Skip to main content

How It Works / Local & Privacy

Your knowledge, on your terms

Local-first architecture is a design principle, not a compromise. Every conversation, memory, and document is a file on your filesystem. What you route to a cloud provider travels directly from your machine to theirs — Memorandai runs no servers that intercept or hold your data.

Local Architecture

All Memorandai data — conversations, memories, keystones, documents — lives on your filesystem. No cloud sync, no remote servers, no third-party storage. When you route a prompt to a cloud AI provider, it goes directly to that provider under their terms. Memorandai is never in the middle.

You can browse, back up, port, or delete any of it at any time — standard file formats on your filesystem, nothing proprietary in between.

Data Management

The Data screen under Library → Exporters gives you a curated export path on top of the filesystem-level access. Pick what to back up by category — Projects (flow graphs, workspaces), Memories (conversation shards, keystones, ingested documents), Notebooks (pages, domains, embedded images), Settings (API keys, model preferences, feature flags), Profile (identity and AI-generated profile) — and Memorandai writes a single zip you can copy to another machine, save to cloud storage, or hand to a backup tool.

Restore is a drop-target away: drag a previous backup zip into the Restore panel and Memorandai re-hydrates the categories you choose to bring over.

Memorandai's Data Management screen with two panels: an Export panel on the left listing five selectable data categories (Projects, Memories, Notebooks, Settings, Profile) each with file counts and a checkbox, ending in an 'Export Selected' button; and a Restore panel on the right with a drag-and-drop zone for uploading a backup zip.

No proprietary container, no vendor lock-in. The export is a standard zip of the same files you could move manually — Data Management is just the convenient shortcut.

Bring Your Own Keys

Use your own API keys from OpenAI, Anthropic, Google, and xAI. You pay the providers directly at their published rates. Memorandai never sees your keys, never adds markup, and encrypts them at rest.

Memorandai's API Providers settings screen showing four provider cards in a 2-by-2 grid (OpenAI, Anthropic, Google, xAI), each with the provider's active model name (gpt-5.5, claude-opus-4-7-1m, gemini-3.1-pro-preview, grok-3), the canvas features it powers (chat nodes plus the relevant image-generation provider), a 'Get your API key' link, a masked key preview, and Change/Remove/Test Connection controls. Above the grid: a Quick Setup row with three preset cards (Best Quality, Balanced, Budget) for auto-configuring all providers at once. A 'Usage & Cost' link sits in the top right; the page header reads '4 of 4 providers configured.'

Built-In Local Inference

Download and run local GGUF models in a few clicks — GPU-accelerated when available, CPU-friendly otherwise. Free for local-only conversations and useful for sessions you'd rather keep entirely on-device. Memorandai works best with cloud providers configured for the full feature set; local inference is a complement, not a complete replacement.

  • Configurable tool access on models that support it
  • No internet required for local-only conversations after initial model downloads
  • Same canvas workflow as cloud models — local nodes slot into the same Flows
  • Curated, rotating recommendations — current slate: Qwen 3 8B, Llama 3.1 8B Instruct, Gemma 3 4B Instruct, and Qwen 3 1.7B — all one-click downloadable in the app
  • Custom download — paste any HuggingFace model URI or direct .gguf URL for models beyond the curated set
Memorandai's Local Models screen with three sections stacked vertically. The Hardware panel at the top shows the detected GPU (NVIDIA GeForce RTX 4090 Laptop GPU running on the Vulkan backend), VRAM totals (15.7 GB total, 5.1 GB used, 10.5 GB free), and the currently active model (Qwen3 8B, 4.7 GB in memory, 37 GPU layers) with an Unload button. The Downloaded Models panel below lists two installed GGUF models with Load/Unload and delete controls per model. The Recommended Models panel at the bottom shows curated download cards for Qwen 3 8B (tagged tool-calling, recommended, and latest) and Llama 3.1 8B Instruct (tagged popular and general), each card showing model size, a one-paragraph description, and a Download button.

Local Model Support

Memorandai supports four cloud chat providers (Anthropic, OpenAI, Google, xAI) and local GGUF inference via node-llama-cpp. Local coverage is comprehensive for chat workflows, partial for some background processing, and absent for features that require strict JSON output, vision, or cloud-anchored orchestration. The matrix below names every feature explicitly.

Full Local Support

Chat workflows and most companion features run end-to-end on local models with quality on par with cloud for typical use.

