Semantic memory for your Obsidian vault · Beta v0.2.0

A finding aid for your knowledge graph

Turns your Obsidian vault into a live, queryable knowledge graph. Connect it once — every agent you use gets semantic search, wikilink traversal, and vault health through standard MCP tools.

Terminal · archiver-rag Acc. No. 0001

How your notes become searchable

From save to searchable in seconds

A background file watcher fires on every Obsidian save, re-chunks the note, and updates the vector index — no manual step required.

Step 01
The Vault
Your Obsidian markdown files, organised however you work. archiver-rag watches the root non-destructively.
Step 02
Ingest
On every save the watcher picks up the change, splits the note into 500-word overlapping chunks, and prepends structural metadata.
Step 03
ChromaDB
Vectors stored locally with rich metadata: folder, type, tags, wikilinks, incoming link count. Persistent across restarts. Chunks for deleted or moved notes are pruned automatically — the index never drifts from disk.
Step 04
The Agent
Any MCP-compatible agent calls search_vault and receives ranked results with graph boost scores.

How search ranks what matters

Three layers of signal, not one

Semantic similarity is the entry point. Graph proximity and hub importance shape the final ranking.

Layer I
Contextual prefix

Before embedding, each chunk is prepended with the note's location, tags, and wikilinks. The vector carries structural context, not just raw text — so similar structure surfaces alongside similar meaning.

Layer II
Metadata filtering

Every chunk is stored with folder, type, tags, wikilinks, and incoming link count. The type field is a ChromaDB pre-filter — applied before the vector ranking runs. Tags narrow the result set post-retrieval over an over-fetched candidate pool.

Layer III
Graph reranking

After ChromaDB returns candidates, scores are boosted by proximity to a context_note and by hub importance — how many other notes link to this one.

Everything the service can do

What it can do

Eight capabilities built into the same background service.

Ref · 001
Auto-linking

After every ingest, linker.py rebuilds the ## Related section with wikilinks to every note that clears a relevance margin of the top match — the graph stays dense where it matters, not append-only noise.

Ref · 002
Knowledge logging

log_note creates notes in typed folders (decision/, lesson/, gotcha/) — the filename is the note's identity, the date lives in frontmatter. The watcher picks them up and auto-links them immediately.

Ref · 003
Vault health

vault_status returns orphaned notes, missing frontmatter, broken wikilinks, tag stats, and recent activity — in a single MCP call, no arguments.

Ref · 004
Link-aware moves

move_notes moves one or many files and rewrites every [[wikilink]] across the vault automatically. No orphaned references left behind.

Ref · 005
Semantic folder placement

Each folder declares a description in _folder.md — generated by archiver-rag describe and kept fresh by the watcher. New notes are embedded against those descriptions and moved to the best match above a threshold, with a frontmatter type: fallback. The watcher runs this automatically; full-graph label propagation stays a manual command.

Ref · 006
Smart clustering

Label propagation over the wikilink graph suggests folder groupings for the entire vault. Preview first, then --apply to move files — deliberately manual, run when you want a reorganization pass.

Ref · 007
Soft delete

archiver-rag delete moves notes to .trash/ (Obsidian's own delete convention — recoverable, no rm) and sweeps every inbound [[wikilink]] across the vault so nothing points at a gone note.

Ref · 008
Agent-agnostic

Standard MCP over stdio or HTTP. No proprietary SDK, no vendor lock-in. Claude Code, Cursor, Windsurf, Gemini CLI, Zed — if it speaks MCP, it works with archiver-rag.

Structure your vault understands

Notes are nodes.
Wikilinks are edges.

archiver-rag understands the structure of your vault, not just the text inside it. Every [[link]] is a graph edge that shapes search, clustering, and auto-linking.

Frontmatter is first-class: type and tags are stored as filterable metadata on every chunk. type is the stable taxonomy — it reads frontmatter, not the folder, so it survives auto-cluster moves.

type: decision tags: [architecture] related: pattern-async date: 2026-04-18
Knowledge graph — notes as nodes, wikilinks as edges INDEX.md decision-04 pattern-async lesson-02 gotcha-11 meeting-01 idea-07

Tools exposed to any MCP agent

Six tools. Any agent.

Every capability is a discrete MCP tool — discoverable, composable, and callable from any agent that speaks stdio MCP.

№ Tool Function
001 search_vault Semantic search with graph reranking. Pass context_note to boost wikilink neighbors of a known note. Filter by frontmatter type (stable across folder moves) or narrow by tags.
002 vault_status Structure, health, orphaned notes, tag statistics, and recent activity — one call, no arguments.
003 get_connections BFS wikilink traversal. Returns direct links or multi-hop neighborhoods up to depth 3.
004 move_notes Move one or many files. All [[wikilinks]], [[note#heading]], and [[note|alias]] forms across the vault are rewritten automatically, including bare names in YAML related: blocks.
005 log_note Create a knowledge note from any agent. Filename is the note's slug-identity; date lives in frontmatter. The watcher indexes and auto-links it within seconds.
006 suggest_folder Suggestion only — never moves anything. Suggests a folder for one note by semantic similarity against declared folder descriptions (_folder.md), with a frontmatter type: fallback, using the same config as the CLI and the watcher. Returns the score and the winning reason; a wikilink neighbor vote comes along for reference. Call move_notes to act on it.

Up and running in minutes

Up and running in three commands

Install the package with pipx or uv, point it at your vault, then register it as an MCP server — done.

pipx install archiver-rag
uv tool install archiver-rag
archiver-rag init
claude mcp add --scope user archiver-rag $(which archiver-rag) serve
~/Documents/MyVault — archiver-rag
$ pipx install archiver-rag ✓ archiver-rag is now on your PATH $ archiver-rag init Path to your Obsidian vault: ~/Documents/MyVault Start automatically on login? [y/n]: y ✓ Config saved → ~/.config/archiver-rag/config.json ✓ Indexed 47 notes, 203 chunks ✓ Watcher service registered (launchd) $ claude mcp add --scope user \ archiver-rag $(which archiver-rag) serve ✓ MCP server registered $ archiver-rag status ✓ running · 47 notes indexed