walrus-memory
llms.txt131 starsChanged 2 months agoApache-2.0View on GitHub
MemWal is a privacy-first AI memory layer. It stores encrypted memories on Walrus (decentralized storage) and retrieves them with semantic search. Ownership is enforced onchain via Sui smart contracts. The TypeScript SDK (@mysten-incubation/memwal) gives any app persistent, encrypted memory in a few lines of code. Important notes:
We split this llms.txt into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
All content is end-to-end encrypted — only the owner and authorized delegates can decrypt
≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# MemWal > MemWal is a privacy-first AI memory layer. It stores encrypted memories on Walrus (decentralized storage) and retrieves them with semantic search. Ownership is enforced onchain via Sui smart contracts. The TypeScript SDK (`@mysten-incubation/memwal`) gives any app persistent, encrypted memory in a few lines of code. Important notes: - The SDK talks to a relayer service that handles embedding, SEAL encryption, Walrus upload/download, and vector search - All content is end-to-end encrypted — only the owner and authorized delegates can decrypt - Delegate keys provide scoped access — agents can read/write memory without holding the owner's private key - Memory is scoped by `owner + namespace` — each namespace is an isolated memory space ## Docs - [What is MemWal?](https://docs.wal.app/walrus-memory/getting-started/what-is-memwal): Overview of features, architecture, and use cases - [Quick Start](https://docs.wal.app/walrus-memory/getting-started/quick-start): Install the SDK, generate credentials, store and recall your first memory - [Choose Your Path](https://docs.wal.app/walrus-memory/getting-started/choose-your-path): Pick the right integration path (MemWal, MemWalManual, or withMemWal AI middleware) ## SDK - [SDK Quick Start](https://docs.wal.app/walrus-memory/sdk/quick-start): Install, configure, and store your first memory - [MemWal Usage](https://docs.wal.app/walrus-memory/sdk/usage/memwal): Default relayer-handled client — remember, recall, analyze, restore - [MemWalManual Usage](https://docs.wal.app/walrus-memory/sdk/usage/memwal-manual): Manual client — client-side embedding and SEAL encryption - [withMemWal AI Middleware](https://docs.wal.app/walrus-memory/sdk/usage/with-memwal): Vercel AI SDK integration — automatic memory recall and save - [SDK API Reference](https://docs.wal.app/walrus-memory/sdk/api-reference): Full method signatures, return types, and config fields ## Relayer - [Relayer Overview](https://docs.wal.app/walrus-memory/relayer/overview): Architecture, trust boundary, key pool, single-instance design - [Public Relayer](https://docs.wal.app/walrus-memory/relayer/public-relayer): Managed relayer endpoints provided by Walrus Foundation - [Self-Hosting](https://docs.wal.app/walrus-memory/relayer/self-hosting): Run your own relayer with full control over encryption and embedding - [Relayer API Reference](https://docs.wal.app/walrus-memory/relayer/api-reference): HTTP routes, authentication headers, request/response shapes ## Smart Contract - [Contract Overview](https://docs.wal.app/walrus-memory/contract/overview): Onchain ownership model and package IDs - [Delegate Key Management](https://docs.wal.app/walrus-memory/contract/delegate-key-management): Add, remove, and rotate delegate keys - [Ownership & Permissions](https://docs.wal.app/walrus-memory/contract/ownership-and-permissions): Access control model ## OpenClaw Plugin - [OpenClaw Overview](https://docs.wal.app/walrus-memory/openclaw/overview): NemoClaw/OpenClaw memory plugin overview - [OpenClaw Quick Start](https://docs.wal.app/walrus-memory/openclaw/quick-start): Install and configure the plugin - [How It Works](https://docs.wal.app/walrus-memory/openclaw/how-it-works): Architecture, hooks, and message flow - [OpenClaw Reference](https://docs.wal.app/walrus-memory/openclaw/reference): Hooks, tools, CLI, and configuration ## Reference - [Configuration](https://docs.wal.app/walrus-memory/reference/configuration): MemWalConfig, MemWalManualConfig, WithMemWalOptions - [Environment Variables](https://docs.wal.app/walrus-memory/reference/environment-variables): Relayer env vars for self-hosting ## Optional - [Concepts: Memory Space](https://docs.wal.app/walrus-memory/fundamentals/concepts/memory-space): Namespace isolation and memory boundaries - [Architecture: Core Components](https://docs.wal.app/walrus-memory/fundamentals/architecture/core-components): System overview and component responsibilities - [Data Flow & Security Model](https://docs.wal.app/walrus-memory/fundamentals/architecture/data-flow-security-model): Trust boundaries and encryption flows - [Contributing: Run Repo Locally](https://docs.wal.app/walrus-memory/contributing/run-repo-locally): Monorepo setup for contributors - [Example Apps](https://docs.wal.app/walrus-memory/examples/example-apps): Playground, Chatbot, Noter, Researcher
In this repository2 other files it gives its agents.
- docs/llms-full.txtllms.txt
- memwalSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.