Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Agent memory layers usually force a choice between an opaque vector store and an unranked folder of notes; this one indexes a filesystem the agent can also read directly, and its recall-by-path design keeps context small. Useful for developers running long coding-agent sessions, teams comparing agent-memory layers.
Where this stands now
agent-memory — Markdown-file long-term memory runtime for coding agents: local ranked retrieval returns paths instead of past ranks #2 of 7 tracked Agent Memory items by composite score (8.2 against a section median of 8.2). The section currently carries 4 Silver, 3 Gold. RepoRadar has retained observations for this record since 2026-09-09 (31 days in the current window).
Who should use it
Who should skip it
Skip agent-memory — Markdown-file long-term memory runtime for coding agents: local ranked retrieval returns paths instead of past if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
agent-memory — Markdown-file long-term memory runtime for coding agents: local ranked retrieval returns paths instead of past is tracked by RepoRadar as a developer tool in the Agent Memory section. First seen 2026-09-09; the source record was last checked on 2026-09-09. The current verdict is 'try now' with a Gold tier and review needed setup difficulty. agent-memory — Markdown-file long-term memory runtime for coding agents: local ranked retrieval returns paths instead of past leads on novelty (10.0) and momentum (10.0); its lowest signal is setup ease (6.5), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The agent-memory — Markdown-file long-term memory runtime for coding agents: local ranked retrieval returns paths instead of past record combines a 8.2/10 composite score with separate popularity (100.0), risk (none), and setup (review needed) 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
No inherent user-impacting risk is flagged from the captured evidence.