MiniSearch
Minimalist web-searching platform featuring an AI assistant for browser-based queries.
GraphCanon updated 1d · GitHub synced 1d
Decision brief
MiniSearch is a minimalist web-search platform that integrates AI capabilities such as question answering and retrieval-augmented generation directly into browsers.
Good fit when
- When you require an efficient browser-based solution for web searches with built-in AI assistance, specifically designed to operate without relying on heavy server dependencies.
- If your use case involves lightweight operations within the browser environment, leveraging TypeScript, and requiring a robust yet compact search functionality.
Avoid when
- In scenarios where extensive offline functionalities are required because MiniSearch operates directly from the browser and may not be viable for operations without internet connectivity.
- If you need heavy customization of the AI-assisted features beyond what is provided, as MiniSearch offers a compact setup which might limit deep feature personalization.
- Hosting:
- unknown - The tool operates directly from the browser, suggesting it runs client-side; however, specifics on its model hosting are not provided in the repository.
- Requirements:
- Dependencies on web browsers that support TypeScript and modern JavaScript features.; Access to online resources as the platform appears to rely on Internet connectivity for operation.
Observed Jul 15, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of 1d
- Provenance
- Not a fork · Personal account
- As of 1d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
npm install MiniSearchSimilar 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
A minimalist yet powerful web-search engine with integrated AI capabilities designed to run directly within user browsers, offering services such as question answering and retrieval-augmented generation.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Aug 25, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Aug 25, 2026
- CLI
- CLI entrypoint
Source: package.json:bin|scripts · Aug 25, 2026
- MCP server
- No MCP server detected
Source: repo_scan · Aug 25, 2026
- Languages
- typescript, javascript
Source: github.language+package.json · Aug 25, 2026
Categories
Tags
README
Quick start
Run the published image:
docker run -p 7860:7860 ghcr.io/felladrin/minisearch
Then open http://localhost:7860 and start searching.
Pin to a specific build
latest moves on every release, so it changes under you. To stay on a known-good build, pin the digest, which always identifies the same image:
docker inspect --format '{{index .RepoDigests 0}}' ghcr.io/felladrin/minisearch:latest
docker run -p 7860:7860 ghcr.io/felladrin/minisearch@sha256:1a2b3c...
The version the running instance reports (in the menu, and under build on /status) tells you which commit it was built from.
Images carry provenance and SBOM attestations, which you can inspect with:
docker buildx imagetools inspect ghcr.io/felladrin/minisearch:latest
Use Docker Compose
Add the service to your docker-compose.yml:
services:
minisearch:
image: ghcr.io/felladrin/minisearch:latest
ports:
- "7860:7860"
Build from source
git clone https://github.com/felladrin/MiniSearch.git
cd MiniSearch
docker compose -f docker-compose.production.yml up --build
Host it on Hugging Face
Duplicate the Space to get your own hosted instance, no server required. Environment variables can be set in the Space settings.
License
Apache License 2.0
For agents
This page has a .md twin and JSON over the API.