(the whole org)"] + Priv["Private channel memory
(that room's members)"] + Emp["Employee memory
(you, in DM)"] + + Priv -.reads.-> Pub + Emp -.reads.-> Pub + Emp -.reads.-> Priv +``` + +A DM is the widest seat in the room precisely because it's the most private one — the bot answers you there with everything *you* could see, stitched together. A public channel is the opposite: the whole org can read it, so it only ever draws on what the whole org is allowed to know. + +
+ **Jordan Alvarez** (acme-corp.io) sent a **new message**. +
+
+ Quick context: v3 search is deprecated, but we've committed to legacy support through end of year, so it's still worth fixing rather than telling people to migrate. Most likely cause is a change
+
+
+
+
+ Reproducing against the v3 search test suite now. +
+
+ **Resolution:** +
+ • Scoped the short-circuit to skip only the rewrite step, not the whole `rewriteQuery` path +
+ • Added a regression test covering `rewriteQuery` against a cache hit +
+
+ **Repository:** `supermemoryai/mono` +
+
+
+ Please do it ASAP — it's an enterprise customer! +
-
- )
-}
-```
-
-
- {messages.map((message) => (
-
-
-
-
-
- ))}
- {message.content}
-
- {/* Customer List Sidebar */}
-
- )
-}
-```
-
-## Testing Your Support System
-
-### Step 4: Test Support Scenarios
-
-1. **Test Customer Tiers**:
- - Free tier: Basic responses, self-service guidance
- - Pro tier: Detailed help, proactive suggestions
- - Enterprise: White-glove service, escalation readiness
-
-2. **Test Memory & Context**:
- - Ask about a previous issue
- - Reference customer preferences
- - Follow up on unresolved tickets
-
-3. **Test Escalation Triggers**:
- - Use keywords like "angry", "manager", "refund"
- - Test enterprise customer automatic escalation
-
-This comprehensive customer support recipe provides the foundation for building intelligent, context-aware support systems that improve customer satisfaction through personalized service.
-
----
-
-*Customize this recipe based on your specific support workflows and customer needs.*
diff --git a/apps/docs/cookbook/document-qa.mdx b/apps/docs/cookbook/document-qa.mdx
deleted file mode 100644
index 5aa071eb..00000000
--- a/apps/docs/cookbook/document-qa.mdx
+++ /dev/null
@@ -1,877 +0,0 @@
----
-title: "Document Q&A System"
-description: "Build a chatbot that answers questions from your documents with citations and source references"
----
-
-Create a powerful document Q&A system that can ingest PDFs, text files, and web pages, then answer questions with accurate citations. Perfect for documentation sites, research databases, or internal knowledge bases.
-
-## What You'll Build
-
-A document Q&A system that:
-- **Ingests multiple file types** (PDFs, DOCX, text, URLs)
-- **Answers questions accurately** with source citations
-- **Provides source references** with page numbers and document titles
-- **Handles follow-up questions** with conversation context
-- **Supports multiple document collections** for different topics
-
-## Prerequisites
-
-- Node.js 18+ or Python 3.8+
-- Supermemory API key
-- OpenAI API key
-- Basic understanding of file handling
-
-## Implementation
-
-### Step 1: Document Processing System
-
-
-
-
- {/* Main Content */}
-
-
- Customers
-
- {mockCustomers.map((customer) => (
-
- handleCustomerSelect(customer)}
- className={`p-4 cursor-pointer hover:bg-gray-50 ${
- selectedCustomer?.id === customer.id ? 'bg-blue-50 border-r-2 border-blue-500' : ''
- }`}
- >
-
- ))}
-
-
- {customer.name}
-
- {customer.tier}
-
- {customer.email}
-
- Member since {customer.joinDate}
-
-
- {selectedCustomer ? (
- <>
- {/* Customer Header */}
-
-
-
-
-
-
-
-
- {selectedCustomer.name}
-{selectedCustomer.email}
-
-
- {selectedCustomer.tier.toUpperCase()} Customer
-
- {showEscalation && (
-
-
- Needs Escalation
-
- )}
-
- {/* Chat Area */}
-
-
- ) : (
-
- {/* Messages */}
-
-
- {/* Customer History Sidebar */}
-
- {messages.length === 0 && (
-
-
- {/* Chat Input */}
-
-
- )}
-
- {messages.map((message) => (
- Welcome to Support Chat
- - Start a conversation with {selectedCustomer.name} -
-
-
- Customer Tier: {selectedCustomer.tier}
-Join Date: {selectedCustomer.joinDate}
-
-
- ))}
-
- {isLoading && (
-
-
-
-
- {message.role === 'user' ? selectedCustomer.name : 'Support Agent'}
-
-
- {new Date().toLocaleTimeString()}
-
-
- {message.content}
-
-
- )}
-
-
-
-
- Agent is typing...
-
-
-
-
-
-
-
-
- Customer History
-
- {customerHistory.map((interaction, index) => (
-
-
-
- ))}
-
- {customerHistory.length === 0 && (
-
- {interaction.type}
-
- {new Date(interaction.timestamp).toLocaleDateString()}
-
-
- - {interaction.content.length > 100 - ? `${interaction.content.substring(0, 100)}...` - : interaction.content - } -
- {interaction.outcome && ( -
-
- {interaction.outcome}
-
-
- )}
-
-
- )}
- No previous interactions
-
-
- )}
-
-
- Customer Support
- Select a customer to start a support conversation
-
-
- )
- }
-
- return (
- Sources:
-
- {sources.map((source) => (
-
-
-
- Document {source.citationNumber}
-
- {source.title}
-
- ({source.relevantChunks} relevant chunks, {(source.score * 100).toFixed(1)}% match)
-
-
- ))}
-
-
- )
-}
-```
-
-## Testing Your Q&A System
-
-### Step 4: Test Document Processing
-
-1. **Upload Test Documents**:
- - Upload a PDF manual or research paper
- - Add a few web articles via URL
- - Upload some text files with different topics
-
-2. **Test Question Types**:
- ```
- Factual: "What is the definition of X mentioned in the documents?"
