#77th of 21 in RAG and search
manticoresearch
C++ search database with full-text, vector and hybrid search over SQL and HTTP
- Stars
- 12.1k
- License
- GPL-3.0
- Last commit
- Nov 2026
- Last release
- Sep 2026
- Language
- C++
11,671 on 25 Apr 202612,092 on 14 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Manticore Search is a C++ search database with SQL (MySQL protocol) and HTTP JSON interfaces, positioned as an Elasticsearch alternative. It combines full-text search, KNN vector search, hybrid queries and auto-embeddings with chunking, and adds conversational search through SQL CALL CHAT. Storage is row-wise or columnar, with real-time inserts, sharded tables and Galera-based multi-master replication.
Who it is for: Engineers replacing Elasticsearch or adding hybrid search to self-hosted apps
Strengths
- Hybrid full-text and KNN retrieval in one query, with auto-embeddings and chunking
- Speaks MySQL protocol and HTTP JSON; official clients for nine languages
- Columnar storage for datasets larger than RAM; about 40MB RSS when empty
- Replication, sharded tables, built-in auth, backup to S3-compatible storage
Weaknesses
- GPL-3.0 licence may constrain embedding in proprietary products
- Not fully ACID; only isolated transactions and binary logging
- Elasticsearch compatibility covers writes only, not the full query API
- Benchmark claims come from the project's own suite and are workload-specific
What it needs
- C++, auto-embeddings, LLM-backed CALL CHAT
- Needs Manticore Columnar Library (columnar storage), LLM provider (conversational search)
What changed
“⚠️ v29.0.0 Issue #4739 Added streamed heartbeat replies for long-running shard writes and replication SST, changing the SHARDWRITE API and the cluster protocol. This matters only when upgrading or do…”
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Head to head
Also in RAG and search
See all 21| Rank | Project | Score |
|---|---|---|
| 1 | xerjElasticsearch-compatible search server that auto-indexes folders for coding agents | 87 out of 100 |
| 2 | sonicLightweight schema-less search index that returns object IDs, written in Rust | 82 out of 100 |
| 3 | xbergRust document extraction engine with OCR, tables and 15 language bindings | 80 out of 100 |
| #4 | qmdLocal hybrid search over markdown notes and docs, with CLI and MCP server | 78 out of 100 |
| #5 | llm-appYAML-configured RAG server that keeps a vector database synced with a document folder | 77 out of 100 |