Clai is an open-source command-line AI harness for terminal power users, run as a standalone CLI or embedded as a Go package for agent workflows.
Yes, Clai is open source under the MIT license.
Clai is free to use.
Yes, Clai can be self-hosted (the source is available under the MIT license).
Clai is an open-source command-line AI harness for terminal power users: context-engineering and agent workflows you drive from the shell, as a standalone CLI or embedded as a Go package. Open source: yes (MIT); self-hostable; free OSS. It has ~145 stars and is established and actively maintained, with ~925 commits since 2024.
Clai lives in the terminal. Rather than a chat window, it gives command-line users a way to run AI with deliberate context engineering: assembling the right context and driving agent workflows from the shell, where a developer already works. Its second shape is as a Go package, so the same harness can be embedded inside your own tools rather than only invoked as a CLI. It is MIT-licensed and self-hostable in the sense that you run it yourself and point it at your own model access. Open source: yes (MIT); free OSS. This is a general-purpose developer tool, so what it does for a GTM stack depends on what you build with it.
Most GTM automation gets built by someone comfortable in a terminal, and a harness that lives there — with context engineering as a first-class idea and a Go package you can embed — is a practical building block for that person. Clai is not a GTM product; it is plumbing a builder can wire into prospecting, enrichment, or reporting scripts and then reuse inside a larger tool. For a technical RevOps or growth engineer who prefers the command line to a dashboard, it is worth a look. The honest read: reach is modest (~145 stars), and because it is general-purpose, the GTM value is entirely in what you assemble on top of it. If you want a turnkey workflow rather than a harness, this is not it.