| What it does | Agent memory that learns from experience
| AI consulting, automation and voice agents for Australian businesses
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2024
| Not given
|
|---|
| Based in | US
| AU
|
|---|
| 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
| Monthly retainer plans: Starter from $2,800/mo (1 solution, light integrations, QA, weekly check-ins); Growth $5,200/mo (2-3 solutions, custom integrations, A/B testing, SLAs); Enterprise $8,200/mo (bespoke solutions, compliance reviews, on-call support, training). Fixed-scope projects also availabl
|
|---|
| 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
| - AI phone answering assistants that answer calls 24/7 and book jobs
- Website chat assistants for lead qualification
- Business automation for repetitive admin tasks
- AI integrations with CRMs, ERPs and data warehouses
- Business dashboards and reporting in Looker Studio, Power BI, GA4
- Website design and development for service businesses
- Guardrails and human-in-the-loop controls for AI safety
- 2-6 weeks delivery for pilots and focused solutions
- Integration with Twilio, HubSpot, Salesforce, Slack, OpenAI, Anthropic
- SOC2-friendly controls and data handling included
|
|---|
| 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
| - Industry-specific AI training for trades, construction and service businesses rather than generic tools
- Fast delivery in 2-8 weeks from first call to live system
- Founder-led, data science trained team with proven results
- Transparent, fixed-price proposals and published pricing
- Security and privacy-first with data minimization and audit trails
|
|---|
| 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 | 37 ▼ −1 (down) since last check |
| Trust Flow (Majestic) | 18 | 4 |
| Citation Flow (Majestic) | 47 | 16 |
| Referring domains (Majestic) | 1378 | 8 |