Practical overview
When it fits
Use it when you want to query a Readwise highlights library from a self-hosted search API or make that search available to an MCP-capable LLM client.
Who it is for
- Readwise users who want semantic search across their saved highlights.
- Developers who want to expose a Readwise library search endpoint or MCP search server to LLM clients.
- Operators who want to run and monitor a reading-search service on local or cloud infrastructure.
Documented uses
- Search highlights using a natural-language query rather than exact matching.
- Narrow vector search by source, tags or highlighted date range.
- Stream search results over HTTP SSE or provide search through an MCP server.
- Sync an initial Readwise backfill and run incremental syncs.
- Monitor the service with Prometheus metrics.
Requirements & limits
The repository is public and specifies the MIT license. The documented application is self-hosted; the README lists required service credentials and local setup prerequisites.
- The documented embedding path uses an OpenAI API key, while Readwise access requires a Readwise token.
- The local setup uses PostgreSQL with pgvector; the cloud pattern uses Supabase PostgreSQL with pgvector and can pair with Vercel.
- HTTP SSE is documented for serverless MCP use; the TCP MCP server is presented for local development and dedicated-server deployments.
- The API example supports filters for source, tags and highlight dates.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up the local API and sync Readwise highlights
Prepare the local service, run its database migrations and perform an initial Readwise library backfill.
Before you start
- Python 3.12
- Poetry 1.8 or later
- Docker and Docker Compose
- Readwise token and OpenAI API key
- A .env file with the documented credentials and local PostgreSQL DATABASE_URL
Steps
Clone the repository and install its dependencies with Poetry.
Start the PostgreSQL and pgvector database using Docker Compose, then apply the Alembic migrations.
Start the API with Uvicorn and run the CLI backfill command to sync the library.
Expected outcome
A locally hosted API backed by a database populated with the initial Readwise highlights sync.
Guide limitations
- The README gives setup and sync instructions but does not specify an automatic schedule for this local recipe.
- This is source-based guidance, not a verification that a particular environment will run successfully.
Compare options for Vector search
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Readwise Vector Db | Search highlights using a natural-language query rather than exact matching. | Self-hosted, Server | The repository is public and specifies the MIT license. The documented application is self-hosted; the README lists required service credentials and local setup prerequisites. |
| Chatbot with PDF for Semantic Search | Prepare document content as embeddings and save it to a supported vector database. | Web | The repository is identified as open source and publicly visible on GitHub. |
| AI LLM Playground | Ask questions about PDF documents through an assistant interface. | Web |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 17 October 2026
- Original website title
- leonardsellem/readwise-vector-db · Official homepage title · retained in its source language