Home / Companies / Perplexity / Blog / Post Details
Content Deep Dive

Brain: Agentic memory as a knowledge wiki

Blog post from Perplexity

Post Details
Company
Date Published
Author
Perplexity Engineering
Word Count
3,425
Company Posts That Month
8
Language
English
Hacker News Points
-
Post removed?
No
Summary

Brain is a memory architecture for Computer agents designed to retain and apply user context across long-running work spanning many sessions. It organizes persistent information in a filesystem with a synthesized, Git-backed Markdown knowledge wiki called Brain, topical notes, and raw session histories; wikilinks connect related concepts while citations trace claims to supporting evidence. Foreground agents explore this memory through standard file operations and can use a Memory Agent to semantically retrieve and locally materialize additional files, avoiding the latency of remote filesystem access and the context overload of loading all information at once. Background “Dream” agents periodically summarize new sessions, update knowledge pages, verify evidence, and stage changes for deterministic and semantic validation before synchronization. Internal offline and production-derived evaluations reported that Brain improved correctness, evidence recall, and currentness, particularly for preferences, temporal reasoning, and information distributed across sessions, while also reducing token use, costs, and response time.

Trends Found in this Post
Trend Post Mentions Total Month Mentions Posts Companies MoM
LLM 1 5,068 1,020 229 -34%
Subagents 1 276 88 41 +39%
Web search for AI agents 1 No monthly metrics for this publish month.
Use This Data

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.