Retrieval Pipeline
Multi-signal search. One answer.
Every recall runs multiple search strategies in parallel across your memory store and knowledge graph. Our proprietary scoring algorithm combines results into a single ranked list.
The Pipeline
Understand
Analyses the query to determine what kind of memory retrieval is needed
Optimise
Rewrites and expands the query for maximum retrieval accuracy
Search
Runs multiple search strategies in parallel across your knowledge graph
Score
Proprietary fusion algorithm combines results from all search paths.
Assemble
Deduplicates, formats, and trims to your token budget. Quality over quantity
Why It Works
Hybrid Graph-Retrieval
Combines knowledge graph traversal with semantic search. Finds connections between entities that pure embedding similarity misses entirely.
Multi-Signal Search
Multiple search strategies run in parallel. Each catches different types of results. The fusion layer combines them into a single ranked list.
Temporal Awareness
Understands time. When you ask 'what happened last week', the pipeline knows to search by date range, not just semantic similarity.
Knowledge Updates
When facts change, old information gets archived and new information takes priority. No stale results polluting your context window.
The Result
83.6% accuracy on the LongMemEval-S benchmark, running gpt-4o-mini. Ahead of the industry leader best system on the leaderboard, which uses the significantly more expensive GPT-4o. The retrieval pipeline does the heavy lifting, not the model. That means better results at a fraction of the cost.
524
tokens
Median context
688
tokens
Average context
1,642
tokens
95th percentile
Selective retrieval by design. Only what matters, not the entire context window.