Kensaku
Kensaku is a free, MIT-licensed desktop launcher for Windows, macOS and Linux that searches file names, text inside documents, OCR'd text in screenshots and meaning, all locally, and lets AI agents search the same index over a read-only MCP server.
Why it matters
For anyone who remembers what was in a file but not its name. It brings full-text, screenshot and meaning-based search to all three desktop platforms without a cloud account, and gives Claude or Cursor local file search through MCP.
Highlights
- Searches names, full text (PDF, DOCX, PPTX, XLSX, EPUB, ODF, RTF, code, logs, CJK text) and meaning in one box, with typo tolerance and plain-language time filters like "last week".
- OCR reads text in images with PP-OCRv6 by default; v1.0.11 adds an optional Indra engine (about 27 MB pack, downloaded only if chosen) with deskew and multi-script recognition.
- Agents connect with kensaku-cli mcp, or over loopback HTTP with a bearer token via kensaku-cli serve; agent tools are read-only and reindex is off by default.
- The maker reports name search across 100,000 files in about 1.3 ms with roughly 12 MB of memory, measured on Linux.unverified
- No account or telemetry; credential files such as .pem and .key are excluded from indexing by default.
Taken from the project's own README, docs or launch page. Claims about speed or accuracy are the maker's unless stated otherwise.
Worth knowing: Builds aren't code-signed yet, so Windows and macOS show security warnings, and there's no auto-updater. The index holds extracted text from your files, so treat it as sensitive. The README says Windows has had the most real-world testing.
Quick facts
| Pricing | Free |
|---|---|
| Free or paid | Free (open source) |
| License | MIT |
| Language | Rust (Tauri app; build needs Bun 1.1+) |
| Platform | Windows, macOS (Apple silicon and Intel), Linux (AppImage, deb, rpm); kensaku-cli included |
| GitHub stars | ★ 255 (as of 2026-10-30) |
| Maker | yjid (GitHub) |
Links
- Repository: https://github.com/yjid/kensaku
- Release notes: https://github.com/yjid/kensaku/releases
- Docs: https://github.com/yjid/kensaku/blob/master/docs/USAGE.md
Related ranking
See how established tools compare in Best Research & Cited Answers. New releases aren't scored until we review them against the rubric.
What we couldn't verify
- highlights[3] (performance figures are the maker's own benchmark)
Checked 2026-10-30 from the tool's own pages. Prices and star counts change, so confirm on the official site. Listing here is not a ranking or an endorsement.
One email a week on AI that saves business owners time
Every Friday: one tool pick with the business use case, what changed in tools you already use, and the week's AI news in plain English. No spam.
Free. Unsubscribe any time. See our privacy policy.