KEPTA — the memory for AI systems vs Datris
KEPTA — the memory for AI systems is an MCP server published by DamianTodorovic. Marketplaces we read that list it: 2 (Official MCP Registry, npm registry (MCP servers)). Datris is an MCP server published by datris. Marketplaces we read that list it: 2 (Official MCP Registry, PyPI (MCP servers)). As of our marketplace pass on 2026-10-24. 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
| Marketplace |  KEPTA — the memory for AI systems |  Datris |
|---|---|---|
| Official MCP Registry | Listed Version: 3.4.0 Downloads/month (npm): 5 290 Downloads/week (npm): 210 Forks (GitHub): 0 Stars (GitHub): 2 Not marked · First seen |
Listed Version: 1.53.0 Downloads/month (PyPI): 10 146 Downloads/week (PyPI): 1 062 Forks (GitHub): 1 Stars (GitHub): 13 Not marked · First seen |
| npm registry (MCP servers) | Listed Version: 3.4.0 Downloads/month (npm): 5 290 Downloads/week (npm): 210 Forks (GitHub): 0 Stars (GitHub): 2 Not marked · First seen |
Not listed |
| PyPI (MCP servers) | Not listed | Listed Version: 1.53.0 Downloads/month (PyPI): 10 146 Downloads/week (PyPI): 1 062 Forks (GitHub): 1 Stars (GitHub): 13 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 | KEPTA — the memory for AI systems | Datris |
|---|---|---|
| Marketplaces that list it | 2 | 2 |
| Stars (GitHub) (differs) | 2 (worse) | 13 (better) |
| Forks (GitHub) (differs) | 0 (worse) | 1 (better) |
| Last release (differs) | 2026-10-14 (worse) | 2026-10-21 (better) |
| Where it runs (differs) | On your machine (kepta-mcp) | On your machine (datris-mcp-server) |
| Transport | stdio | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 2, secrets among them: 1 |
| Licence (differs) | BUSL-1.1 | Apache-2.0 |
| Repository (differs) | github.com/damiantodorovic/kepta | github.com/datris/datris-platform-oss |
| Changes in the last 7 days (differs) | 0 | 4 |
| First seen | 2026-10-11 | 2026-10-11 |
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
KEPTA — the memory for AI systems
Local encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.
Datris
The data control plane for AI agents — acquire, validate, land, and query data over MCP.
How to run each
KEPTA — the memory for AI systems As a local MCP server: npm package
claude mcp add --transport stdio kepta -- npx -y kepta-mcpDatris As a local MCP server: PyPI package
claude mcp add --env "DATRIS_API_KEY=<YOUR_DATRIS_API_KEY>" --env "DATRIS_API_URL=<YOUR_DATRIS_API_URL>" --transport stdio datris -- uvx datris-mcp-serverRequires: DATRIS_API_KEY (secret), DATRIS_API_URL
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
The marketplaces of KEPTA — the memory for AI systems publish no settings it asks for, so we do not compare settings.
What it can do: KEPTA — the memory for AI systems · What it can do: Datris · Compare two other plugins
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Package data comes from the public npm registry (registry.npmjs.org). Package data comes from the Python Package Index (pypi.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.