev is a resident daemon reviewing every commit with panel synthesis on pull requests, multi is an on-demand consensus pass over one target.
OpenQodex: the other local pre-push gate; OpenQodex pairs scanners with one isolated reviewer under a completeness contract, multi pairs several reviewers with a convergence contract and no scanners.
Greptile: the hosted swarm with learned rules; multi has no memory between runs, which is the point when you want opinions that did not learn your team’s habits.

Bottom line
#

Recommended for developers who already pay for two or more model families and want a second-opinion instrument for risky changes, priced in their existing subscriptions. Not for teams that want PR-inbox automation, learned rules, or an independently validated defect-finding rate. My disagreeable claim: the corroborated-versus-disagreed split is the correct interface for multi-model review, and every single-report reviewer in this category is discarding the one signal their parallel models produce that a human reviewer cannot.

Changes
#

2026-10-16 - Created after the entrant scan resolved the szarkans/multi candidate (a skills-worker flag resolved to this category on kind); nine sources fetched this run, including the zero-HN-threads search as the coverage signal.

References
#

https://github.com/szarkans/multi - repo facts: 23 stars, 2 forks, MIT, created 2026-07-05, pushed 2026-10-08, 125 commits, renamed from multi-code-review (GitHub API, as of 2026-10-16)
https://raw.githubusercontent.com/szarkans/multi/main/README.md - the bucketed report, backends, profiles, depth knob, loop mode, refusal to run single-model, and the training-use table
https://raw.githubusercontent.com/szarkans/multi/main/evals/RESULTS.md - the eval protocol: red-green bug corpus, blind majority grading, the fix-revert exam discarded as broken, and the limitations list
https://raw.githubusercontent.com/szarkans/multi/main/config.example.toml - the backend and profile configuration surface
https://raw.githubusercontent.com/szarkans/multi/main/INSTALL.md - the non-marketplace install path for other hosts
https://api.github.com/repos/szarkans/multi/tags - 24 tagged releases, v1.17.2 latest (GitHub API, as of 2026-10-16)
https://www.openagentskill.com/blog/introducing-szarkans-multi-code-review - the independent August 28, 2026 review: disagreement as signal, track-don’t-adopt conclusion, fetched 2026-10-16
https://www.openagentskill.com/skills/szarkans-multi-code-review - the registry’s audit page: shell and credential surface flagged, low-adoption signals stated, fetched 2026-10-16
https://hn.algolia.com/api/v1/search?query=szarkans%20multi&tags=story - the coverage search that returned zero threads (queried 2026-10-16)

multi-model on tomrochette.com

multi

What it is
#

Status
#

Strengths
#

Cautions
#

Pricing
#

Compared to
#

Bottom line
#

Changes
#

See also
#

References
#

multi-model on tomrochette.com

multi

What it is #

Status #

Strengths #

Cautions #

Pricing #

Compared to #

Bottom line #

Changes #

See also #

References #

What it is
#

Status
#

Strengths
#

Cautions
#

Pricing
#

Compared to
#

Bottom line
#

Changes
#

See also
#

References
#