AI memory that stays
on your machine.
VeritasMemoria is a structured, auditable memory layer for AI-assisted workflows. Every record is cryptographically signed and hash-chained. No cloud. No accounts. No telemetry.
Built different by design
Most memory systems trade transparency for convenience. VM trades neither.
Local-First
All data stays on the machine running it. Nothing is sent to any server — not even to check for updates. Your memories are yours.
Tamper-Evident
Records are HMAC-signed. The audit log is hash-chained and append-only. You can verify that nothing has been altered — ever.
Human-in-the-Loop
The system cannot commit or retire memories without passing configurable oversight gates. You stay in control of what gets kept.
LLM-Agnostic
Works with OpenAI, Anthropic, Ollama, or any OpenAI-compatible endpoint. Runs fully offline in copy-paste mode with no LLM required.
Semantic Retrieval
Hybrid search combining dense vector embeddings and keyword indexing. Finds the right memory even when you don't remember exactly how you phrased it.
Transparent Storage
SQLite by default — a single file you can inspect, back up, or move. No opaque binary formats. Your data is always accessible without VM.
Simple architecture, serious guarantees
You write a memory
Paste text, upload a document, or let an agent push context. VM assigns it to working memory.
VM gates and signs it
Coherence and oversight checks run. On approval the record is HMAC-signed and appended to the hash chain.
Retrieve it later
Semantic and keyword search surface the right context instantly. Pass it to any LLM or read it yourself.
Running in under a minute
Pre-built binary for Windows — no Python, no dependencies, no installer.
- Download the
.zipfrom the Releases page - Extract to a folder you can write to
- Double-click
VeritasMemoria.exe - Open
localhost:8000
Minimum: Windows 10 64-bit, 2 GB RAM, 500 MB disk. macOS 12+ and Ubuntu 20.04+ supported via source install. GPU not required.
Works with what you already use
Switch providers in a single line of config. Or skip the LLM entirely and run in copy-paste mode.
Your data. Your machine. Your call.
VeritasMemoria ships blank and learns only what you explicitly give it. No defaults phoning home. No model training on your memories.