SLM360

Released

The First AI That Thinks, Learns, and Remembers On-Device

SLM360 is a revolutionary AI system that combines Natural Language Understanding with multi-step reasoning, self-improving memory, and predictive capabilities--all running entirely on-device in just 50MB. It breaks the traditional NLU trilemma of choosing between accuracy, latency, and efficiency by achieving 98-100% accuracy at 39ms latency with zero cloud dependency.

Specifications

50MB

Footprint

39ms

Latency

100%

Banking77

98%

SNIPS

<100ms

Reasoning

~64KB

Memory/User

Features

Hybrid classification: pattern matching (<1ms) + semantic embeddings (39ms) with confidence arbitration
Multi-step reasoning engine with conditional execution, sequences, and automatic rollback in <100ms
5-tier SmartMemory: short-term, episodic, semantic, procedural, and meta-learning -learns from every interaction
Predictive context engine: anticipates user needs from topic transitions, time patterns, and entity preferences
Cross-platform deployment: Linux, macOS, Windows, WebAssembly, with iOS and Android planned
100% on-device processing -GDPR, HIPAA, PCI-DSS compliant by architecture, not policy
50MB total footprint: ONNX model (32MB), pattern engine (8MB), reasoning (4MB), SmartMemory (2MB), cache (3MB), runtime (1MB)
196 tests passing with comprehensive coverage across NLU, reasoning, memory, WASM, and async