← Back to Remember

REMEMBER.md Spec v1

Open standard for AI memory configuration. Status: Living Draft · Last updated 2026-05-05

Pitch

AGENTS.md tells your AI how to work. REMEMBER.md tells your AI how to remember. Together they form the markdown duo for portable, tool-agnostic AI configuration — one file for behaviour, one for memory, both human-readable and version-controllable.

Core rules

  1. The file is named REMEMBER.md.
  2. It lives at the root of your brain (or any project that needs overrides).
  3. It is plain markdown. ## Section Name headings delimit blocks.
  4. Seven section names are reserved by the spec (see below). All optional.
  5. An empty file means "use engine defaults". Zero config = it works.
  6. Engines MUST ignore sections they don't understand (forwards-compatible).
  7. Engines MUST NOT auto-modify the file. It belongs to the user.
  8. User rules override engine defaults; project-level overrides global.

Reserved sections

SectionPurpose
## Capture RulesAlways-capture / never-capture filters and thresholds.
## RoutingWhere each kind of content lands in the brain.
## ProcessingHow content is formatted, tagged, summarised.
## Custom TypesUser-defined entity types beyond the engine's defaults.
## ConnectionsAuto-linking rules and relationship hints.
## LanguageMultilingual capture and processing preferences.
## Promotion ThresholdsConfidence/sources thresholds for promoting beliefs to a pinned section.
## TemplatesOverride engine-default templates per file kind.

Override semantics

Engine guarantees

Reference parser (20 lines)

import re

def parse_remember_md(path):
    with open(path) as f:
        text = f.read()
    sections = {}
    for match in re.finditer(
        r'^## (.+)\n(.*?)(?=^## |\Z)',
        text, re.M | re.S
    ):
        name = match.group(1).strip()
        content = match.group(2).strip()
        if content:
            sections[name] = content
    return sections

Reference implementation

The Remember plugin (github.com/remember-md/remember) is the canonical engine. It ships:

Adopting REMEMBER.md

Tool authors are encouraged to read REMEMBER.md from the project root and apply the rules described above. A 20-line parser (in any language) is enough for v1 compliance. Engines are free to extend with additional sections, as long as they do so under the ## x-* prefix or as ## Override: <name> blocks to avoid name conflicts.

Versioning

Status & contributions

v1 is a living draft. Implementations, feedback, and competing parser libraries are welcome at github.com/remember-md/remember/issues.


Inspired by .editorconfig (one page, dead-simple, 30+ editors), llms.txt (markdown-native, grassroots), and AGENTS.md (cross-tool agent instructions).