Context Lens

io.github.cornelcroiPublished by GitHub account cornelcroiv0.1.8Updated Oct 24, 2026

Semantic search knowledge base with serverless LanceDB. Zero setup, 100% local, 25+ file types

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & Memory

Overview

AI-generated overview

A local, zero-setup semantic search knowledge base backed by serverless LanceDB, letting an assistant search your own files across 25+ file types.

What you can do
Search a local knowledge base semantically, using LanceDB as the serverless vector store behind it. Index and query content from more than 25 file types. Keep everything on the user's machine, with no setup or external service required.
When to use it
Useful when you want an assistant to find information across a personal or project collection of mixed-format files by meaning rather than exact keywords, and you prefer to keep the data local.
Requirements
Runs as a local process over stdio, installed from the PyPI package context-lens, so a Python environment is needed. No authentication, environment variables or headers are declared. Desktop only; not available as a web executable.
Before you install
The manifest lists no tools, so the exact operations and whether it writes or indexes data cannot be confirmed from the input. It reads local files, so point it only at directories you are comfortable exposing to the assistant.

Installation

In SourceWeft

  1. Open Context Lens in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.8LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.