| What it does | An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
| Cloud memory for AI agents and teams
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| JP
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Prototype: free during beta, then from December 16, 2026 it costs $1 per 1,000 agent calls after 1,000 monthly included calls. Production: $20 a month with 20,000 agent calls included, then $1 per 1,000 calls after that. Top-ups: $1 per 1,000 calls, from $10 to $500 at a time, never expiring.
| Free: 100 memos, 3 projects, 1 public project, no file uploads; Pro: $6/month with 500 memos, 5 projects, 2 public projects, 100 MB storage; Max: $9/month with 10,000 memos, 1,000 projects, 5 public projects, 1 GB storage, 1 family member; Team: $15/seat/month with unlimited memos, projects, public
|
|---|
| Key features | - Prompt rebuilt from journal under token cap at each step to keep it bounded as history grows
- Spending limits checked before each model call at token prices you declare
- Resume after crash without repeating finished actions
- Tool calls returned as actions for your code to carry out
- Proof of what ran: check prompts, re-run engine, download hash-chained journal
- Integrations with Vercel AI SDK, OpenAI Agents SDK, LangGraph, Mastra, Pydantic AI
- MCP server for Claude Code, Claude Projects and Codex
- Works with any model via bring-your-own-key
- TypeScript and Python clients for HTTP API access
| - Save and recall memos across chat sessions
- Works with ChatGPT, Claude, Gemini, Grok and other MCP clients
- Organize memos into projects with access control
- Public projects that anyone can follow
- File uploads and storage on paid plans
- Memo history and activity tracking
- API for custom chatbots and apps
- Temporary memos that auto-archive
- Tags and search by meaning
|
|---|
| What makes it different | - Bounded prompt under a fixed cap while history grows, so costs per call stop climbing on long sessions
- Every run recorded with cryptographic proof: rebuilable prompts, hash-chained journal, re-runnable engine
- Resumes from crash without repeating finished actions using stable idempotency keys
- Budget enforcement before each model call, not reactive overage billing
- No model key storage or logging; your provider bills you directly
| - Memory persists across different AI tools, not locked into one application
- Shared team memory in a single workspace instead of scattered notes
- No installation required, integrates via protocol endpoint
- Works with any MCP-compatible client, not just one platform
- Free tier with 100 memos and 3 projects to start
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 40 ● no change since last check |
| Trust Flow (Majestic) | 0 | 4 |
| Citation Flow (Majestic) | 9 | 26 |
| Referring domains (Majestic) | 4 | 66 |