baize

Lightweight AI Agent Framework

2 followers

Lightweight AI Agent Framework

2 followers

Visit website

Auditable Agent runtime for your existing systems

Free

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team / Built With

Render Sandboxes: a computer for every agentGive every agent its own machine. Starts in under a second

Promoted

Maker

📌

Hey Product Hunt! 👋 I'm RA, maker of Baize. Baize is an open-source AI agent designed to add AI capabilities to existing services without rewriting them. It runs as a standalone binary alongside your service and communicates via plain HTTP callbacks. No SDK, no code changes. When you're done, delete the binary — zero trace. Why Go? Because deployment shouldn't require a DevOps team. A single static binary with no runtime dependencies runs anywhere — old Windows servers, minimal Linux containers, even AIX. Baize is MIT-licensed and supports standard protocols like MCP, so it can also be called by other agents. If Baize sounds useful, a star on GitHub helps more people discover it. Found a bug or have an idea? Open an issue — I read every one. 👉 GitHub: https://github.com/rebornace/baize What existing service would you want to add AI to first? Thanks for checking out Baize!

Report

2mo ago

Forum Threads

p/baize

•

16d ago

Approval gates for every write, OpenAPI connectors, and bidirectional MCP — what's new in Baize

Baize is a self-hosted sidecar that puts your existing internal APIs and tools behind an LLM agent, with a human checkpoint before anything that changes state. Here's what's new.

1. Human approval before every write

The agent can read freely, but any tool that changes state closing an order, deleting a record, shipping a shipment pauses and asks a person first. The approval card shows the evidence it gathered, the exact tool (with content hash and revision), and the arguments it's about to run. You approve or reject; nothing happens by surprise.

p/baize

•

2mo ago

How do you add AI to a system you can't rewrite?

Hey everyone,

I just launched Baize, an open-source AI agent that helps add AI capabilities to existing services without rewriting them.

But I'm more curious about your experience: What's the biggest blocker when you try to bring AI into an existing product or system? Is it data access, deployment, security, or something else?

I'd love to hear what you've run into and what you wish existed to make it easier.

View all