I built an app that preserves, encrypts, searches, reuses, and hands off the full work traces people create with Claude, Codex, Cursor, OpenClaw, and other AI agents.
It turns Claude, Codex, Cursor, OpenClaw, and other agent sessions into private data assets for your future AI employees.
Some technical details:
- AES-256-GCM encrypted local vault for transcripts, attachments, and state
- No DataMoat cloud vault or server-side transcript storage
- Vault keys and transcript data stay on the user’s machine
- Supported sources today include Claude CLI, Codex CLI/app local sessions, Claude Desktop local-agent sessions on macOS, OpenClaw, and Cursor agent transcripts
- Captures locally written thinking/reasoning blocks when the source tool stores them on disk
- Stores both raw source records and normalized searchable records
- Supports encrypted attachment blobs for supported images, PDFs, documents, and other files
- Password-based unlock with an scrypt verifier
- Optional TOTP authenticator support
- 24-word BIP39 recovery phrase and one-time recovery codes
- Secure Enclave-backed unlock path on supported Macs, with Touch ID in the packaged macOS app
- Packaged macOS app is signed and notarized; Linux source install is available; Windows ZIP builds are available but still unsigned
We believe every person and company should have the fundamental right to own their AI data and build their own data moat.
I think so. I believe this type of reasoning method, which achieves better results through longer computation time, is very useful on edge devices like mobile phones. Consider a scenario where we only need the model to output a function/action call on the phone; we don't require it to provide an immediate response.
We conducted similar research earlier and successfully improved performance to a level comparable to models with 3x larger layer sizes. https://arxiv.org/html/2409.14199v3 We utilize more computational time in the latent space to achieve better performance. However, this approach introduces greater resistance compared to Chain of Thought (CoT) reasoning in the token space, especially if the number of CoT rounds in the latent space exceeds 20.
I would using the term "better approximation of the data distribution" instead of "reasoning" to describe this kind of process.
I am the developer of Realll. I was a data scientist and I learned app development by myself because I cannot find anyone to help building our ambition. Our ambition is to build a real and trustful web system by everyone for everyone. The web is full of fake information and reviews by big companies in order to control our purchase behaviors.
In Realll app, you can rate, review, save and search any product/link provided by you or others. If you click the title on the item page, it redirects to the link immediately. Every rating not from your chain is blocked.
Really excited to hear feedback from you all. If you cannot find any rating, you can follow my account: Max