Everything you need for AI memory
PersistQ combines powerful semantic search, local embeddings, and transparent pricing to give your AI applications long-term memory at scale.
Zero Embedding Costs
Save hundreds per month with local Transformers.js embeddings. No per-token charges, no OpenAI API costs.
- Free embeddings forever
- No per-token fees
- Predictable pricing
Semantic Search
Vector-based search finds relevant memories even with fuzzy queries. Powered by pgvector and automatic embeddings.
- Automatic embeddings
- Hybrid search (semantic + keyword)
- Sub-200ms response time
Simple REST API
Get started in seconds with our intuitive REST API. Works with any language or framework.
- No complex setup
- SDKs for Node.js & Python
- Works with any HTTP client
Privacy First
Your data never leaves your infrastructure for embeddings. No third-party AI service dependencies.
- Local embedding generation
- GDPR compliant
- Secure API authentication
PostgreSQL + pgvector
Built on battle-tested PostgreSQL with pgvector extension. No vendor lock-in, familiar technology.
- Standard PostgreSQL
- pgvector for vectors
- Self-hosting option
Claude Code / MCP Ready
One prompt and Claude Code sets up PersistQ via MCP. Zero manual configuration needed.
- MCP integration
- Auto-setup with Claude
- Instant productivity
Powerful features for production
Everything you need to build AI applications with long-term memory
Memory Management
Store & Retrieve
Store memories with automatic embedding generation. Retrieve by semantic search or exact match.
Groups & Tags
Organize memories with groups and tags. Filter searches by category for precise results.
Metadata Support
Attach custom metadata to memories. Search and filter by any field.
Full CRUD Operations
Create, read, update, and delete memories via simple API endpoints.
Search Capabilities
Vector Search
Semantic search powered by 384-dimensional embeddings. Find relevant memories by meaning.
Keyword Search
Traditional text-based search for exact matches. Fast and reliable.
Hybrid Search
Combines semantic and keyword search for best results. Automatic query optimization.
Filtering
Filter by groups, tags, metadata, and date ranges. Narrow down results efficiently.
Developer Experience
Comprehensive Docs
Clear documentation with examples in multiple languages. Quick start guides included.
Dashboard UI
Web dashboard to view memories, manage API keys, and monitor usage.
Rate Limiting
Built-in rate limiting to protect your application. Configurable per tier.
Usage Analytics
Track API usage, storage, and costs. Basic analytics on free tier, advanced on paid.