Early Access

AI that remembers.
Every client. Every conversation.

Persistent, cross-session memory for AI agents. Not context windows — real memory that survives between calls, users, and days.

$
0
per 1K tokens on our hardware
0K
context window, tiered memory

Memory that works as hard as you do.

Hot

GPU KV Cache

5–10K tokens in GPU VRAM. Instant recall within a session. $0.003 per 1K tokens on RecordorAI hardware — 800x cheaper than GPT-5.4 for the same context density.

🔍
Warm

Semantic Vector Store

Full conversation history in pgvector + Supabase. Infinite retention, queried on demand. No per-token cost scaling with history length.

🧠
Cold

Entity Compression

Each entity (user, project, decision) compressed to ~500 tokens. No hallucination risk — extractive, not generative. Costs almost nothing to store.


Everything your agents need.
Nothing they don't.

🔀

Model Routing

Auto-select Gemma 4 vs GLM-5.1 based on task complexity and cost. Fast tasks on Gemma, deep reasoning on GLM. No thought required.

🔌

REST API + SDKs

Python and JavaScript. Works with LangChain, AutoGPT, CrewAI, or your own stack. Drop-in memory backend — no rewrites.

💬

Chat UI

Browser-based UI for end users, connected to the same memory layer. Every conversation benefits from tiered memory automatically.

🔒

SOC 2 + HIPAA

Supabase is SOC 2 Type II certified and HIPAA-eligible. Customer data stays isolated. Works for security-sensitive workloads.

🛠️

Open Stack

vLLM, pgvector, Supabase — no vendor lock-in. The memory layer is yours. Deploy anywhere.

🧩

Interoperable

Plays well with the rest of the A.L.I.C.E. ecosystem — Runtime, Agents, Hub. Or use RecordorAI standalone with LangChain, CrewAI, AutoGPT, or your existing stack. Your choice.

📡

Webhooks

Memory events stream in real time. Build reactive workflows on top of your agent's memory.


Simple tiers. No surprises.

No API markups. No per-token royalties. You pay RecordorAI — we run the infra.

Starter
$15/mo
For individual builders
  • 50K tokens/day
  • REST API + Chat UI
  • Model routing (Gemma 4)
  • Community support
Start Free
Premium
$175/mo
For growing teams
  • 2M tokens/day
  • Everything in Pro
  • 50 concurrent agents
  • Advanced analytics
  • Priority SLA
Start Free Trial
Enterprise
Custom
For serious scale
  • Unlimited tokens
  • Dedicated infrastructure
  • On-premise option
  • SLA + dedicated support
  • SOC 2 / HIPAA docs
Contact Us
Sovereign
Custom
For regulated + classified
  • Air-gap deployment
  • FedRAMP High / IL5 path
  • Classified-environment hardening
  • 3-year contracts standard
  • Defense + intelligence + healthcare
Contact Us

Start building.
We'll get you in within 48 hours.

Free during beta. No credit card. Just access.

Memory is what you're signing up for. The rest is here if you're curious.

RecordorAI is the memory layer of A.L.I.C.E. — one of four products in a full-stack ecosystem. Each product is independently sold; each strengthens the others.