Living Brain launches cross-platform agent memory layer claiming 92.2% on LoCoMo
rohanpaul_ai · x · 2026-11-04
Living Brain launched a persistent, self-learning interoperable memory layer for AI agents, available via API, SDK and MCP and compatible with 60+ AI platforms, with support for linking custom MCPs.
Vendor-reported internal benchmark numbers:
- 92.2% judged accuracy on LoCoMo across 1,540 questions; 94.7% on temporal queries
- 464 ms median memory retrieval and 3.7 s median answer time
- 5.1K tokens per question on LongMemEval-S vs a 116K full-context baseline: 22.6X fewer tokens and 95% lower cost per task
- Claims 0% hallucinations on LongMemEval-S
Caveat: all results are internal evaluations and self-reported rankings, not third-party verified.
Related event: Living Brain Unveils Cross-Platform Persistent Memory Layer for AI Agents(2 posts)→
More from coding & agent
- Code mode isn't about MCP: it's about whether tool results go to context or program variables — ritakozlov · 2026-11-05
- Agent Arena: frontier models show 55-minute gap on long-horizon agent tasks — arena · 2026-11-05
- Agent-based kernel optimization faces a fidelity-throughput tradeoff: random data misleads, cold starts cost 12.7 minutes — simran_s_arora · 2026-11-05
- Solo dev builds window-free OS where a local Qwen3.5 9B generates every screen — leonardo_c · 2026-11-05
- Apple team ships Siri Evaluations: don't skip evals when wiring App Intents into Siri AI — rudrank · 2026-11-05
- RECAP: RL recipe for context compaction in long-horizon agents, +4.3pp on SWE-bench — Michael_D_Moor · 2026-11-05