--- title: "hora vs search" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/hora-search-hora-vs-kelindar-search" tools: ["hora-search-hora", "kelindar-search"] --- # hora vs search *GraphCanon updated Sep 20, 2026* ## Verdict Pick hora if hora is a Rust-based library for high-performance approximate nearest neighbor search algorithms critical in applications such as image and recommender systems where speed and efficiency are paramount; pick search if search is a Go library enabling embedded vector search and semantic embeddings via the llama.cpp framework. [hora](http://horasearch.com/) reports 2.7k GitHub stars, 77 forks, and 26 open issues, last pushed Feb 17, 2026. [search](https://github.com/kelindar/search) has 559 stars, 24 forks, and 5 open issues, last pushed Sep 19, 2026. Figures are from public GitHub metadata via [hora's repository](https://github.com/hora-search/hora) and [search's repository](https://github.com/kelindar/search). | | [hora](/tools/hora-search-hora.md) | [search](/tools/kelindar-search.md) | | --- | --- | --- | | Tagline | efficient approximate nearest neighbor search algorithm collections library written in Rust | Go library for embedded vector search and semantic embeddings with llamacpp | | Stars | 2,655 | 559 | | Forks | 77 | 24 | | Open issues | 26 | 5 | | Language | Rust | Go | | Adopt for | Hora is a Rust-based library for high-performance approximate nearest neighbor search algorithms critical in applications such as image and recommender systems where speed and efficiency are paramount. | search is a Go library enabling embedded vector search and semantic embeddings via the llama.cpp framework. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT | | Categories | Data & Retrieval, Vector Databases | Data & Retrieval, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [hora](/tools/hora-search-hora.md) | [search](/tools/kelindar-search.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Very active (96%) | | Days since push | 214d | 0d | | Open issues (now) | 26 | 5 | | Stars delta | -8 (30d) | +4 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/hora-search-hora/trust.md) | [trust report](/tools/kelindar-search/trust.md) | ## Decision facts: hora - **Adopt for:** Hora is a Rust-based library for high-performance approximate nearest neighbor search algorithms critical in applications such as image and recommender systems where speed and efficiency are paramount. ## Decision facts: search - **Adopt for:** search is a Go library enabling embedded vector search and semantic embeddings via the llama.cpp framework. ## Choose when ### Choose hora if… - hora is primarily Rust; search is Go. - License: hora is Apache-2.0, search is MIT. - Tags unique to hora: algorithm, approximate-nearest-neighbor-search, artificial-intelligence, data-structures. - When you require a high-speed library written in Rust to implement an efficient similarity-search solution ### Choose search if… - search is primarily Go; hora is Rust. - License: search is MIT, hora is Apache-2.0. - Tags unique to search: ai, bert, embeddings, gguf. - Use for projects needing a lightweight, fast integration of semantic search capabilities within applications written in Go ## When NOT to use hora - If your project is restricted to languages other than Rust and you cannot work with Rust bindings or require a more general-purpose vector database library - When exact nearest neighbor search accuracy is preferred over the speed provided by approximate algorithms, as Hora specializes in sacrificing minimal precision for significant performance gains ## When NOT to use search - Avoid if relying on out-of-the-box support beyond Go or requiring heavy customization that is not supported directly by llama.cpp's capabilities - Not suitable when a more comprehensive database service with extensive querying and integration features is desired over an embedded solution ## Common questions ### What is the difference between hora and search? hora: efficient approximate nearest neighbor search algorithm collections library written in Rust. search: Go library for embedded vector search and semantic embeddings with llamacpp. See the comparison table for live GitHub stats and shared categories. ### When should I choose hora over search? Choose hora over search when hora is primarily Rust; search is Go; License: hora is Apache-2.0, search is MIT; Tags unique to hora: algorithm, approximate-nearest-neighbor-search, artificial-intelligence, data-structures; When you require a high-speed library written in Rust to implement an efficient similarity-search solution. ### When should I choose search over hora? Choose search over hora when search is primarily Go; hora is Rust; License: search is MIT, hora is Apache-2.0; Tags unique to search: ai, bert, embeddings, gguf; Use for projects needing a lightweight, fast integration of semantic search capabilities within applications written in Go. ### When should I avoid hora? If your project is restricted to languages other than Rust and you cannot work with Rust bindings or require a more general-purpose vector database library When exact nearest neighbor search accuracy is preferred over the speed provided by approximate algorithms, as Hora specializes in sacrificing minimal precision for significant performance gains ### When should I avoid search? Avoid if relying on out-of-the-box support beyond Go or requiring heavy customization that is not supported directly by llama.cpp's capabilities Not suitable when a more comprehensive database service with extensive querying and integration features is desired over an embedded solution ### Is hora or search more popular on GitHub? hora has more GitHub stars (2,655 vs 559). Stars measure visibility, not whether either tool fits your constraints. ### Are hora and search open source? Yes - both are open-source projects on GitHub (hora: Apache-2.0, search: MIT). ### Where can I find alternatives to hora or search? GraphCanon lists graph-backed alternatives at [hora alternatives](/tools/hora-search-hora/alternatives) and [search alternatives](/tools/kelindar-search/alternatives) ([hora markdown twin](/tools/hora-search-hora/alternatives.md), [search markdown twin](/tools/kelindar-search/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/hora-search-hora-vs-kelindar-search.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, hora or search? hora: Slowing. search: Very active. 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 hora and search? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [hora trust report](/tools/hora-search-hora/trust); [search trust report](/tools/kelindar-search/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=hora-search-hora`](/api/graphcanon/graph?tool=hora-search-hora) - 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/_