Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for teams running multi-agent pipelines that need shared state across runs and frameworks, for developers who want agent memory without a hosted vendor holding their context, and for anyone wiring memory into a non-MCP client that only speaks HTTP.
Where this stands now
doobidoo/mcp-memory-service ranks #50 of 74 tracked Agent Infrastructure items by composite score (7.3 against a section median of 7.7). The section currently carries 34 Silver, 29 Gold, 11 Bronze. Signal extremes versus the section: momentum at the 72th percentile; novelty at the 26th percentile.
Who should use it
Who should skip it
Skip doobidoo/mcp-memory-service unless the captured evidence suggests it solves a problem you are actively working on.
About this signal
doobidoo/mcp-memory-service is tracked by RepoRadar as an MCP server in the Agent Infrastructure section. First seen 2026-08-28; the source record was last checked on 2026-08-28. The current verdict is 'try now' with a Silver tier and moderate setup difficulty. The standout signals for doobidoo/mcp-memory-service are workflow potential (8.8) and open-source/build quality (8.4), while setup ease (7.0) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar captured from https://github.com/doobidoo/mcp-memory-service.
How this item is evaluated
The doobidoo/mcp-memory-service record combines a 7.3/10 composite score with separate popularity (100.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
This is a persistent store for whatever your agents observe, which can include code, credentials in transcripts, and customer data. Decide scoping, retention, and who can read the store before pointing production agents at it; It exposes an HTTP API, OAuth, a dashboard, and SSE. Self-hosting means you own the auth boundary, TLS, and network exposure of all of them; Version surfaces disagree at review time: the newest GitHub release is v11.8.2 (2026-08-23) while PyPI publishes 11.10.0, so pin deliberately and check which artifact you are actually running; The stated 5ms retrieval figure is the project's own claim in its README. RepoRadar has not benchmarked it.