--- title: "MiniSearch vs cherche" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/felladrin-minisearch-vs-raphaelsty-cherche" tools: ["felladrin-minisearch", "raphaelsty-cherche"] --- # MiniSearch vs cherche *GraphCanon updated Aug 25, 2026* ## Verdict Pick MiniSearch if miniSearch is a minimalist web-search platform that integrates AI capabilities such as question answering and retrieval-augmented generation directly into browsers; pick cherche if cherche is a Python library for implementing neural search capabilities. [MiniSearch](https://felladrin-minisearch.hf.space) reports 581 GitHub stars, 66 forks, and 0 open issues, last pushed Aug 24, 2026. [cherche](https://github.com/raphaelsty/cherche) has 332 stars, 14 forks, and 4 open issues, last pushed Jun 1, 2024. Figures are from public GitHub metadata via [MiniSearch's repository](https://github.com/felladrin/MiniSearch) and [cherche's repository](https://github.com/raphaelsty/cherche). | | [MiniSearch](/tools/felladrin-minisearch.md) | [cherche](/tools/raphaelsty-cherche.md) | | --- | --- | --- | | Tagline | Minimalist web-searching platform featuring an AI assistant for browser-based queries. | Neural Search | | Stars | 581 | 332 | | Forks | 66 | 14 | | Open issues | 0 | 4 | | Language | TypeScript | Python | | Adopt for | MiniSearch is a minimalist web-search platform that integrates AI capabilities such as question answering and retrieval-augmented generation directly into browsers. | Cherche is a Python library for implementing neural search capabilities. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT | | Categories | Data & Retrieval, Inference & Serving | Data & Retrieval, Evaluation & Observability, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [MiniSearch](/tools/felladrin-minisearch.md) | [cherche](/tools/raphaelsty-cherche.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Dormant (18%) | | Days since push | 0d | 812d | | Open issues (now) | 0 | 4 | | Stars delta | +3 (30d) | 0 (30d) | | Open issues delta | -31 (30d) | 0 (30d) | | Full report | [trust report](/tools/felladrin-minisearch/trust.md) | [trust report](/tools/raphaelsty-cherche/trust.md) | ## Decision facts: MiniSearch - **Hosting:** unknown - The tool operates directly from the browser, suggesting it runs client-side; however, specifics on its model hosting are not provided in the repository. - **Requirements:** Dependencies on web browsers that support TypeScript and modern JavaScript features.; Access to online resources as the platform appears to rely on Internet connectivity for operation. - **Adopt for:** MiniSearch is a minimalist web-search platform that integrates AI capabilities such as question answering and retrieval-augmented generation directly into browsers. - **License detail:** Apache-2.0 ## Decision facts: cherche - **Adopt for:** Cherche is a Python library for implementing neural search capabilities. ## Choose when ### Choose MiniSearch if… - MiniSearch is primarily TypeScript; cherche is Python. - License: MiniSearch is Apache-2.0, cherche is MIT. - The tool operates directly from the browser, suggesting it runs client-side; however, specifics on its model hosting are not provided in the repository. - Requirements: Dependencies on web browsers that support TypeScript and modern JavaScript features.; Access to online resources as the platform appears to rely on Internet connectivity for operation.. - Tags unique to MiniSearch: ai, ai-search-engine, artificial-intelligence, generative-ai. - Also covers Inference & Serving. - MiniSearch ships Docker support for self-hosted deployment. - When you require an efficient browser-based solution for web searches with built-in AI assistance, specifically designed to operate without relying on heavy server dependencies. ### Choose cherche if… - cherche is primarily Python; MiniSearch is TypeScript. - License: cherche is MIT, MiniSearch is Apache-2.0. - Tags unique to cherche: bm25, flashtext, machine-learning, natural-language-processing. - Also covers Evaluation & Observability, Vector Databases. - Cherche is a Python library for implementing neural search capabilities. ## When NOT to use MiniSearch - In scenarios where extensive offline functionalities are required because MiniSearch operates directly from the browser and may not be viable for operations without internet connectivity. - If you need heavy customization of the AI-assisted features beyond what is provided, as MiniSearch offers a compact setup which might limit deep feature personalization. ## When NOT to use cherche - Last GitHub push was 815 days ago (dormant maintenance, Jun 1, 2024). Validate activity before betting a new project on cherche. - Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough. - Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. - Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ## Common questions ### What is the difference between MiniSearch and cherche? MiniSearch: Minimalist web-searching platform featuring an AI assistant for browser-based queries.. cherche: Neural Search. See the comparison table for live GitHub stats and shared categories. ### When should I choose MiniSearch over cherche? Choose MiniSearch over cherche when MiniSearch is primarily TypeScript; cherche is Python; License: MiniSearch is Apache-2.0, cherche is MIT; The tool operates directly from the browser, suggesting it runs client-side; however, specifics on its model hosting are not provided in the repository; Requirements: Dependencies on web browsers that support TypeScript and modern JavaScript features.; Access to online resources as the platform appears to rely on Internet connectivity for operation.; Tags unique to MiniSearch: ai, ai-search-engine, artificial-intelligence, generative-ai; Also covers Inference & Serving; MiniSearch ships Docker support for self-hosted deployment; When you require an efficient browser-based solution for web searches with built-in AI assistance, specifically designed to operate without relying on heavy server dependencies. ### When should I choose cherche over MiniSearch? Choose cherche over MiniSearch when cherche is primarily Python; MiniSearch is TypeScript; License: cherche is MIT, MiniSearch is Apache-2.0; Tags unique to cherche: bm25, flashtext, machine-learning, natural-language-processing; Also covers Evaluation & Observability, Vector Databases; Cherche is a Python library for implementing neural search capabilities. ### When should I avoid MiniSearch? In scenarios where extensive offline functionalities are required because MiniSearch operates directly from the browser and may not be viable for operations without internet connectivity. If you need heavy customization of the AI-assisted features beyond what is provided, as MiniSearch offers a compact setup which might limit deep feature personalization. ### When should I avoid cherche? Last GitHub push was 815 days ago (dormant maintenance, Jun 1, 2024). Validate activity before betting a new project on cherche. Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ### Is MiniSearch or cherche more popular on GitHub? MiniSearch has more GitHub stars (581 vs 332). Stars measure visibility, not whether either tool fits your constraints. ### Are MiniSearch and cherche open source? Yes - both are open-source projects on GitHub (MiniSearch: Apache-2.0, cherche: MIT). ### Where can I find alternatives to MiniSearch or cherche? GraphCanon lists graph-backed alternatives at [MiniSearch alternatives](/tools/felladrin-minisearch/alternatives) and [cherche alternatives](/tools/raphaelsty-cherche/alternatives) ([MiniSearch markdown twin](/tools/felladrin-minisearch/alternatives.md), [cherche markdown twin](/tools/raphaelsty-cherche/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/felladrin-minisearch-vs-raphaelsty-cherche.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, MiniSearch or cherche? MiniSearch: Very active. cherche: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for MiniSearch and cherche? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [MiniSearch trust report](/tools/felladrin-minisearch/trust); [cherche trust report](/tools/raphaelsty-cherche/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=felladrin-minisearch`](/api/graphcanon/graph?tool=felladrin-minisearch) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_