GraphCanon updated Aug 14, 2026 · GitHub synced Aug 14, 2026
29views this month
Decision brief
Farfalle is an AI search engine that supports both local and cloud-integrated LLMs, built in TypeScript with support for multiple frontend frameworks including Next.js and React under the Shadcn UI.
Good fit when
- When you require self-hosting capabilities to maintain data privacy and security while utilizing an AI-powered search engine.
- For deployment scenarios where integration with both local LLMs and cloud services is needed, offering flexibility in infrastructure choices.
Avoid when
- If your project strictly requires low-code or no-code solutions, as Farfalle demands a more technical setup including modifying environment files and API configurations.
- In environments where a search engine needs to be up and running with minimal configuration time, since setting up Farfalle involves custom setup steps documented in separate instructions.
- Requirements:
- Setting up requires Docker for development purposes.; API keys may be required depending on the LLM chosen for integration.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (685d since push)
- As of Aug 14, 2026
- Provenance
- Not a fork · Personal account
- As of Aug 14, 2026
- Security (OSV)
- No lockfile
- As of Jul 15, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
npm install farfalleSimilar 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
An AI-powered search engine built with TypeScript that allows users to self-host and integrate it with local or cloud LLMs.
Capability facts
- Languages
- typescript, python
Source: github.language+pyproject.toml · Aug 14, 2026
Categories
Tags
README
Quick Start: Modify .env with your API keys (Optional, not required if using Ollama) Start the app: Wait for the app to start then visit http://localhost:3000. For custom setup instructions, see custom setup instructions.md
For agents
This page has a .md twin and JSON over the API.