Research
Benchmarking a Token-Efficient Memory Algorithm for AI Agents
Libra's token-efficient memory algorithm achieves high accuracy on LoCoMo, LongMemEval, and BEAM while using a fraction of the tokens of full-context approaches.
Benchmark results
Numbers below are placeholders — we publish only figures we can reproduce.
LoCoMo
- Questions
- <N>
- Categories
- <N>
- Overall
- <score>
- Mean Tokens
- <n>
LongMemEval
- Questions
- <N>
- Categories
- <N>
- Overall
- <score>
- Mean Tokens
- <n>
BEAM (1M / 10M)
- Overall
- <score>
- Mean Tokens
- <n>
What's New
Two advances under the hood
Single-Pass ADD-Only Extraction
Treat agent-generated facts as first-class, extracted in a single pass without redundant re-processing.
Multi-Signal Retrieval
Three scoring passes run in parallel — semantic similarity, keyword matching, and entity matching — then fused for relevance.
What We're Building Next
The road ahead
Temporal abstraction
Reason about when facts were true and how they evolve over time.
Cross-session structure
Connect memories across sessions into coherent, queryable structure.
Agent-native memory
Memory primitives designed for how agents actually plan and act.