Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
Meilisearch
Meilisearch is a developer-first search engine written in Rust, delivering sub-50ms full-text search responses with typo-tolerance, faceting, filtering, and geosearch out of the box. Its Community Edition is fully open source under MIT. It also supports hybrid (keyword + vector) search, making it a natural fit for RAG and semantic retrieval pipelines.
Key Features
- Instant search — returns results in under 50ms on datasets with millions of documents
- Typo tolerance — handles misspellings, partial matches, and word-order variations natively
- Hybrid search — combine BM25 keyword and vector similarity scores in a single query
- Faceted filtering — structured filters on any attribute with zero extra configuration
- Multi-tenant — built-in API key scoping and index-level access control
- Simple REST API — index documents, run searches, and manage synonyms via a clean HTTP API
- AI embeddings — built-in support for OpenAI, HuggingFace, Ollama, and REST embedder endpoints
Quick Start
curl -L https://install.meilisearch.com | sh
./meilisearch --master-key="masterKey"
from meilisearch import Client
client = Client('http://localhost:7700', 'masterKey')
index = client.index('movies')
index.add_documents([{"id": 1, "title": "2001: A Space Odyssey"}])
results = index.search('spac odyssy') # typo-tolerant
print(results['hits'])
Install via ai-supply
npx ai-supply add meilisearch-ai-search-engine
Curated mirror of the open-source Meilisearch (MIT). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/meilisearch-ai-search-engine/check). Click a policy:
Consume Meilisearch programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/meilisearch-ai-search-engine
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/meilisearch-ai-search-engine/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add meilisearch-ai-search-engine
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/meilisearch-ai-search-engine/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "meilisearch-ai-search-engine" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.