monkeSearch
monkeSearch is a free, open-source desktop utility for finding local files with natural-language queries.
What monkeSearch is
monkeSearch is a free, open-source desktop utility for finding local files with natural-language queries. Searches can combine a file type, temporal context, and other keywords. The project describes two fully offline approaches, with no data leaving the machine. Its main development branch uses a local language model to translate queries into macOS Spotlight search arguments, relying on Spotlight’s existing index and the NSMetadataQuery API. That branch is currently macOS-only and searches Spotlight-indexed files and metadata, not file contents. A separate vectordb branch replaces live query-time language-model use with vector databases and is described as supporting macOS, Windows, and Linux. On Windows, that design crawls the filesystem with os.walk and uses ChromaDB for storage and retrieval. The main branch requires macOS, Python 3.8 or later, llama-server, and a GGUF model. The project is Apache-2.0 licensed.
Good
- Fully offline processing keeps data on the machine
- Natural-language queries combine type and time context
- Open source under the Apache-2.0 license
- Vectordb branch is described as cross-platform
- Spotlight approach is read-only with access controls
Watch out
- Main branch is currently macOS-only
- Search covers indexed metadata, not file contents
- Small models may misunderstand queries
- Main setup requires a roughly 700 MB model
Who it suits
It suits users who want offline, natural-language searches across local files. The main branch is for macOS users comfortable meeting its Python, llama-server, and GGUF requirements.
Verdict
monkeSearch provides private, natural-language local-file discovery, especially on macOS through Spotlight. Check its indexing and metadata limits, or consider the vectordb branch for the described cross-platform approach.
The facts
Each one read from monkeSearch's own pages, with the date it was checked.
What it does
- Agent use
- The maker says the LLM-based implementation can serve as a natural-language file-discovery bridge for AI agents and orchestration systems.checked 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.checked 11 Oct 2026
- Data handling
- The maker says nothing leaves the machine; the Spotlight approach is read-only and uses Spotlight's access controls.checked 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.checked 11 Oct 2026
- License
- The repository lists the project under the Apache-2.0 license.checked 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.checked 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.checked 11 Oct 2026
- Local processing
- The project says both its LLM and vector database approaches run fully offline.checked 11 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.checked 5 Oct 2026
- Product
- monkeSearch is an open-source, offline-first desktop tool for searching local files with natural-language queries.checked 5 Oct 2026
- Purpose
- monkeSearch is an offline-first desktop tool for searching local files with natural language.checked 11 Oct 2026
- Requirements
- The repository lists macOS, Python 3.8+, llama-server from llama.cpp, and a GGUF model as requirements.checked 11 Oct 2026
- Search inputs
- The maker describes queries as combining file type, temporal context, and other keywords.checked 5 Oct 2026
- Search queries
- Queries can combine file type, temporal context, and other keywords.checked 11 Oct 2026
- Security
- The maker describes the Spotlight-based approach as read-only and scoped through Spotlight’s access controls.checked 5 Oct 2026
- Support
- The project page asks users who find the open-source project useful to star its GitHub repository.checked 11 Oct 2026
Where it runs
- Current platform status
- The repository describes the main branch as currently macOS-only and says cross-platform support is in the vectordb branch.checked 11 Oct 2026
- macOS approach
- The main/dev branch uses a local LLM to turn queries into macOS Spotlight search arguments.checked 11 Oct 2026
- macOS integration
- The main/dev branch uses Spotlight’s existing index and the NSMetadataQuery API for file discovery.checked 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.checked 5 Oct 2026
- Vector database approach
- The vectordb branch uses vector databases instead of a live LLM at query time and is described as cross-platform.checked 11 Oct 2026
- Windows integration
- The vectordb Windows architecture uses an os.walk filesystem crawl and ChromaDB for vector storage and retrieval.checked 5 Oct 2026
Alternatives to monkeSearch
- 1
Recoll
Free planOpen sourceAndroidWebAPIExtension7.9Free plan - 2
GitHub CodeQL
Free planWebExtensionLinuxmacOS7.5From $30 a month - 3
Open Semantic Desktop Search
Free planOpen sourceWebAPIExtensionLinux7.5Free plan - 4
Agent Ransack
Free planWindows6.6$20 one-time - 5
Magpie
Free planWindows6.6Free plan - 6
WizFile
Free planWindows6.6$20 one-time