GraphCanon updated today · GitHub synced today
Decision brief
Lightweight Rust-based embedding storage for efficiency.
Good fit when
- When developing applications requiring efficient similarity searches over embeddings that are written in Rust or integrate well with Rust systems.
Avoid when
- For heavy-scale distributed vector operations as tinyvector is designed to be lightweight and might not scale as expected compared to larger solutions like Faiss or PQ.
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (969d since push)
- As of today
- Provenance
- Not a fork · Personal account
- As of today
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
cargo add tinyvector crates.ioSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
tinyvector is a lightweight and efficient vector database implemented in the Rust programming language. It focuses on embedding storage and similarity search operations critical for machine learning applications.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Aug 23, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Aug 23, 2026
- Languages
- rust
Source: github.language · Aug 23, 2026
Categories
Tags
README
🐳 Docker
We provide a lightweight Docker container that you can run anywhere. It only takes one command to get up and running with the latest changes:
docker run \
-p 8000:8000 \
ghcr.io/m1guelpf/tinyvector:edge
Note When running via Docker Compose or Kubernetes, make sure to bind a volume to
/tinyvector/storagefor persistence. This is handled automatically in the command above.
📄 License
This project is open-sourced under the MIT license. See the License file for more information.
For agents
This page has a .md twin and JSON over the API.