| What it does | One memory, every AI tool. Write once, recall anywhere.
| Agent memory that learns from experience
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2024
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: $0 with 1,000 queries/day, 10,000 atoms, 60 req/min. Pro: $29/mo with 50,000 queries/day, 500,000 atoms, 600 req/min. Team: $149/mo with 500,000 queries/day, 5,000,000 atoms, 3,000 req/min. Enterprise: Custom limits and 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
|
|---|
| Key features | - Persistent cross-tool memory API working with Claude, Cursor, VS Code, ChatGPT, Python, and any HTTP client
- Hebbian associations that strengthen links between concepts recalled together
- Outcome feedback that re-ranks recall based on usefulness
- Automatic query expansion along learned associations
- Python SDK with typed errors for write, read, feedback, and stats
- REST API for any HTTP client
- Per-tenant org isolation and SHA-256 hashed API keys
| - 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
|
|---|
| What makes it different | - Learns from outcomes and improves over time, unlike vector databases that only perform similarity search
- Works across every AI tool with a single API key, not locked to one platform
- Complementary to RAG: remembers outcomes and lessons, not just document similarity
- Free tier with full API access and MCP server, no credit card required
| - 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
|
|---|
| 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) | 40 ▼ −1 (down) since last check | 68 ▲ +1 (up) since last check |
|---|
| Trust Flow (Majestic) | 7 | 18 |
|---|
| Citation Flow (Majestic) | 37 | 47 |
|---|
| Referring domains (Majestic) | 200 | 1378 |
|---|
Mnemoverse
Vectorize