What it does
Manifest is an LLM gateway: a middle layer between your apps and AI models. You connect your API keys, subscriptions and local models, and apps talk to one OpenAI-style address.
It can choose a model for each request, switch to another model if one fails, and log every request. It tracks spending and can send alerts and set limits.
You can use the makers' cloud version or run it yourself with Docker.
Who it's for
Developers and teams running AI agents or apps across several AI providers.
Can I use it without coding?
With some setup. There is a hosted version, or a Docker image and deployment guides for self-hosting. New to this? Start here.
Can I run it?
- Cost
- Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
- Runs on
- Server, Cloud
- Computer
- Made for servers or data centres
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Needed. An API key is a password-like code from an online AI service. What's that?
Try it
- Choose the hosted version, or deploy the Docker image on your own server.
- Connect your AI provider keys, subscriptions or local models.
- Point your apps at the gateway's address.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- Keep your API key private. Never paste it into websites or share it, and set a spending limit with the AI service.
- More on staying safe
Where people are talking about it
- Everyone is building LLM routers, we deprecated oursHacker News · Jul 2026
- Show HN: I built a backend so simple that it fits in a YAML fileHacker News · Jun 2024