Tag
Vector search tools
Vector database or similarity search. 16 reviewed tools: 15 free or open source, 1 paid or paid-led.
Order: free and open source first, then hosted products with a real free tier, then paid-led; catalog order inside each group, with quiet or archived repos last. Not a score, and no tool pays for its place.
16 tools
- QdrantOpen-source vector database with filtering
Free / OSS · Apache-2.0 · 35.1k GitHub stars
VerdictSelf-hostable vector search with production-grade features.
CatchOperational burden of self-hosting. Smaller ecosystem than Pinecone. Some advanced features require understanding internals.
- GraphitiApache-2.0 temporal knowledge graphs for agent memory; Zep's OSS engine
Free / OSS · Apache-2.0 · 32k GitHub stars
VerdictApache-2.0 temporal memory graphs. Free self-host; Zep Cloud is the paid path.
CatchFramework only — you run a graph DB + ops. Zep Community Edition deprecated; full Zep SaaS is separate (Free credits then Flex ~$104/mo billed annually). Not a drop-in chat history store. Schema/ops cost vs Mem0 Docker.
- ChromaApache-2.0 open-source embedding database for AI apps
Free / OSS · Apache-2.0 · 29.5k GitHub stars
VerdictApache-2.0 embedding DB. Free self-host.
CatchHosted Chroma is commercial; self-host ops still yours. Distinct from Qdrant and Pinecone.
- LanceDBApache-2.0 embedded multimodal vector store on Lance
Free / OSS · Apache-2.0 · 11.7k GitHub stars
VerdictApache-2.0 embedded vectors. Free locally.
CatchEmbedded is not zero ops forever - disk growth still matters. Distinct from Chroma collections DX and sqlite-vec.
- WeaviateBSD-3-Clause OSS vector database with hybrid search
Free / OSS · OSS/MIT · 16.9k GitHub stars
VerdictBSD OSS vector DB. Free self-host.
CatchCluster ops are real work. Cloud is paid beyond trials. Distinct from Chroma/LanceDB embedded lanes and Pinecone.
- Milvus LiteApache-2.0 lightweight Milvus for local vector search
Free / OSS · Apache-2.0 · 465 GitHub stars
VerdictApache-2.0 local Milvus. Free for prototypes.
CatchLite is not production HA. Thinner stars than core Milvus. Distinct from full Milvus and Chroma/LanceDB peers.
- sqlite-vecApache-2.0 vector search as a SQLite extension
Free / OSS · Apache-2.0 · 8.2k GitHub stars
VerdictApache-2.0 vectors-in-SQLite. Free forever.
CatchExtension load path and platform wheels need care. Distinct from Chroma/LanceDB stores and libSQL fork.
- USearchApache-2.0 fast similarity search across languages
Free / OSS · Apache-2.0 · 4.3k GitHub stars
VerdictApache-2.0 embeddable similarity search. Free forever.
CatchLibrary, not a managed vector DB. You own persistence. Distinct from Chroma/Weaviate databases and sqlite-vec.
- VectorMPL-2.0 logs/metrics/traces data plane vs OTel Collector/Alloy
Free / OSS · MPL-2.0 · 22.7k GitHub stars
VerdictMPL-2.0 obs data plane. Free to run; watch MPL + Datadog stewardship.
CatchMPL-2.0 (file-level copyleft, not MIT/Apache). Datadog-maintained after Timber acquisition - product direction follows Datadog. Distinct from OpenTelemetry Collector and Grafana Alloy.
- PageIndexMIT self-hosted vectorless tree-RAG core — local mode with your own LLM key
Free / OSS · OSS/MIT · 39.3k GitHub stars
VerdictMIT self-hosted tree-RAG core for long text-heavy PDFs with your own LLM key — not the freemium pageindex-mcp; OCR, folders, metadata, MCP, and File System are cloud.
