--- title: "cherche vs voy" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/raphaelsty-cherche-vs-tantaraio-voy" tools: ["raphaelsty-cherche", "tantaraio-voy"] --- # cherche vs voy *GraphCanon updated Aug 23, 2026* ## Verdict Pick cherche if cherche is a Python library for implementing neural search capabilities; pick voy if voy specializes in Webassembly-based vector similarity searches, coded in Rust, with support for k-d-trees and nearest-neighbor searching. [cherche](https://github.com/raphaelsty/cherche) reports 332 GitHub stars, 14 forks, and 4 open issues, last pushed Jun 1, 2024. [voy](https://www.npmjs.com/package/voy-search) has 1.1k stars, 41 forks, and 22 open issues, last pushed Sep 20, 2023. Figures are from public GitHub metadata via [cherche's repository](https://github.com/raphaelsty/cherche) and [voy's repository](https://github.com/tantaraio/voy). | | [cherche](/tools/raphaelsty-cherche.md) | [voy](/tools/tantaraio-voy.md) | | --- | --- | --- | | Tagline | Neural Search | A WASM vector similarity search written in Rust | | Stars | 332 | 1,069 | | Forks | 14 | 41 | | Open issues | 4 | 22 | | Language | Python | Rust | | Adopt for | Cherche is a Python library for implementing neural search capabilities. | Voy specializes in Webassembly-based vector similarity searches, coded in Rust, with support for k-d-trees and nearest-neighbor searching. | | Persona | - | - | | Runtime | - | - | | License | MIT | Apache-2.0 | | Categories | Data & Retrieval, Evaluation & Observability, Vector Databases | Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [cherche](/tools/raphaelsty-cherche.md) | [voy](/tools/tantaraio-voy.md) | | --- | --- | --- | | Days since push | 812d | 1067d | | Open issues (now) | 4 | 22 | | Stars delta | 0 (30d) | +4 (30d) | | Owner type | User | Organization | | Full report | [trust report](/tools/raphaelsty-cherche/trust.md) | [trust report](/tools/tantaraio-voy/trust.md) | ## Decision facts: cherche - **Adopt for:** Cherche is a Python library for implementing neural search capabilities. ## Decision facts: voy - **Adopt for:** Voy specializes in Webassembly-based vector similarity searches, coded in Rust, with support for k-d-trees and nearest-neighbor searching. ## Choose when ### Choose cherche if… - cherche is primarily Python; voy is Rust. - License: cherche is MIT, voy is Apache-2.0. - Tags unique to cherche: bm25, flashtext, information-retrieval, machine-learning. - Also covers Data & Retrieval, Evaluation & Observability. - Cherche is a Python library for implementing neural search capabilities. ### Choose voy if… - voy is primarily Rust; cherche is Python. - License: voy is Apache-2.0, cherche is MIT. - Tags unique to voy: k-d-tree, nearest-neighbor-search, rust, similarity-search. - When you require a Rust implementation of WebAssembly for embedding in web applications or for secure sandboxed execution on the server-side. ## 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. ## When NOT to use voy - If high availability and extensive fault tolerance features are required, as Voy focuses primarily on vector similarity searches rather than system-wide reliability enhancements. - When your project demands integration with existing large-scale SQL database systems, since Voy is specialized for a specific type of search operation. ## Common questions ### What is the difference between cherche and voy? cherche: Neural Search. voy: A WASM vector similarity search written in Rust. See the comparison table for live GitHub stats and shared categories. ### When should I choose cherche over voy? Choose cherche over voy when cherche is primarily Python; voy is Rust; License: cherche is MIT, voy is Apache-2.0; Tags unique to cherche: bm25, flashtext, information-retrieval, machine-learning; Also covers Data & Retrieval, Evaluation & Observability; Cherche is a Python library for implementing neural search capabilities. ### When should I choose voy over cherche? Choose voy over cherche when voy is primarily Rust; cherche is Python; License: voy is Apache-2.0, cherche is MIT; Tags unique to voy: k-d-tree, nearest-neighbor-search, rust, similarity-search; When you require a Rust implementation of WebAssembly for embedding in web applications or for secure sandboxed execution on the server-side. ### 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. ### When should I avoid voy? If high availability and extensive fault tolerance features are required, as Voy focuses primarily on vector similarity searches rather than system-wide reliability enhancements. When your project demands integration with existing large-scale SQL database systems, since Voy is specialized for a specific type of search operation. ### Is cherche or voy more popular on GitHub? voy has more GitHub stars (1,069 vs 332). Stars measure visibility, not whether either tool fits your constraints. ### Are cherche and voy open source? Yes - both are open-source projects on GitHub (cherche: MIT, voy: Apache-2.0). ### Where can I find alternatives to cherche or voy? GraphCanon lists graph-backed alternatives at [cherche alternatives](/tools/raphaelsty-cherche/alternatives) and [voy alternatives](/tools/tantaraio-voy/alternatives) ([cherche markdown twin](/tools/raphaelsty-cherche/alternatives.md), [voy markdown twin](/tools/tantaraio-voy/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/raphaelsty-cherche-vs-tantaraio-voy.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, cherche or voy? cherche: Dormant. voy: 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 cherche and voy? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [cherche trust report](/tools/raphaelsty-cherche/trust); [voy trust report](/tools/tantaraio-voy/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=raphaelsty-cherche`](/api/graphcanon/graph?tool=raphaelsty-cherche) - 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/_