diff --git a/apps/docs/intro.mdx b/apps/docs/intro.mdx
index f089d3c9..20eef381 100644
--- a/apps/docs/intro.mdx
+++ b/apps/docs/intro.mdx
@@ -4,81 +4,82 @@ sidebarTitle: "Overview"
icon: "book-open"
---
-Supermemory is the long-term and short-term memory and context infrastructure for AI agents. It is the [state of the art](https://supermemory.ai/research) across multiple benchmarks, including LongMemEval and LoCoMo.
+Supermemory is the memory and context engine for AI agents — and it's the state of the art, ranked **#1 on every major memory benchmark**: [LongMemEval](https://github.com/xiaowu0162/LongMemEval), [LoCoMo](https://github.com/snap-research/locomo), and [ConvoMem](https://github.com/Salesforce/ConvoMem).
-With supermemory, you give your agents perfect recall about their users — so they're more intelligent, more personalized, and more consistent. Every piece of the context stack is built in, behind one API.
+Your AI forgets everything between conversations. Supermemory fixes that. It learns from every interaction, **reasons over a directed knowledge graph** to resolve contradictions and track how facts change over time, forgets what's expired, and serves the right context at the right moment — through one API.
+
+## State of the art, by the numbers
+
+Most memory systems claim to be better. Supermemory is measurably ahead — first place across all three independent benchmarks the field uses to grade AI memory.
+
+| Benchmark | What it measures | Supermemory |
+|---|---|---|
+| [LongMemEval](https://github.com/xiaowu0162/LongMemEval) | Long-term memory across sessions, with knowledge updates | **81.6% — #1** |
+| [LoCoMo](https://github.com/snap-research/locomo) | Fact recall across long conversations (multi-hop, temporal, adversarial) | **#1** |
+| [ConvoMem](https://github.com/Salesforce/ConvoMem) | Personalization and preference learning | **#1** |
+
+Read the full methodology on the [research page](https://supermemory.ai/research), or reproduce it yourself with [MemoryBench](/memorybench/overview), our open-source benchmarking framework.
+
+## What makes Supermemory different
+
+Most "memory layers" are a vector store that retrieves the nearest chunk. Supermemory is an engine that *understands* — which is why it tops the benchmarks instead of just claiming to.
+
+
+
+ Resolves contradictions, tracks temporal change, follows multi-hop relationships, and forgets expired facts automatically. Reasoning is why it wins every benchmark.
+
+
+ One evolving directed graph and a single ontology across all your data — not a flat vector store, and not a raw graph you have to traverse yourself.
+
+
+ Memory, user profiles, hybrid search (RAG), connectors, and file processing — together, sharing one context pool. No stitching five tools together.
+
+
+ Text, conversations, PDFs, images (OCR), video (transcription), and code (AST-aware chunking). Upload it and it just works.
+
+
+ One API, plus SDKs, a CLI, a memory filesystem, and MCP. Infrastructure you ship products on — not a closed box.
+
+
+ Hosted for zero-ops scale, or the full engine as one self-hosted binary — fully offline if you want, same API either way.
+
+
**Hosted or self-hosted — same API.** Use the [managed platform](https://console.supermemory.ai) for zero-ops scale, or [run the entire engine on your own machine](/self-hosting/overview) — one binary, zero config, fully offline. Move between them by changing a single `baseURL`.
-## What you can build with it
-
-
-
- Extract and evolve facts about each user over time — knowledge updates, temporal changes, automatic forgetting.
-
-
- A live blend of static and dynamic context your agent should always know, built automatically from memory.
-
-
- Semantic search with metadata filtering, contextual chunking, and reranking — over memories and raw documents in one query.
-
-
- Ingest text, conversations, PDFs, images, and even video — all turned into searchable, structured context.
-
-
- Continuously pull from Google Drive, Notion, Gmail, OneDrive, and more, with no pipeline to maintain.
-
-
- Production-grade retrieval as a service, tuned to work alongside the memory engine.
-
-
-
-All of it shares the **same context pool** for a given user (`containerTag`), so memory and search reinforce each other instead of living in separate silos.
-
## How does it work? (at a glance)
- You send Supermemory text, files, and chats.
-- Supermemory [intelligently indexes them](/concepts/how-it-works) and builds a semantic understanding graph on top of an entity (e.g., a user, a document, a project, an organization).
-- At query time, we fetch only the most relevant context and pass it to your models.
+- It [indexes them intelligently](/concepts/how-it-works) and builds a directed knowledge graph on top of an entity (a user, document, project, or organization).
+- At query time, it fetches only the most relevant context and passes it to your models.
-## Supermemory is context engineering
+## Three ways to add context
-We offer three ways to add context to your LLMs — mix and match them as your use case needs.
+Memory, profiles, and search all draw from the **same context pool** for a given user (`containerTag`) — so they reinforce each other instead of living in silos. Mix and match as your use case needs.
#### Memory API — learned user context
-Supermemory learns and builds memory for each user. These are extracted facts that:
+Supermemory learns and builds memory for each user — extracted facts that:
- [Evolve on top of existing context about the user](/concepts/graph-memory), **in real time**
-- Handle **knowledge updates, temporal changes, and forgetfulness**
+- Handle **knowledge updates, temporal changes, and contradictions**
- Power a **user profile** that acts as the default context provider for the LLM
-_Provide this to your LLM for more contextual, personalized responses._
-
#### User profiles
-The latest, evolving context about a user also produces a [**User Profile**](/concepts/user-profiles) — static and dynamic facts the agent should **always** know:
+The evolving context produces a [**User Profile**](/concepts/user-profiles) — the facts your agent should **always** know, in one ~50ms call:
-- **Static:** information the agent should **always** know.
-- **Dynamic:** **episodic** information about the last few conversations.
-
-Configure what counts as static vs. dynamic for your use case for extremely personalized retrieval.
+- **Static:** stable facts the agent should always know.
+- **Dynamic:** episodic context from the last few conversations.
#### RAG — advanced semantic search
-Alongside user context, run search over the raw content. Full RAG-as-a-service, with:
-- Advanced metadata filtering
-- Contextual chunking
-- Tight integration with the memory engine
-
-
-All three approaches share the **same context pool** when using the same user ID (`containerTag`). Mix and match based on your needs.
-
+Run hybrid [search](/search) over the raw content too: advanced metadata filtering, contextual chunking, and reranking — tightly integrated with the memory engine, in a single query.
## Start building