- Home
- Desktop Search Software
- monkeSearch
On the recordRead 11 Oct 202622 facts
monkeSearch
On the record
- Agent use
- The maker says the LLM-based implementation can serve as a natural-language file-discovery bridge for AI agents and orchestration systems.monkesearch.github.io · read 5 Oct 2026
- Benchmark
- The maker's benchmark page says its query-parsing evaluation covers 80 queries across file type, temporal awareness, combined queries, and noise resistance.monkesearch.github.io · read 11 Oct 2026
- Current platform status
- The repository describes the main branch as currently macOS-only and says cross-platform support is in the vectordb branch.github.com · read 11 Oct 2026
- Data handling
- The maker says nothing leaves the machine; the Spotlight approach is read-only and uses Spotlight's access controls.monkesearch.github.io · read 11 Oct 2026
- Integrations
- The main/dev approach uses macOS Spotlight and is described as a natural-language filesystem bridge for AI pipelines and agents.monkesearch.github.io · read 11 Oct 2026
- License
- The repository lists the project under the Apache-2.0 license.github.com · read 11 Oct 2026
- License and support
- The project is open source under the Apache-2.0 license, and its site asks users to support it by starring the repository.github.com · read 5 Oct 2026
- Limitations
- The repository says the main implementation searches Spotlight-indexed files, searches metadata rather than file contents, and supports only simple time expressions.github.com · read 11 Oct 2026
- Local processing
- The project says both its LLM and vector database approaches run fully offline.monkesearch.github.io · read 11 Oct 2026
- macOS approach
- The main/dev branch uses a local LLM to turn queries into macOS Spotlight search arguments.monkesearch.github.io · read 11 Oct 2026
- macOS integration
- The main/dev branch uses Spotlight’s existing index and the NSMetadataQuery API for file discovery.monkesearch.github.io · read 5 Oct 2026
- Performance tradeoff
- On macOS, the maker says disabling LEANN recompute makes searches faster at the cost of disk space; recompute is enabled by default.monkesearch.github.io · read 5 Oct 2026
- Platform architecture
- The maker describes vectordb support for macOS, Windows, and Linux; the repository says the main branch is currently macOS-only.github.com · read 5 Oct 2026
- Product
- monkeSearch is an open-source, offline-first desktop tool for searching local files with natural-language queries.monkesearch.github.io · read 5 Oct 2026
- Purpose
- monkeSearch is an offline-first desktop tool for searching local files with natural language.monkesearch.github.io · read 11 Oct 2026
- Requirements
- The repository lists macOS, Python 3.8+, llama-server from llama.cpp, and a GGUF model as requirements.github.com · read 11 Oct 2026
- Search inputs
- The maker describes queries as combining file type, temporal context, and other keywords.monkesearch.github.io · read 5 Oct 2026
- Search queries
- Queries can combine file type, temporal context, and other keywords.monkesearch.github.io · read 11 Oct 2026
