vault-of-loci
llms.txt0 starsChanged 5 days agoMITView on GitHub
An Obsidian vault template for learning anything (a course, book, certification, interview, research, skill or language) with AI agents: tracks, sessions, concept notes, references that say whether they were verified, flashcards and automatic checks. Rules for agents are in AGENTS.md.
In this repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- adaptive-scaffoldSkill
- calibration-coachSkill
- compression-challengeSkill
- counterfactualSkill
- defuddleSkill
- dependency-checkSkill
- error-recoverySkill
- json-canvasSkill
- memory-palaceSkill
- misconception-drillSkill
- mistake-reviewSkill
- new-concept-noteSkill
- new-trackSkill
- no-ai-checkpointSkill
- obsidian-basesSkill
- obsidian-cliSkill
- obsidian-markdownSkill
- pretestSkill
- process-paperSkill
- process-webSkill
- quizSkill
- record-attemptSkill
- recovery-after-inactivitySkill
- retention-auditSkill
- review-queueSkill
- run-checksSkill
- schedule-reviewSkill
- spoken-mockSkill
- teach-the-agentSkill
- transfer-labSkill
- vault-searchSkill
- visual-reconstructionSkill
The file
Files
# Vault of Loci > An Obsidian vault template for learning anything (a course, book, certification, interview, research, skill or language) with AI agents: tracks, sessions, concept notes, references that say whether they were verified, flashcards and automatic checks. Rules for agents are in AGENTS.md. ## Start here - [INDEX.md](INDEX.md): every note with its type, line count and summary; open sections by line range from 90_System/index.json - [README.md](README.md): what it is, how to start and which agent reads which file - [AGENTS.md](AGENTS.md): how to read the vault, frontmatter, writing rules, tutor mode, safety - [How_to_Study_with_this_Vault.md](How_to_Study_with_this_Vault.md): the study method - [00_Home.md](00_Home.md): dashboard ## Examples - [Retrieval practice](20_Concepts/Retrieval_Practice.md): a concept note with the full study layer - [Test-enhanced learning](40_References/Papers/Test-Enhanced_Learning_(Roediger_and_Karpicke,_2006).md): a verified paper note - [Example course](10_Tracks/01_Example_Course/Example_Course.md): a track of kind course with one session - [Example book](10_Tracks/02_Example_Book/Example_Book.md): a track of kind book with one chapter session ## Guides - [Studying with AI](40_References/Guides/Studying_with_AI.md): evidence, tutor-mode protocol and FSRS - [Research reading pipeline](40_References/Guides/Research_Reading_Pipeline.md): papers in three passes, then a verified reference note - [Reading and highlights](40_References/Guides/Reading_and_Highlights.md): what to do instead of highlighting and rereading - [Repository and documentation patterns for AI](40_References/Guides/Repository_and_Documentation_Patterns_for_AI.md) ## Optional - [Tools and customization](90_System/Specs/Tools.md): every script, what each check guards, and how to customize - [Track kinds](90_System/Specs/Track_kinds.md): one recipe per kind of learning project, and the rituals every track shares - [Study layer spec](90_System/Specs/Study_layer.md) - [Mistakes log](50_Review/Mistakes.md): wrong answers and their corrected cards - [Checkpoint template](90_System/Templates/Checkpoint.md): closed-book session sheet - [Weakest concepts base](90_System/Bases/Weakest.base) - [Interleave base](90_System/Bases/Interleave.base) - [Progress base](90_System/Bases/Progress.base): sessions by track and what to review next - [Blueprint base](90_System/Bases/Blueprint.base): concepts ranked by exam weight and confidence - [Tutor mode eval](90_System/Evals/Tutor_mode.md): seventeen scenarios to check an agent by hand or with a script - [Tutor mode eval results](90_System/Evals/Tutor_mode_results.md): every run kept here, with the judges, the interval and whether they agree - [Learning eval](90_System/Evals/Learning_evals.md): fifteen scenarios on whether the agent uses the learner's record - [Learning eval results](90_System/Evals/Learning_evals_results.md): every run of the learning benchmark kept here
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

