Ext Ops Panel
Open dashboard
Comparison

agent vs Kai AGI - Autonomous AI Agent

agent is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑20.

agent is a plugin bundle for AI coding tools published by Jörgen. No marketplace we read lists it any more. Kai AGI - Autonomous AI Agent is an MCP server published by mcp.kai-agi.com. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-29. 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
MarketplaceagentKai AGI - Autonomous AI Agent
Community marketplace air-gapped/skills Removed on 2026-10-20
Version: 0.20261004.216
Forks (GitHub): 0
Stars (GitHub): 5
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 1.4.0
No figure published
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

agent vs Kai AGI - Autonomous AI Agent
Factagentno longer listed · Kai AGI - Autonomous AI Agent
Marketplaces that list it (differs)01
Stars (GitHub) (differs)5No figure on GitHub
Forks (GitHub) (differs)0No figure on GitHub
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleRemote server (mcp.kai-agi.com/mcp)
Transport (differs)Not statedStreamable HTTP
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Parts of the bundle (differs)5Not a bundle
Licence (differs)MITNot stated
Repository (differs)github.com/air-gapped/skillsNot stated
Changes in the last 7 days00
First seen (differs)2026-10-152026-10-11
Endpoint at the last check (differs)no remote endpoint we checkNot responding since 2026-10-14

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 agent

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

  • auto-research

    Autonomous skill improvement through parallel research agents. Inspired by Karpathy's autoresearch methodology, it spawns 5 parallel agents (domain expert, quality auditor…

    by gyoz-ai · Plugin bundle

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

  • deep-research

    This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API. It aut

    by Gleb Kalinin · Plugin bundle

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

  • hyperresearch

    Deep research skill for Claude Code. Bootstraps the hyperresearch CLI and hands off to its 16-step research pipeline.

    by Jordan Gibbs · Plugin bundle

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

  • agent-loops

    Drop-in agentic loop skills (autoresearch, literature & writing, data, optimization, red-team, power analysis). Skills install namespaced as agent-loops:<name>.

    by gaasher · Plugin bundle

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

  • run-deep-research

    Skills for deep research with OpenAI, Perplexity, Edison/Falcon, Cyberian, and OpenScientist

    by ai4curation · Plugin bundle

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

  • claude-scholar

    Semi-automated research assistant with skills for literature review, experiments, analysis, writing, and project knowledge management

    by Galaxy-Dawn · Plugin bundle

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

Its card, with similar plugins by marketplace

What each says it does

agent

In its own words, on Community GitHub marketplaces:

Agent workflow suite — Karpathy-pattern autoresearch (hill-climbing, multi-agent research) and skill-improver (Claude Code skill optimization loop).

Kai AGI - Autonomous AI Agent

In its own words, on Official MCP Registry:

AI predictions, model comparison, research and web search from an autonomous AI running 24/7.

How to run each

agent

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

Kai AGI - Autonomous AI Agent As a remote MCP server

Claude Code
claude mcp add --transport http kai-agi https://mcp.kai-agi.com/mcp

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

Only Kai AGI - Autonomous AI Agent has a remote endpoint we check. How we check endpoints

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: agent · What it can do: Kai AGI - Autonomous AI Agent · 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.

Where the data comes from: how the catalog is built