CatchCloud: OCR and image understanding, Metadata, Folders, the MCP server, and the PageIndex File System (corpus-scale indexing) are PageIndex Cloud only — need a PageIndex API key. Local mode is text-heavy PDFs, one document tree at a time. Not a duplicate of the pageindex-mcp gem: that one is the freemium hosted MCP surface; this is the self-hosted MIT tree-RAG core you run in your own code. Your LLM key pays for every index and query — tree reasoning is token-hungry on big docs. SDK is young (0.2.x); pin it.
- EdgeQuakeApache-2.0 GraphRAG engine in Rust, runs on local models
Free / OSS · Apache-2.0 · 2.3k GitHub stars
VerdictLocal-first GraphRAG in Rust — worth a try for private documents, if you can give it a capable extraction model.
CatchPre-1.0 with a small group of contributors (about a dozen), so expect breaking changes. Graph quality depends heavily on the model you use for entity extraction — small local models produce thinner, noisier graphs, and the first local run pulls several GB of models. Vs cognee (a more established memory and knowledge-graph layer for agents): EdgeQuake is the lighter Rust option for local GraphRAG.
- pgvectorOpen-source vector similarity search inside Postgres
Free / OSS · OSS/MIT · 23.4k GitHub stars
VerdictThe default first vector store if you already run Postgres — reach for a dedicated vector database only when you outgrow it.
CatchIt is an extension, so on self-hosted Postgres you compile or package it yourself, and on managed Postgres you are limited to the version your provider ships. HNSW indexes on large tables are slow to build and need plenty of maintenance_work_mem; at hundreds of millions of vectors you will be tuning, quantizing or partitioning. Filtered queries can return fewer rows than expected with approximate indexes unless you use iterative scans (0.8+).
- DatabendApache-2.0 Rust cloud data warehouse on object storage
Free / OSS · Apache-2.0 · 9.5k GitHub stars
VerdictA Snowflake-style warehouse you can run yourself — compare with ClickHouse before choosing.
CatchThe README now positions it as an enterprise warehouse for AI agents, and the recommended start is Databend Cloud (free to start, commercial beyond that); self-hosting a cluster is more work. Smaller ecosystem than ClickHouse or DuckDB. Releases are frequent nightly-style builds, so pin versions.
- OramaApache-2.0 full-text, vector and hybrid search in JS
Free / OSS · Apache-2.0 · 10.6k GitHub stars
VerdictA great zero-server search library for docs and small catalogs.
CatchThe index lives in memory in your process, so it fits small to medium datasets, not millions of large documents. The last release was December 2025 and the last code change July 2026, so the open-source library moves slowly while the company focuses on Orama Cloud. GitHub does not detect the license; the LICENSE.md text is Apache-2.0.
- OpenLLMetryApache-2.0 OpenTelemetry instrumentation for LLM apps
Free / OSS · Apache-2.0 · 7.5k GitHub stars
VerdictThe vendor-neutral way to get LLM calls into your existing tracing.
CatchTraces can include prompts and completions, which may hold personal data, so configure content capture deliberately. The Traceloop SDK defaults point toward Traceloop's hosted platform; set your own exporter. It is instrumentation, not a UI, so you still need a backend.
- PineconeVector database for AI applications
Paid-led · Freemium
VerdictThe managed vector database for production AI.
CatchVendor lock-in for a core AI capability. Costs scale with vector count and queries. Self-hosting is not an option.
FAQ
- What is the top free pick among Vector search tools?
- Qdrant leads the Stack Gems list for Vector search tools. Verdict: Self-hostable vector search with production-grade features.
- How many Vector search tools does Stack Gems review?
- 16: 15 free or open source, 1 paid or paid-led. Each review has a verdict and an honest Catch; no tool pays for its spot.
- Which Vector search tools can I self-host for free?
- Qdrant, Graphiti, Chroma, LanceDB, Weaviate, Milvus Lite, sqlite-vec, USearch and 7 more.
- Which Vector search tools have the most GitHub stars?
- PageIndex (39.3k), Qdrant (35.1k), Graphiti (32k), per GitHub on 2026-10-19. Stars measure attention, not fit; read the Catch.
- What is the catch with Qdrant?
- Operational burden of self-hosting.