Ext Ops Panel
Open dashboard
Comparison

sublinear-time-solver vs io.github.JaysonAIOnline/cognitive-substrate

sublinear-time-solver is an MCP server published by ruvnet. Marketplaces we read that list it: 1 (npm registry (MCP servers)). io.github.JaysonAIOnline/cognitive-substrate is an MCP server published by JaysonAIOnline. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-11-08. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplacesublinear-time-solverio.github.JaysonAIOnline/cognitive-substrate
npm registry (MCP servers) Listed
Version: 1.8.0
Downloads/month (npm): 4 099
Downloads/week (npm): 1 205
Forks (GitHub): 36
Stars (GitHub): 93
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 1.0.1
Downloads/month (PyPI): 163
Downloads/week (PyPI): 21
Forks (GitHub): 0
Stars (GitHub): 1
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

sublinear-time-solver vs io.github.JaysonAIOnline/cognitive-substrate
Factsublinear-time-solverio.github.JaysonAIOnline/cognitive-substrate
Marketplaces that list it11
Stars (GitHub) (differs)93 (better)1 (worse)
Forks (GitHub) (differs)36 (better)0 (worse)
Last release (differs)2026-11-06Not published
Where it runs (differs)On your machine (sublinear-time-solver)On your machine (mcp-cognitive-substrate)
Transport (differs)Not statedstdio
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Licence (differs)MIT OR Apache-2.0Not stated
Repository (differs)github.com/ruvnet/sublinear-time-solvergithub.com/jaysonaionline/mcp-cognitive-substrate
Changes in the last 7 days (differs)20
First seen (differs)2026-10-122026-10-11

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

sublinear-time-solver

In its own words, on npm registry (MCP servers):

Sparse linear solvers (Neumann, Jacobi, Gauss-Seidel, conjugate gradient), PageRank, personalized PageRank and local forward/backward push, as an MCP server, CLI and library. The dependency-free core ships separately as @ruvnet/sublinear-core.

io.github.JaysonAIOnline/cognitive-substrate

In its own words, on Official MCP Registry:

28-layer cognitive substrate with cross-session ToT evolutionary memory and self-telemetry tools

How to run each

sublinear-time-solver

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

io.github.JaysonAIOnline/cognitive-substrate As a local MCP server: PyPI package

Claude Code
claude mcp add --transport stdio cognitive-substrate -- uvx mcp-cognitive-substrate

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: sublinear-time-solver · What it can do: io.github.JaysonAIOnline/cognitive-substrate · Compare two other plugins

Package data comes from the public npm registry (registry.npmjs.org). 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