LEANN Roadmap - 2026 Q1
Author: yichuan-wCreated Feb 7, 2026Updated Mar 7, 2026
LEANN aims to be a personal knowledge layer - not just a storage-efficient vector database, but a unified, always-up-to-date knowledge base that runs entirely on your own machine. It connects your code, images, and your personal data (documents, emails, browser history, chats) into a single multimodal search interface.
Contributions and feedback are welcome. Join Slack at https://join.slack.com/t/leann-e2u9779/shared_invite/zt-3ol2ww9ic-Eg_kB8omwe6xmYVd0epr4Q.
P0 — Core
LEANN MCP
- IVF backend (#231, #89, #141) @ASuresh0524
- Merkle tree (
leann watch) (#41) @yichuan-w - Cold start optimization (#166, #177) @andylizf
Search Quality
- Hybrid search (#233, #90)
Documentation
- ReadTheDocs (#234) @ASuresh0524
- Benchmarks @jane-jhu
P1
Multimodal
- Video retrieval (#160) @yichuan-w
- CLIP support (#94)
- OCR (#158)
Platform & Distribution
- Windows support (#14) @andylizf
- UI (#229) @ASuresh0524
Applications & Integrations
- Agent + Deep research (#104) @ASuresh0524
- Local Cursor — local model + local retrieval (#47)
- LlamaIndex integration (#217)
- Obsidian support (#96)
Timeline
| Target | |
|---|---|
| P0 — Core | Q1 2026 (Jan–Mar) |
| P1 | Q2 2026 (Apr–Jun) |
Contributing
Contributions are welcome! If you're interested in working on any of the items above, please reach out to @yichuan-w or @andylizf. Join our Slack to discuss.
Source: StarTrail-org/LEANN