| What it does | Agent memory that learns from experience
| Your voice and skills in every AI tool you use
|
|---|
| Stage | Startup
| Startup
|
|---|
| Founded | 2024
| Not given
|
|---|
| Based in | US
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| 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
| Free: 1 Profile, 10 Skills, 50 Documents, 10 Artifacts, 1 Style Guide from Starter Pack, 100 Hosted Chat AI credits/month. Pro: $24/mo or $20/mo billed annually, 5 Profiles, 75 Skills, 500 Documents, 75 Artifacts, 1 Style Guide, 1,000 Hosted Chat AI credits/month. Max: $49/mo or $40/mo billed annual
|
|---|
| 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
| - Profiles to define voice, tone, and judgment
- Style Guides to enforce writing rules
- Knowledgebases to store trusted documents and notes
- Skills to package repeatable workflows
- Artifacts for versioned, shareable outputs
- Hosted Chat with custom runtime
- MCP integration with external tools
- Team workspaces with shared knowledge
- Skill Catalog for discovery and import
- Collections to group and present artifacts
|
|---|
| 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
| - Output sounds like you, not generic AI, because every tool reads the same profiles and style guides
- Stop re-uploading docs and rewriting instructions for each new tool
- Individual voice, shared standards on teams
- Built-in changelogs instead of Git for managing skills
- Works with any MCP-compatible AI client without vendor lock-in
|
|---|
| 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 | 2 ● no change since last check |
|---|
| Trust Flow (Majestic) | 18 | 4 |
|---|
| Citation Flow (Majestic) | 47 | 25 |
|---|
| Referring domains (Majestic) | 1378 | 27 |
|---|
Vectorize