Item detail
github.com

NanoFlow-io/engram

NanoFlow-io/engram is a package that RepoRadar is tracking in its Agent Infrastructure section, currently rated Silver tier with a 'worth watch' verdict. Its strongest signal is open-source/build quality, scored 8.4 out of 10.

Score7.6
Popularity1.0
Riskconditional
TierSilver
Score breakdown
Usefulness7.0
Novelty8.0
Momentum6.0
Maturity5.6
Open-source/build8.4
Evidence7.2
Workflow potential8.4
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for OpenClaw users who want a local-first memory layer they can inspect, tune, and decay instead of treating long-term agent memory as a black box.

Who should use it

OpenClaw users who want persistent local memory between sessionsAgent builders comparing hybrid structured-plus-semantic memory designsDevelopers who need inspectable memory storage instead of a hosted memory black boxAdvanced users tuning decay classes and recall behavior for long-running agents

Who should skip it

Hold off on NanoFlow-io/engram until it graduates from watchlist status with stronger evidence.

About this signal

NanoFlow-io/engram is tracked by RepoRadar as a package in the Agent Infrastructure section. It was first seen on 2026-07-01 and last updated on 2026-07-01. The current verdict is 'worth watch' with a Silver tier and moderate setup difficulty. NanoFlow-io/engram leads on open-source/build quality (8.4) and workflow potential (8.4); its lowest signal is maturity (5.6), so factor that in before investing setup time. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned NanoFlow-io/engram a composite score of 7.6 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

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

Embeddings can be sent to OpenAI if you use the documented default embedding path, so sensitive memory categories should stay out until you confirm provider choice and retention settings; Auto-capture and auto-recall hooks can resurface stale or sensitive project context, so first setup should keep categories narrow and review the decay settings.

Evidence links
Closest alternatives / related signals
agent-memoryopenclawsqlitelancedbpluginmit