Ext Ops Panel
Open dashboard
Comparison

autoresearch vs Opik

autoresearch is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑18.

autoresearch is a plugin bundle for AI coding tools published by bn-l. No marketplace we read lists it any more. Opik is an MCP server published by comet-ml. Marketplaces we read that list it: 2 (Official MCP Registry, Docker MCP Catalog). As of our marketplace pass on 2026-10-23. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.

Where each is published

Where each is published
MarketplaceautoresearchOpik
Community marketplace bn-l/claude-autoresearch-mod Removed on 2026-10-18
Version: 0.2.0
Forks (GitHub): 0
Stars (GitHub): 3
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 3.0.7
Downloads/month (PyPI): 3 591
Downloads/week (PyPI): 1 906
Forks (GitHub): 37
Stars (GitHub): 225
Not marked · First seen
Docker MCP Catalog Not listed Listed
Version: sha256:0e0d7d33d5eb
Forks (GitHub): 37
Pulls (Docker Hub): 17 135
Stars (Docker Hub): 1
Stars (GitHub): 225
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

autoresearch vs Opik
Factautoresearchno longer listed · Opik
Marketplaces that list it (differs)02
Stars (GitHub) (differs)3225
Pulls (Docker Hub) (differs)No figure on Docker Hub17 135
Forks (GitHub) (differs)037
Last release (differs)Not published2026-10-23
Where it runs (differs)Installs as a plugin bundleRemote server or your machine
Transport (differs)Not statedStreamable HTTP, stdio
Tools it declares (differs)Not published13
Environment variables it asks for (differs)Not published4, secrets among them: 1
Parts of the bundle (differs)3Not a bundle
Licence (differs)MITApache-2.0
Repository (differs)github.com/bn-l/claude-autoresearch-modgithub.com/comet-ml/opik-mcp
Changes in the last 7 days22
First seen (differs)2026-10-152026-10-11
Endpoint at the last check (differs)no remote endpoint we checkNot responding since 2026-10-21

Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.

What to use instead of autoresearch

Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.

  • autoresearch-ai-plugin

    Autonomous experiment loop for Claude Code. Run an endless optimize-measure-keep/discard cycle on any optimization target: LLM training loss, test speed, bundle size, build time…

    by proyecto26 · Plugin bundle

    Listed on: Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

  • autoresearch

    Autonomous experiment loops on any codebase — one file, one metric, one loop. An agent edits a constrained file, runs an eval, keeps improvements, reverts failures, and repeats…

    by pjhoberman · Plugin bundle

    Listed on: Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

  • autoresearch-agent

    Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/ar:setup, /ar:ar-run, /ar:loop, /ar:ar-status, /ar:ar-resume), 8 built-in evaluators…

    by Alireza Rezvani · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • autoresearch-discover

    Scan a codebase to find where autoresearch experiments would be most valuable.

    by PJ Hoberman · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • research

    Reviewable ML research: literature, planning, methodology review, bounded runs, sweeps, implementation verification, ablations, retrospectives, Kaggle, and setup

    by Jirka · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • scientific-coding

    Principles and rules for writing faithful scientific code. Scientific code serves truth, not users. This plugin teaches Claude the fundamental differences between scientific and…

    by cemde · Plugin bundle

    Listed on: Claude Code: claude-plugins-community · Describes nearly the same job

Its card, with similar plugins by marketplace

What each says it does

autoresearch

In its own words, on Community GitHub marketplaces:

Autonomous experiment loop for Claude Code: run, measure, keep or discard. A port of pi-autoresearch.

Opik

In its own words, on Official MCP Registry:

Read and score Opik traces, experiments, datasets and prompts from your AI assistant.

How to run each

autoresearch

No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.

Opik As a remote MCP server

Claude Code
claude mcp add --transport http opik-mcp https://www.comet.com/opik/api/v1/mcp

Requires: OPIK_API_KEY (secret)

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Only Opik has a remote endpoint we check. How we check endpoints

Tools each declares

The marketplaces of autoresearch publish no list of tools, so we do not compare tools.

Settings each asks for

The marketplaces of autoresearch publish no settings it asks for, so we do not compare settings.

What it can do: autoresearch · What it can do: Opik · Compare two other plugins

Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built