Feature Notes
Local Chat node (Flows mode) Native llama.cpp via node-llama-cpp v3, GGUF models loaded into VRAM. Tool calling via grammar-constrained generation, capped at 20 user-selected tools.
Chat View (linear chat mode) Local routing branch alongside the four cloud providers.
Roundtable (local participant) Loaded local model fans out alongside cloud participants. One-shot, no tools. Synthesis stays cloud-only (Helios runs the synthesis pass).
Reflection node Margin notes in the local model's voice when attached to a local response. Prose-only, no JSON fragility.
Auto-memo / nightly consolidation Routes local first when a model is loaded; cloud fallback on error or empty result.
Thread brief generation Tries local first, then gpt-4o-mini, then haiku.

Partial — Cloud Recommended

Background tasks where local inference is wired up but quality varies. Open prose works; tasks requiring strict JSON output are fragile on smaller local models.

Feature Notes
Self-notes (Dream Cycle, per-genus) Generally works. Open-ended prose.
Helios convergence self-note Generally works. Open prose. Loses some Helios voice — the brief is built for the user's preferred cloud model.
Identity brief generation Generally works. Long-form prose. Quality drop noticeable but functional.
Profile identity-summary Generally works. Explicit local branch.
Helios Keystone Revision Cycle Fragile. Requires parseable JSON disposition array.
Keystone mining (Dream Cycle phase) Fragile. Requires parseable JSON with category, importance, and confidence fields.
Memory quality scoring Fragile. Strict JSON output.
Archive review scoring Fragile. Strict JSON output.

Cloud Only

Features that require cloud provider APIs by construction — orchestration paths bound to a cloud preferred model, hardcoded SDK calls, vision support, and image generation.

Feature Why cloud-only
Helios chat Orchestrator hardcoded to a cloud preferred model.
Per-provider chat nodes (Claude, GPT, Gemini, Grok) Bound to their provider by definition.
Roundtable synthesis Helios runs the synthesis pass; cloud-only by construction.
Daily Insight (regular and Helios voice modes) Direct cloud SDK calls.
Keystone miner (dedicated route) Direct cloud SDK calls. Distinct from the Dream Cycle keystone-mining phase, which is in the partial-support table above.
Helios proposal miner Direct cloud SDK calls.
Timeline scan Direct cloud SDK calls.
Knowledge distillation Hardcoded provider list.
Idea miner Direct cloud SDK calls.
MCP server builder Hardcoded to Claude with Anthropic tool use.
Custom node builder Hardcoded to Claude with Anthropic tool use.
Connectivity test Tests cloud provider reachability by definition.
Image generation (DALL-E 3, GPT Image 2, Imagen 4, Grok Aurora) No local image-gen path.
Image attachments in chat (vision) Local inference has no vision support; image attachments only work on the four cloud chat nodes.

Matrix reflects Memorandai 0.8.8.

MCP Servers

Extend Memorandai with Model Context Protocol servers. Install community servers or build your own. Each server adds new tools that every AI model on your canvas can use. The extensibility layer for power users.

Memorandai's MCP Servers page with an 'Add MCP Server' modal open in the foreground. The modal lets users register a new server with transport type (Command for local stdio or Remote SSE for hosted endpoints), server name, command (e.g. npx), arguments (one per line), optional environment variables, and an optional description. A warning at the bottom reminds users that only servers from trusted sources should be added — the command runs with the user's account permissions and can read or write to local data. Behind the modal: the existing MCP Servers list including a built-in Memory Search server with its available tools (memory-search, quotes-composer, memory-info).

Custom Nodes

Build your own node types with MCP command transport. Define input forms, connect to external services, stream results back to the canvas. Your workflow, your tools.

Memorandai's Custom Node Builder, a three-panel workspace for designing custom canvas nodes through an LLM-assisted spec-and-build flow. Left panel: a list of builder sessions including 'code-security-scanner', 'Test New Node Build', and 'Web Search Results Node', with a 'New Builder Session' button at the top. Center panel: a long Markdown spec for a search-results-display node covering UI features (search query display, clickable URLs, scrollable results, clean typography, error handling), design features (dark-theme color coding, icons, responsive sizing), and technical details (tool mapping, data handling, status management, TypeScript, React Flow); a 'Describe the custom code you want to build' input box sits at the bottom of the center panel. Right panel: a Live Preview pane showing the rendered node mockup (search-results-display with a search input and 'No results found' placeholder), a Mapped Tools section, and a Component Code byte counter.

Encryption & Security

API keys are encrypted at rest using machine-specific keys. No telemetry, no analytics, no tracking. The app does not phone home. Memorandai never sees, stores, or transmits your data — what reaches a cloud model is your call alone.

Offline-Friendly License

Activate once online. After that, your license works offline — no subscription server to check in with, no recurring validation. Local-only chat works fully offline; cloud sessions and background features (Dream Cycle, Daily Insight, keystone mining) require Internet and API keys.

Take control of your knowledge

Your data, your keys, your machine. No compromises.

Become a Founding Member