Proof System Surfaces Reviewable Memory License Get MOOTx01
New · MOOTx01 v1.0.25

Reviewable memory
for long-running agents.

Fable's return made the timing clear. Anthropic now tells teams to build memory systems, and Claude can use a simple file-shaped interface to do it: one memory tool, one /memories folder, and familiar file operations.

MOOTx01 v1.0.25 gives Claude that same interface while saving each memory as a record you can review.

The agent gets the simple memory handle. You get memory you can inspect, confirm, limit, withdraw, and carry forward.

Available today Free for individuals Same memory_20250818 interface Every memory a reviewable record
Why This Matters Now
Memory isn't new.
The timing is.

Memory has existed in AI systems for a while. People have stored summaries, embeddings, preferences, transcripts, project notes, and many other forms of scratchpad state.

The model changed the timing. Fable 5 made memory more practical. Anthropic's guidance now treats memory as part of the agent loop, and the memory_20250818 tool gives Claude a simple way to use it across conversations.

A file-shaped interface is useful because everyone can understand it. A model can use files. A developer can inspect files. A product team can explain files.

But a file only tells you what text is present. Long-running agents need more than that.

The Missing Questions

Six questions a file
can't answer.

When an agent writes memory, the next session may treat that memory as working context. Before that happens, the user should be able to ask:

01Who wrote this memory?
02Was it confirmed by a person?
03What did it replace?
04What changed later?
05Can it leave this machine?
06Should the next session trust it?
"MOOTx01 is built to keep those questions attached to the memory."
The Contract

Same memory commands.
Safer memory records.

Diagram: Claude uses the Anthropic memory interface (view, create, str_replace, insert, delete, rename) while MOOTx01 stores each memory in a vault with source records, confirmation state, full audit trail, and reversible controls.
Anthropic memory interface memory_20250818 MOOTx01 storage vault Records · History · Audit · Withdrawal
Claude keeps the interface Anthropic defined.

It can call memory. It can work under /memories. It can receive the same file-like responses back.

view create str_replace insert delete rename
memory.create /memories/project-notes.md
saved as reviewable record · source: model · unconfirmed
MOOTx01 changes what happens after the write.

Each memory becomes a record the user can review. New model-written memories start unconfirmed. Edits keep older versions in the history. Deletes remove memory from active use while keeping a record of what happened.

The interface stays simple for Claude. The memory stays accountable to the user.

After the Write

What MOOTx01 adds
to every operation.

On create
Provenance

When the agent creates memory, MOOTx01 records that the model wrote it and keeps it unconfirmed until a person reviews it.

On edit
History

When the agent edits memory, MOOTx01 keeps the older version in the history. What it replaced stays visible.

On delete
Audit

When the agent deletes memory, MOOTx01 removes it from active use while preserving a record of the change.

On view
Familiarity

When the agent views memory, MOOTx01 shows Claude the file-shaped view it expects. Nothing about the interface changes.

"This gives agents a familiar way to work while giving users a practical way to manage trust."
Use It Today

Two commands.
Pick your surface.

MCP & interactive use
mootx01 enable memory-tool

Turns on the memory tool surface for Claude and any MCP-capable client. Claude sees the interface it already knows; every write lands in your MOOT as a reviewable record.

Messages API developers
pip install moot-memory

A drop-in handler for the memory_20250818 tool in your own agent loop. Same contract, reviewable records underneath.

MOOTx01 v1.0.25 is available today and free for individuals to use.