Precision File Search vs Recoll
Precision File Search
pfs-ai.github.ioRecoll
recoll.orgSide by side
| Figure | Precision File Search | Recoll |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | Yes |
| Web | — | Yes |
| Windows | Yes | Yes |
| macOS | Yes | Yes |
| Linux | Yes | Yes |
| Android | — | Yes |
| API | — | Yes |
| Self-hosted | — | Yes |
| Plans published | 1 | 4 |
| Spec score · Desktop Search Software | 7.6 (#23) | 8.4 (#4) |
| Languages | The site lists support for 18 languages, including English, Arabic, Chinese, French, German, Hindi, Japanese, and Spanish. | The index uses Unicode UTF-8 and supports multilingual and multi-character-set searching. |
| What it does | Precision File Search is a desktop application for searching, classifying, and understanding local files. | Recoll is a desktop full-text search program that searches document contents and filenames. |
Plans
Recoll
- LinuxFree
- Recoll (Linux and source)Free
- Recoll for WindowsPriced on request
- Windows binaryPriced on request
In their own words
Precision File Search
Precision File Search is a free desktop application for finding, classifying, and understanding local files on Windows, macOS, and Linux. It combines classic search with semantic search using a retrieval-augmented generation pipeline, and can answer natural-language questions with summarized responses. A trainable machine-learning model sorts scattered documents into categories users define. The maker says the application and AI models can operate locally, without cloud dependency, and that files, queries, and personal data are not sent to external servers. The project lists support for 18 languages, including English, Arabic, Chinese, French, German, Hindi, Japanese, and Spanish. An internet connection is needed on first run to download multilingual AI models; later runs can be offline. PFS supports OpenAI-compatible inference URLs, including online providers and local engines such as Ollama and LM Studio. The README lists 8 GB of RAM for the core platform and a dedicated GPU, with at least 4 GB of VRAM for smaller models, for local LLM use. The project is licensed under MPL-2.0.
Recoll
Recoll is free desktop search software that finds documents by their contents and file names. It indexes many common document formats and compressed files, including email attachments nested inside archives. Search supports Boolean queries, phrases, proximity, wildcards, and filters for file type or directory tree. Indexing can run periodically as a batch job or continuously for real-time updates. Users can search through a Qt desktop interface, a web browser, the command line, GNOME Shell, KDE KIO, or KRunner; the browser interface queries a Recoll index. A Python 3 extension can query or update that index. Recoll can index PDF attachments and annotations, extract custom XMP metadata, and apply OCR to image-only PDFs using Tesseract or ABBYY FineReader. It supports multiple languages and UTF-8, and users can choose a stemming language at query time. Linux and source are free under the GPL. A contribution is requested for the Windows binary, but no amount is stated. Some formats on Linux and macOS need external applications or libraries, and the Windows port lacks some features, including multithreaded execution.