supermemory launches CLI with npx install, scoped agent access, and audit logs

• supermemory launched a CLI that makes agents “first class users,” with the company saying everything available on the platform can now be driven from the command line via the launch thread.
• The initial flow is lightweight: supermemory’s launch post shows an npx supermemory entry point rather than a longer local install path.
• Alongside the CLI, supermemory added an Agents page and deeper API scoping so agents can be granted tag-specific read/write access instead of broad account access, according to the scoping update.
• supermemory’s agent workflow post positions the CLI as part of a closed test loop, with agents able to set up memory, then use supermemory add and supermemory search as part of their runtime flow.

The core launch is a command-line interface aimed at agent use, not just human operators. In the main announcement, supermemory argues “CLIs can be more powerful” than MCP for some workflows and says “every single thing” on the platform can be done by agents through the CLI. The demo post also highlights the npx supermemory entry point and includes a short product walkthrough CLI demo.

That matters because the product framing is narrower than a generic developer CLI. In the workflow thread, supermemory says an agent can “fully set up supermemory” and then call supermemory add and supermemory search directly, positioning the tool as a memory layer inside agent loops rather than a separate admin surface.

The more consequential implementation detail is the new agent-specific permission model. According to the scoping update, the release adds an “Agents” page plus “deeper scoping” for the API, letting developers give agents scoped access to a supermemory account with permissions limited to certain tags and to read/write operations.

supermemory also says those agent actions are fully audit-logged in the same update, which gives teams a way to let agents write memory without handing over unrestricted account access. The supporting UI screenshot in the agents screenshot shows agents listed as connected account entities with an explicit “Read + Write” status, reinforcing that agents are now treated as distinct principals inside the product rather than opaque API consumers.