Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI researchers, ML researchers, agent developers, learners, self-learners, students, autodidacts, technical educators, AI-curious readers, founder-CTOs, engineering teams, technical writers, and anyone who wants Claude Code (or OpenAI Codex) to remember what they explained instead of forgetting it ten days later -- and who can pair Engram with a Claude Code subscription (or OpenAI Codex
Who should use it
Who should skip it
Move on from nagisanzenin/engram if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
nagisanzenin/engram is tracked by RepoRadar as a evidence-based learning engine f in the Learning / Agent Plugin section. It was first seen on 2026-07-06 and last updated on 2026-07-06. The current verdict is 'try now' with a Gold tier and easy setup difficulty. Across RepoRadar's eight signals, nagisanzenin/engram is strongest on workflow potential (9.9) and practical usefulness (9.0) and weakest on maturity (6.6) — a profile worth weighing against your own priorities. 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 nagisanzenin/engram a composite score of 8.4 out of 10, placing it in the Gold 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 'low' 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
Version 0.3.0 is recent (created 2026-07-05; 1 day before this cycle) and the community is small (275★) -- treat the first evaluation cycle as a smoke test (install via `claude plugin marketplace add nagisanzenin/engram` + restart the Claude Code session + run /learn on one topic + work through 3 concepts + check the receipts at ~/.claude/learning/) before relying on the FSRS-4.5 scheduler for production learning flows; the data path is 100% local but the curriculum architect fires web search on new-topic map builds -- keep secrets out of the goal line; or ask for an offline map (the README documents both paths).