Persistent memory for AI agents and robots with Git-style versioning
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Serverless inference with per-token pricing (pay for output, input, and cached tokens). Training pricing from $0.50 to $10.00 per 1M training tokens depending on model size and fine-tuning type. On-demand deployments at $0.134 to $0.334 per minute ($8 to $20 per hour) for various GPU types.
Not given
Key features
Guided training runs
Configuration-led training
Custom training logic
Serverless inference
On-demand dedicated deployments
Reserved capacity
OpenAI compatible API
Model library with latest open models
Reinforcement learning support
Multi-region deployments
Hybrid vector and knowledge-graph retrieval
Zero-copy state branching and merging
44 memory tools over MCP protocol
Sub-0.4ms P99 retrieval latency
Built-in importers from Mem0, Zep, Pinecone and others
Entity deduplication and linking
Offline operation with fleet synchronization
Memory Copilot for schema generation
Object storage for multimodal state
What makes it different
Drop-in replacement for closed-model APIs with cost savings of 50-75%
Instant production deployment from any training checkpoint in seconds
Optimized inference engine for industry-leading throughput and latency
Elastic and global RL inference scaling
Own the complete learning loop for specialized intelligence
Memory versioning with Git-style fork, diff and merge—test changes safely and undo mistakes
Native MCP integration: one URL works with Claude, Cursor, Windsurf and any MCP client
Seamless migration from Mem0, Zep, Pinecone and other systems without data loss