Skip to content
SkillModel-led1,512 tokens in use

memory-bridge

Browse, search and compare Obsidian wiki pages by the AI tool that produced them, and see which tools hold knowledge the others have never touched.

3,792 stars on the repository MIT LicenseAr9av/obsidian-wiki · skills/memory-bridge
pip install obsidian-wiki
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing memory-bridge costs

42tokens idle
1,512tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

memory-bridge reads the vault manifest to find which AI tool each wiki page came from, then lets you work with that view. You can list the pages from one tool, search within them, diff two tools, or print a matrix of every page against every tool.

Recognized sources are claude, codex, hermes, openclaw, copilot, pi, hand-written pages and documents added through ingest. The diff mode points out the most surprising gaps between tools.

What You Get

  • A list of the pages each AI tool contributed, grouped by category
  • A diff of two tools showing what only one of them knows
  • A page by tool matrix, with the most cross-tool pages first
  • A log entry in the vault for each use

Common Use Cases

  • See what your Codex sessions taught the wiki that Claude never saw
  • Find the topics a tool has covered, then search within them
  • Spot blind spots when you use several agents
  • Check how much knowledge each tool has contributed

What Makes It Unique

It uses source provenance already recorded in the manifest and in page sources fields, so it needs no extra tagging. It reads page frontmatter and not full bodies, and it names the most surprising asymmetry between tools as the main finding of a diff.

Under The Hood

The skill is instructions for the agent. It reads the vault config, manifest and index, greps page frontmatter, and runs ripgrep over the pages from one tool for search mode. It can spawn the impl-validator subagent to check its own output, and it appends one line to the vault log. It writes nothing else and makes no web requests.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers