0xwilliamortiz
Featured
ponytail-improved
Ponytail is a plugin for AI coding agents that enforces a disciplined ladder of reuse before writing code, reducing code volume by roughly 54% while preserving safety.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It is notable for applying rigorous learning science (generation effect, FSRS scheduling, blind grading) within coding assistant workflows, with a fully audited grader that has never inflated grades (0/258), and full local data ownership.
Who it is for
- Developers using AI coding assistants who want to remember technical concepts
- Self-directed learners in STEM, music theory, or any structured topic
- Educators and researchers interested in evidence-based AI tutoring and retention measurement
- Users of Claude Code, OpenAI Codex, or other supported platforms
Use cases
- Learn new topics during coding sessions (e.g., Kalman filters, Rust lifetimes)
- Daily 2–4 minute review sessions to reinforce learned material
- Weekly coaching for retention stats, calibration, and dashboard
- Export anonymized learning data for community science (optional, consent-based)
Strengths
- Evidence-based: implements generation, spaced practice, FSRS-4.5, and blind assessment
- Multi-platform: works with Claude Code, OpenAI Codex, OpenCode, Hermes Agent, Antigravity, OpenClaw
- Privacy-first: 100% local (no network code, verified by build test), state files owned by user
- Audited grader: 0/258 blind judgments graded up; gold set publicly auditable
Considerations
- Requires Python3 (stdlib only, stock macOS/Linux works)
- Learning sessions can take 5–60 minutes (user-controlled intensity)
- Some platform integrations have minor gaps (e.g., Antigravity nudge not ported, OpenClaw needs config flag)
README quick start
Your AI can explain anything. Engram makes sure you still know it next month.
The mix-up worth clearing first: Engram is not an agent-memory plugin. It doesn't give your agent persistent memory, context, or knowledge of your codebase — memory MCPs and context tools do that, for the agent. Engram points the other way: it's a learning system for the human. Your agent becomes a tutor that makes you do the thinking, a blind examiner that checks you actually got it, and a scheduler that brings each idea back right before your brain drops it. The agent doesn't get smarter. You do — measurably, with receipts.
Born as a Claude Code plugin; the same skills and engine now run on six agentic platforms — including, as of v1.0.8, one that puts the tutor in your chat app:
claude plugin marketplace add nagisanzenin/engram
claude plugin install engram@engram
| Platform | Install | Then |
|---|---|---|
| Claude Code (born here) | the two commands above | /learn /review /coach |
| OpenAI Codex | codex plugin marketplace add nagisanzenin/engram then codex plugin add engram@engram → INSTALL-CODEX.md | $learn $review $coach |
| OpenCode | "plugin": ["opencode-engram-learning"] in opencode.json (npm) | /learn /review /coach |
| Hermes Agent | clone + skills.external_dirs → INSTALL-HERMES.md — verified live on v0.18.2 | /skill learn (or /study) /review /coach |
| Google Antigravity | agy plugin install https://github.com/nagisanzenin/engram | /learn /review /coach |
| OpenClaw | openclaw plugins install engram --marketplace nagisanzenin/engram → INSTALL-OPENCLAW.md — verified on 2026.7.1-2 | /learn /review /coach |
OpenCode: opencode.json is read globally (~/.config/opencode/opencode.json) or per-project; pin to source instead of npm with "plugin": ["git+https://github.com/nagisanzenin/engram.git"].
Antigravity: The due-review session nudge isn't ported yet, and the architect and smith subagents are currently dropped by AG 1.1.4's strict installer. Everything else works the same.
OpenClaw: the nudge needs openclaw config set hooks.internal.enabled true (OpenClaw ignores plugin hooks until internal hooks are switched on), and it fires on `/new
Description
Evidence-based learning engine for Claude Code — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.
Related repositories
Similar projects matched by category, topics, and programming language.
makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
0xwilliamortiz
Featured
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.