| What it does | Agent memory that learns from experience
| On-demand cloud macOS for AI agents, billed per minute
|
|---|
| Stage | Startup
| Startup
|
|---|
| Founded | 2024
| 2026
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Freemium
| Paid
|
|---|
| Pricing | Self-hosted: Free, MIT licensed. Hindsight Cloud: Pay-as-you-go with free credits to start. Retain (store memories) $10.00 per million tokens, Recall (retrieve memories) $0.75 per million tokens, Reflect (synthesize patterns) $0.05 per call, Iris Extract (structured extraction) $7.50 per million tok
| $0.90 per hour, billed per minute. Prepaid credit starts at $10, never expires and needs no subscription. Bigger top-ups add up to 20% bonus credit: $100 buys 133 hours. 7-day money-back guarantee on first purchase.
|
|---|
| Key features | - Per-user persistent memory with preferences, history and decisions kept separate
- Cross-session persistence allows context to survive weeks between interactions
- Fast parallel retrieval in under 100ms through four strategies running simultaneously
- Works with any LLM without losing learned context when swapping models
- Learns from mistakes and corrects behavior on repeated problems
- Automatic pattern detection synthesizes individual facts into consolidated knowledge
- Conflict detection preserves both old and new states with timestamps when facts change
- Integrates with 20+ coding agents including Claude Code, Cursor, and Copilot
| - Real macOS on Apple M6 or M5 Pro silicon, ready in about a minute
- Full admin access with no password prompts
- Xcode 27 preinstalled with Homebrew, Node, Python and CocoaPods
- iOS Simulator with screenshots and screen recordings
- Persistent 20 GB encrypted drive between sessions
- Control via MCP, CLI, API or SSH
- App Store submissions and TestFlight uploads
- Secrets management without chat exposure
- Desktop view and control in browser
|
|---|
| What makes it different | - 94.6% retrieval accuracy on LongMemEval-S, beating next-best system at 74.0%
- MIT licensed open source with no usage limits, telemetry or restrictions
- Reflection layer automatically builds judgment and mental models over time without manual tagging
- Entity resolution handles hundreds of entities with 99.5% query reduction
| - Agents work autonomously without human prompts or permission dialogs
- Pay only for minutes used, not idle Mac time
- Complete end-to-end app building and publishing from iOS Simulator to App Store
- Built-in isolation and security with ephemeral sessions
|
|---|
| 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) | 68 ▲ +1 (up) since last check | 20 ▼ −1 (down) since last check |
|---|
| Trust Flow (Majestic) | 18 | 13 |
|---|
| Citation Flow (Majestic) | 47 | 28 |
|---|
| Referring domains (Majestic) | 1378 | 140 |
|---|
Vectorize
NoMac