
Freshvault
io.github.KIOKO-LABPublished by GitHub account KIOKO-LABv0.4.0Updated Oct 24, 2026
Local semantic search over your Obsidian vault - always fresh, never reindex.
Overview
Freshvault gives an assistant local semantic search over an Obsidian vault, keeping the index fresh automatically without manual reindexing.
- What you can do
- Search notes semantically, with optional folder, tag and modification-date scoping and exact-title boosting, returning at most two chunks per note. Retrieve a full note together with its backlinks and outlinks from the vault link graph. Check index freshness: note and chunk counts, excluded notes, last sync and watcher state. All three tools are read-only.
- When to use it
- Use it when you keep notes in an Obsidian vault and want an assistant to answer questions from them, especially in Korean, Japanese or other non-English languages, without running index or watch commands.
- Requirements
- A local process run via npx, needing Node 20+ and a running Ollama instance with the bge-m3 embedding model (pulled by the setup wizard). The vault path is set by the FRESHVAULT_VAULT environment variable or the setup command. An OpenAI-compatible embedding endpoint can be used instead via FRESHVAULT_EMBED_API and FRESHVAULT_EMBED_URL, with FRESHVAULT_EMBED_KEY for authenticated endpoints.
Installation
In SourceWeft
- Open Freshvault in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
freshvault
[CI] [npm] [MCP Registry] [node]
Your Obsidian vault is Claude's memory. Always fresh, always local.
Every other vault-search MCP makes you re-run an index command, babysit a watch terminal, or click "Update Index" in a web UI. freshvault watches your vault from inside the MCP server: edit a note, and Claude sees it seconds later. Automatically. Forever.
- 🔄 Never reindex — the file watcher lives in the server process; boot catch-up absorbs offline edits
- 🔒 100% local — embeddings via Ollama (
bge-m3), your notes never leave your machine - 🌏 Multilingual by default —
bge-m3handles Korean, Japanese, and 100+ languages that English-only defaults fail on - 🎯 Benchmark-driven retrieval — unconditional BM25 fusion wrecked Korean paraphrase queries (82.5% → 47.5% top-1), so it's off; pure dense missed identifier queries outright (57.1%), so it's not gone either. Lexical scoring is gated on code-like query tokens: paraphrase 82.5% → 82.5% (identical), identifiers 57.1% → 100% — receipts
- 🪶 No vector DB, no Docker, no Python — JSON metadata + a Float32 sidecar, plain Node, source you can read in one sitting
- 🧠 Chunking that respects sentences — YAML frontmatter stripped, splits on paragraph/sentence boundaries (CJK-aware)
Install
Prerequisites: Node 20+ and Ollama.
That's it. The wizard detects your Obsidian vault, pulls the embedding model, builds the index, and registers with Claude Code. There is no step 2, and there is never a step 2: no index command to re-run, no watch terminal, no background service.
Manual install (Claude Desktop / Cursor / Windsurf)
Claude Code one-liner:
Use
Just ask Claude about your notes:
"Search my notes for what I wrote about cache eviction strategies"
Three tools, all read-only:
Scoped queries competitors gate behind settings or paywalls work per-query here:
"Search my notes tagged #project modified after June for the budget discussion"
How it works
- Incremental: only changed/deleted notes are re-embedded (mtime+size diff), debounced 4s
- Safety net: a 60s mtime sweep catches events the watcher misses (network drives, atomic-rename editors)
- Multi-client safe: first server process becomes the writer (heartbeated lock); others are readers that hot-reload and promote themselves if the writer dies
- Transactional: an embedding-server outage mid-index can never lose or corrupt notes
- Scale: vectors live in a packed Float32 sidecar (fast startup, compact); brute-force cosine over thousands of chunks is milliseconds. Honest note: search is still linear — sub-100ms into tens of thousands of chunks, but this is not a vector DB replacement for huge corpora
Multiple vaults
Register one server per vault — index files are kept per-vault automatically:
Other embedding servers (LM Studio, LiteLLM, OpenAI-compatible)
Anything speaking /v1/embeddings works; FRESHVAULT_EMBED_KEY for authenticated endpoints (never written to the config file).
Configuration
Everything works with zero config after setup. Override when needed:
Commands: setup · serve (default) · index (manual escape hatch) · status
Ignore patterns
Patterns follow gitignore semantics, matched against vault-relative paths:
- A slash anywhere but the end anchors the pattern to the vault root. A trailing slash only means "directory" — it does not anchor.
*and?never cross a/.**crosses directories only as a whole path segment (**/x,x/**,x/**/y); glued inside a segment it collapses to a single*, as in git.- Matches end on a segment boundary —
Templatesnever matchesTemplatesOld. !negation and character classes are not supported; such patterns match nothing.FRESHVAULT_IGNOREis comma-separated, so a pattern cannot contain a comma.
Behaviour change since v0.3.0. v0.3.0 treated a trailing slash as a root anchor, so
Templates/excluded only the vault-rootTemplates/and silently indexed every nested one — no warning, just a quietly polluted index. Patterns shaped likeTemplates/,/Templates,**/xanda/**/bnow exclude more than before (/Templatespreviously matched nothing at all). Conversely,**glued inside a segment (Daily**md) no longer crosses/. Runfreshvault statusafter upgrading and compare the excluded count if it matters to you.
Benchmark
Two retrieval micro-benchmarks ship in-repo (node scripts/bench.mjs): ko-bench (30 Korean notes, 40 paraphrase queries) and id-bench (38 technical notes, 14 identifier queries). Both run under three scoring modes — dense, hybrid-always, and the shipped gated mode — and the script checks the no-regression contract itself. Results and the bge-m3-ko (85.0% top-1, 634MB) import guide in docs/ko-bench.md.
Roadmap
- MCPB bundle for one-click Claude Desktop install
- Reranking pass for large vaults
- PDF text extraction at index time
License
MIT © Kioko Lab
Source: README.md at commit dc6c610
Tools
0Version history
1- v0.4.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts