Decades of documents. Scattered across drives, backups, and cloud exports. Trover scans them all, finds what matters, and lets you ask questions across your entire history.
Check Out the Demos →Every knowledge worker has the same problem. Years of work product buried across backup drives, Time Machine snapshots, NAS boxes, and cloud exports. You know you wrote that board deck. You just can’t find it.
Time Machine snapshots. NTFS drives from your old Windows laptop. ext4 volumes from a Linux server. NAS shares. Google Takeout. iCloud exports. OneDrive dumps. Your career is spread across a dozen devices, three operating systems, and five cloud services.
Spotlight doesn’t index backup drives. Windows Search ignores external volumes. Linux locate only knows what’s mounted right now. No OS search tool scores relevance, understands context, or searches across filesystem boundaries.
ZIP archives, RAR files, 7z bundles, compressed tarballs, encrypted disk images, Outlook PSTs, Apple Mail archives. Your most important data is trapped inside containers that search tools won’t even open. Trover spelunks in.
You can’t ask an AI about documents it’s never seen. Someone has to scan every drive, crack open every archive, extract the text, deduplicate the copies, and organize it all before a single question can be answered. That’s the job.
From dusty drive to answered question in minutes.
Connect any drive. Time Machine, external HDD, NAS, cloud export. Trover scans and scores every document by your definition of importance.
“What did I present to the board in Q1 2025?” Natural language queries across your entire document history. Powered by RAG.
Get answers with sources. The exact file, the exact slide, the exact paragraph. Deduplicated, scored, and cited.
Hard drives, cloud storage, email archives, compressed bundles, proprietary formats—Trover crosses every boundary. No vendor lock-in, no iron curtains between platforms. Your data is yours, and Trover finds it wherever it hides, deduplicates it across every source, and gives you one clean picture.
Documents, images, audio, video, and email archives. Trover extracts text and tables from PPTX, DOCX, PDF, and XLSX. Reads EXIF and OCR from photos. Transcribes audio and video locally via Whisper. Parses email threads from Apple Mail, Gmail, and Outlook. Everything gets chunked, embedded, and made searchable.
By default, everything runs on your machine—scanning, embeddings, deduplication, extraction. Connect cloud sources when you want to, not because you have to. You control what stays local and what gets indexed from the cloud. No forced uploads, no telemetry, no surprises.
Every file gets scored 0–100 by a 4-tier keyword engine you control. A lawyer weights “deposition.” A PM weights “roadmap.” An MRO tech weights “airworthiness directive.” Year bonuses, system path penalties, and multi-match detection surface what matters and bury what doesn’t.
One YAML file controls everything: local drives, cloud sources, keywords, categories, scoring rules, media settings, transcription models, and output structure. Customize for your domain—legal, aviation, consulting, research—in minutes.
Power failure, drive disconnect, laptop sleep—Trover picks up exactly where it stopped. SQLite WAL mode means zero data loss. Only new or changed files get processed on re-runs. Scan 40,000 files today, plug in the same drive next month, and Trover skips what it already knows.
Ten years of family photos on an old drive. A keynote recording from 2019. A deposition on a thumb drive. Trover doesn’t just find them—it understands what’s inside.
Plug in a drive and find every photo your family took in 2016. Trover reads EXIF data—dates, GPS coordinates, camera model—and runs OCR on screenshots, whiteboards, and scanned documents to make the text inside searchable.
“What did the CEO say in that all-hands?” Trover transcribes audio files locally using Whisper—no cloud, no API costs—and indexes every word. Search your voice memos, podcast recordings, and meeting audio by what was said.
Training videos, Zoom recordings, conference talks, family milestones. Trover extracts the audio track, transcribes it locally, and makes the entire recording searchable. “Find the part where we discussed pricing.”
Trover doesn’t care where your data lives. Plug in a hard drive or connect a cloud account—every file flows through the same scan, score, dedup, extract, and index pipeline.
“What did I email the board in March 2021?” Trover parses your email archives—Apple Mail, Gmail exports, Outlook PSTs, Thunderbird—reconstructs threads, extracts attachments, and makes decades of correspondence searchable.
Connect your Google Drive, Dropbox, OneDrive, iCloud, or Box account and Trover treats it as another drive. No manual exports, no downloads. OAuth read-only access, scan on demand, dedup against your local files automatically.
For teams with data in cloud infrastructure—S3 buckets, GCS objects, Azure Blob containers. Trover connects via IAM or service credentials and indexes everything the same way. Plus Slack exports and Gmail API for live email access.
The same board deck on Google Drive, an old backup HDD, and a Gmail attachment from 2021—Trover resolves all three to a single canonical entry with full provenance. That’s the hybrid model: local and cloud, unified.
Trover isn’t just a desktop tool—it’s data infrastructure. Your scored, deduplicated document corpus, ready to query from whatever you’re building.
RAG queries, semantic search, file browsing, collection management, indexing control, and more—directly from Claude, Cursor, or any MCP-compatible AI tool. 5 resources, 4 prompt templates, zero-config discovery via .mcp.json. Works standalone—no FastAPI needed.
High-performance FastAPI with full search, scoring, retrieval, deduplication, job management, and config control. 6 integration patterns out of the box: Zapier, Slack, multi-agent, CLI, Python SDK, and cURL. 4 deployment modes including Docker and Tauri desktop.
Integrates with all major cloud platforms—with a proprietary hybrid model for local and cloud data intelligence, backup, and retrieval.
Trover is in active development. Join the early access list and be first to dig into your own data.