total-recall vs io.github.sumanaddanki/suma-memory
total-recall is a plugin bundle for AI coding tools published by strvmarv. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). io.github.sumanaddanki/suma-memory is an MCP server published by sumanaddanki. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-22. 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 |  total-recall |  io.github.sumanaddanki/suma-memory |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 4.0.4 Forks (GitHub): 5 Stars (GitHub): 15 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 1.5.0 Downloads/month (npm): 188 Downloads/week (npm): 27 Forks (GitHub): 0 Stars (GitHub): 0 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 | total-recall | io.github.sumanaddanki/suma-memory |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 15 (better) | 0 (worse) |
| Forks (GitHub) (differs) | 5 (better) | 0 (worse) |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | Remote server (sumapro.quadframe.work/mcp) |
| Transport (differs) | Not stated | Streamable HTTP |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 1, secrets among them: 1 |
| Hooks it runs (differs) | 3 | Not published |
| Parts of the bundle (differs) | 7 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/strvmarv/total-recall | github.com/sumanaddanki/suma-mcp |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-12 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Answered with HTTP 404 (5 days ago) |
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
total-recall
Coding Agents forget everything when a session ends. total-recall fixes that: a shared memory layer that persists across sessions, tools, and devices. Memory is organized into three tiers (Hot / Warm / Cold) with a 4,000-token budget enforced automatically — so Claude gets relevant context injected at session start without carrying stale noise. Semantic search (all-MiniLM-L6-v2 embeddings, offline) retrieves the right memories on demand. A knowledge base lets you ingest READMEs, API docs, and architecture notes that are retrieved semantically when relevant. An eval framework lets you measure retrieval quality, run benchmarks, and compare config changes — so you know memory is actually helping. All state is local: SQLite + ONNX embeddings, no external services, no API keys required. Works across Claude Code, Copilot CLI, Cursor, Cline, and OpenCode — existing memories auto-import on first run.
io.github.sumanaddanki/suma-memory
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
How to run each
total-recall As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install total-recall@claude-communityio.github.sumanaddanki/suma-memory As a remote MCP server
claude mcp add --transport http suma-memory https://sumapro.quadframe.work/mcp --header "Authorization: Bearer <YOUR_TOKEN>"Requires: SUMA_API_KEY (secret), Authorization header
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only io.github.sumanaddanki/suma-memory 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
The marketplaces of total-recall publish no settings it asks for, so we do not compare settings.
What it can do: total-recall · What it can do: io.github.sumanaddanki/suma-memory · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. 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.