Engram
A learning engine for the agent: first-principles curricula, free-recall checks, FSRS-scheduled memory and explorable materials
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- Creates and saves learning materials and progress data to disk
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/engramDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run one by one in the Claude Code chat
/plugin marketplace add nagisanzenin/engram
/plugin install engram@engramInstall the plugin: claude plugin marketplace add nagisanzenin/engram, then claude plugin install engram@engram. Commands: /learn, /review, /coach.
Other ways from the author
claude plugin marketplace add nagisanzenin/engram
claude plugin install engram@engramThis is third-party code. Review the repository files before installing.
What it does
Engram adds three learning commands to the agent: build a curriculum, check knowledge and coach further. Material is taught from first principles, and checks use free recall with a record of what you remembered. Review is scheduled by the FSRS algorithm so topics come back at the right time. Results are saved as explorable materials you can open and study. It installs as a plugin in several agents.
Who it is for. For self-learners and teachers who want to retain knowledge rather than just read the material.
Good fit when
- You need to learn a new topic from first principles
- You need to check what you actually remember
- You need a review schedule so you do not forget
Not a fit when
- You need a quick answer to a one-off question
- You are not ready to keep up regular reviews
Example request
Build a linear algebra curriculum from first principles and quiz me with free recallLimitations
The quality of curricula and checks depends on the agent's model. Progress data and materials are stored locally, so keeping them safe is up to you.
How to disable. Remove the engram plugin through your agent's tools, for example claude plugin remove.
Security check
- Creates and saves learning materials and progress data to disk
README in short
The README describes Engram as a learning engine with three commands: build a curriculum, check and coach. Checks use free recall with a recorded result, reviews are scheduled by FSRS, and outcomes are saved as explorable materials. Installation is shown for Claude Code, Codex, Antigravity and other agents, each with its own INSTALL file. Commands per platform are listed.
FAQ
How does review work?
By the FSRS algorithm: the engine tells you when to return to a topic to retain it.
Which agents does it support?
Claude Code, Codex, OpenCode and several others; install methods are listed in separate INSTALL files.
Related
A self-hosted knowledge base with block-level references and a built-in MCP server for connecting AI agents to your notes
A CLI for every Google Workspace API with JSON output and agent skills: Drive, Gmail, Calendar, Sheets and more
Local search over Markdown notes, docs and meeting transcripts: keywords, semantic search and reranking, with an MCP server
A task manager for AI-driven development: breaks a PRD into dependent tasks and guides the agent through them via MCP or CLI