--- title: "search vs cherche" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/kelindar-search-vs-raphaelsty-cherche" tools: ["kelindar-search", "raphaelsty-cherche"] --- # search vs cherche *GraphCanon updated Aug 23, 2026* ## Verdict Pick search if search is a Go library enabling embedded vector search and semantic embeddings via the llama.cpp framework; pick cherche if cherche is a Python library for implementing neural search capabilities. [search](https://github.com/kelindar/search) reports 558 GitHub stars, 24 forks, and 5 open issues, last pushed Mar 6, 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 [search's repository](https://github.com/kelindar/search) and [cherche's repository](https://github.com/raphaelsty/cherche). | | [search](/tools/kelindar-search.md) | [cherche](/tools/raphaelsty-cherche.md) | | --- | --- | --- | | Tagline | Go library for embedded vector search and semantic embeddings with llamacpp | Neural Search | | Stars | 558 | 332 | | Forks | 24 | 14 | | Open issues | 5 | 4 | | Language | Go | Python | | Adopt for | search is a Go library enabling embedded vector search and semantic embeddings via the llama.cpp framework. | Cherche is a Python library for implementing neural search capabilities. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | Data & Retrieval, Vector Databases | Data & Retrieval, Evaluation & Observability, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [search](/tools/kelindar-search.md) | [cherche](/tools/raphaelsty-cherche.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Dormant (18%) | | Days since push | 169d | 812d | | Open issues (now) | 5 | 4 | | Stars delta | +3 (30d) | 0 (30d) | | Full report | [trust report](/tools/kelindar-search/trust.md) | [trust report](/tools/raphaelsty-cherche/trust.md) | ## Decision facts: search - **Adopt for:** search is a Go library enabling embedded vector search and semantic embeddings via the llama.cpp framework. ## Decision facts: cherche - **Adopt for:** Cherche is a Python library for implementing neural search capabilities. ## Choose when ### Choose search if… - search is primarily Go; cherche is Python. - 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 ### Choose cherche if… - cherche is primarily Python; search is Go. - Tags unique to cherche: bm25, flashtext, information-retrieval, machine-learning. - Also covers Evaluation & Observability. - Cherche is a Python library for implementing neural search capabilities. ## 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 ## 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 search and cherche? search: Go library for embedded vector search and semantic embeddings with llamacpp. cherche: Neural Search. See the comparison table for live GitHub stats and shared categories. ### When should I choose search over cherche? Choose search over cherche when search is primarily Go; cherche is Python; 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 choose cherche over search? Choose cherche over search when cherche is primarily Python; search is Go; Tags unique to cherche: bm25, flashtext, information-retrieval, machine-learning; Also covers Evaluation & Observability; Cherche is a Python library for implementing neural search capabilities. ### 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 ### 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 search or cherche more popular on GitHub? search has more GitHub stars (558 vs 332). Stars measure visibility, not whether either tool fits your constraints. ### Are search and cherche open source? Yes - both are open-source projects on GitHub (search: MIT, cherche: MIT). ### Where can I find alternatives to search or cherche? GraphCanon lists graph-backed alternatives at [search alternatives](/tools/kelindar-search/alternatives) and [cherche alternatives](/tools/raphaelsty-cherche/alternatives) ([search markdown twin](/tools/kelindar-search/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/kelindar-search-vs-raphaelsty-cherche.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, search or cherche? search: Slowing. 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 search and cherche? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [search trust report](/tools/kelindar-search/trust); [cherche trust report](/tools/raphaelsty-cherche/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=kelindar-search`](/api/graphcanon/graph?tool=kelindar-search) - 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/_