# Introducing DeltaMemory : Cognitive memory for production AI agents

[Learn more >](/content/product/performance#/index.html)

## Performance

### Fast enough for real-time. Efficient enough for scale.

DeltaMemory is built in Rust with a custom storage engine. 50ms queries, 3,714x token compression, and 97% cost reduction over raw context re-processing.

50ms

p50 query latency

Rust-powered retrieval engine

3,714x

Token compression

26M tokens become 7K structured facts

97%

Cost reduction

vs. raw token re-processing

<1ms

Core operations

Write-ahead log + in-memory index

## LoCoMo benchmark results

Head-to-head comparison on the LoCoMo long-term conversation memory benchmark across all evaluation categories.

| Method | Single-Hop | Multi-Hop | Open Domain | Temporal | Overall | Latency (p50) |
| --- | --- | --- | --- | --- | --- | --- |
| DeltaMemory | 91.5% | 87.5% | 90.5% | 82.2% | 89% | 50ms |
| Memobase v0.0.37 | 70.9% | 46.9% | 77.2% | 85.1% | 75.8% | 800ms |
| Zep | 74.1% | 66% | 67.7% | 79.8% | 75.1% | 632ms |
| Memobase v0.0.32 | 63.8% | 52.1% | 71.8% | 80.4% | 70.9% | 900ms |
| Mem0-Graph | 65.7% | 47.2% | 75.7% | 58.1% | 68.4% | 2.6s |
| Mem0 | 67.1% | 51.2% | 72.9% | 55.5% | 66.9% | 1.4s |
| LangMem | 62.2% | 47.9% | 71.1% | 23.4% | 58.1% | 18.0s |
| OpenAI | 63.8% | 42.9% | 62.3% | 21.7% | 52.9% | 466ms |

Evaluated on the LoCoMo long-term conversation memory benchmark. All methods tested under identical conditions using GPT-4.1 as the base model.

## Under the hood

Every layer of the stack is designed for speed and efficiency.

### 3,714x Token Compression

Raw conversations are compressed into structured facts and a knowledge graph. 26 million tokens of conversation history become 7,000 tokens of structured memory. Your agents recall what matters without re-processing entire histories.

### 50ms Query Latency

Hybrid retrieval combines HNSW vector search, BM25 keyword matching, and graph traversal in a single query. Reciprocal Rank Fusion merges results. The entire pipeline completes in under 50ms at the median.

### Rust from the Ground Up

The storage engine is built from scratch in Rust. Write-ahead logging for crash recovery, B-tree sorted storage for fast reads, and parallel HNSW index rebuilding. No garbage collection pauses. No runtime overhead.

### Scales with Your Agents

Per-user session isolation with fine-grained locking means concurrent access for different users while serializing requests for the same user. Background fact extraction and batch embedding generation keep throughput high.

## What this means for your agents

Performance that translates directly into better user experiences and lower operating costs.

01

### Real-Time Responses

Memory retrieval completes in 50ms. Your agents respond with full context without adding noticeable delay to conversations.

02

### Lower Costs at Scale

Instead of re-sending entire conversation histories to your LLM, DeltaMemory delivers only the relevant facts. 97% fewer tokens processed per query.

03

### Always-On Reliability

Every memory write is durable before acknowledgment. If anything goes wrong, recovery is automatic. No data loss, no manual intervention.

## Early Access

### Give your agents memory that compounds.

DeltaMemory is available to select design partners and enterprise teams. Book a demo to see how persistent, cognitive memory works with your AI agents.

[Book a Demo](/content/request-access/index.html)

Delta