autoresearch-agent vs Testers.ai CARBON Test Harness Lite
autoresearch-agent is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑17.
autoresearch-agent is a plugin bundle for AI coding tools published by Md Faiz Alam. No marketplace we read lists it any more. Testers.ai CARBON Test Harness Lite is an MCP server published by jarbon. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-11-10. 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
| Marketplace |  Testers.ai CARBON Test Harness Lite | |
|---|---|---|
| Community marketplace afaizalam2003/master-claude-skill | Removed on 2026-10-17 Version: 2.1.2 Forks (GitHub): 2 Stars (GitHub): 2 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.1.0 Forks (GitHub): 1 Stars (GitHub): 2 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
| Fact | autoresearch-agentno longer listed · | Testers.ai CARBON Test Harness Lite |
|---|---|---|
| Marketplaces that list it (differs) | 0 | 1 |
| Stars (GitHub) | 2 | 2 |
| Forks (GitHub) (differs) | 2 | 1 |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (https://github.com/jarbon/carbon-lite/releases/download/mcp-v0.1.0/carbon-lite-mcp-0.1.0.mcpb) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Parts of the bundle (differs) | 1 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/afaizalam2003/master-claude-skill | github.com/jarbon/carbon-lite |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-15 | 2026-10-11 |
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-agent
Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.
-
Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/autoresearch-agent:setup, /ar-run, /ar-loop, /ar-status, /ar-resume), 8 built-in…
-
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…
-
Structured experiment-driven code optimization using tree search and parallel subagents
-
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…
-
Autonomous LLM agent optimization using LangSmith. Spawns 5 parallel proposers in git worktrees, evaluates candidates via LangSmith experiments, and merges winners automatically…
-
PROACTIVELY use this agent when experiments are started, modified, or when results need analysis. This agent specializes in tracking A/B tests, feature experiments, and iterative…
What each says it does
autoresearch-agent
Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/ar:setup, /ar:run, /ar:loop, /ar:status, /ar:resume), 8 built-in evaluators, configurable loop intervals (10min to monthly).
Testers.ai CARBON Test Harness Lite
Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.
How to run each
autoresearch-agent
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
Testers.ai CARBON Test Harness Lite
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: autoresearch-agent · What it can do: Testers.ai CARBON Test Harness Lite · 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. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.