- Analytical: "What are the pros and cons of approach Y?"
- Comparative: "How does method A compare to method B?"
- Summarization: "Summarize the main findings"
- ```
-
-3. **Verify Citations**:
- - Check that citations appear in responses
- - Verify citation numbers match source list
- - Ensure sources show relevant metadata
-
-## Production Considerations
-
-### Performance Optimization
-
-```typescript
-// Implement caching for frequently asked questions
-const cacheKey = `qa:${collection}:${hashQuery(question)}`
-const cachedResponse = await redis.get(cacheKey)
-
-if (cachedResponse) {
- return JSON.parse(cachedResponse)
-}
-
-// Cache response for 1 hour
-await redis.setex(cacheKey, 3600, JSON.stringify(response))
-```
-
-### Advanced Features
-
-1. **Follow-up Questions**:
- ```typescript
- // Track conversation context
- const conversationHistory = messages.slice(-6) // Last 3 exchanges
- ```
-
-2. **Answer Confidence Scoring**:
- ```typescript
- const confidence = calculateConfidence({
- searchScore: searchResults.results[0]?.score || 0,
- resultCount: searchResults.results.length,
- chunkRelevance: avgChunkRelevance
- })
- ```
-
-3. **Multi-language Support**:
- ```typescript
- // Detect document language and adapt search
- const detectedLanguage = await detectLanguage(question)
- const searchResults = await client.search.documents({
- q: question,
- filters: {
- AND: [{ key: 'language', value: detectedLanguage }]
- }
- })
- ```
-
-This recipe provides a complete foundation for building document Q&A systems with accurate citations and source tracking.
-
----
-
-*Customize this recipe based on your specific document types and use cases.*
diff --git a/apps/docs/cookbook/inf-chat-blog.mdx b/apps/docs/cookbook/inf-chat-blog.mdx
deleted file mode 100644
index f5c2fcbe..00000000
--- a/apps/docs/cookbook/inf-chat-blog.mdx
+++ /dev/null
@@ -1,4 +0,0 @@
----
-title: "Extending context windows in LLMs"
-url: "https://supermemory.ai/blog/extending-context-windows-in-llms/"
----
diff --git a/apps/docs/cookbook/overview.mdx b/apps/docs/cookbook/overview.mdx
deleted file mode 100644
index a36dcfb6..00000000
--- a/apps/docs/cookbook/overview.mdx
+++ /dev/null
@@ -1,64 +0,0 @@
----
-title: "Cookbook"
-description: "Complete examples and recipes for building with Supermemory"
-sidebarTitle: "Overview"
----
-
-The Supermemory Cookbook provides complete, production-ready examples that show how to build real applications with Supermemory. Each recipe includes full implementation details, best practices, and common patterns.
-
-## Available Recipes
-
-
- {/* Document Management Panel */}
-
-
-
-
- {/* Q&A Interface */}
-
-
- Document Collection
- - {/* Collection Selector */} -
-
- setCollection(e.target.value)}
- className="w-full p-2 border border-gray-300 rounded focus:ring-2 focus:ring-blue-500 focus:border-blue-500"
- placeholder="e.g., company-docs"
- />
-
-
- {/* File Upload */}
-
-
-
-
-
- {/* Upload Progress */}
- {Object.keys(uploadProgress).length > 0 && (
-
- {Object.entries(uploadProgress).map(([filename, progress]) => (
-
- )}
-
- {/* Document List */}
-
-
- ))}
-
- {filename}
- {progress}%
-
-
-
-
-
- {documents.map((doc) => (
-
-
-
-
-
- ))}
- {doc.title}
-
- {doc.type} • {doc.status}
-
-
-
-
-
- Ask Questions
- - {/* Messages */} -
- {messages.length === 0 && (
-
-
- {/* Input */}
-
-
- {documents.length === 0 && (
-
- Upload documents and ask questions to get started!
-
-
- )}
-
- {messages.map((message) => (
-
-
- Try asking:
--
-
- "What are the main findings?" -
- "Summarize the key points" -
- "What does section 3 say about...?" -
-
- ))}
-
- {isLoading && (
- {message.content}
-
- {message.role === 'assistant' && sources.length > 0 && (
- formatSources(sources)
- )}
-
-
- )}
-
-
- Searching documents and generating answer...
-
- - Upload documents first to enable questions -
- )} -
-
- )
- }
-
- return (
-
-
- 🤖 Personal AI Assistant
- setTempName(e.target.value)} - className="w-full px-4 py-2 border rounded-lg" - /> - setTempEmail(e.target.value)} - className="w-full px-4 py-2 border rounded-lg" - /> - -
-
- )
-}
-```
-
-
- {messages.map((message) => (
-
-
-
-
-
- ))}
- {message.content}
-
+ 
+
+
+
+
+ )
+}
+
++ {title} +
++ {description} +
+
+
diff --git a/apps/docs/add-memories.mdx b/apps/docs/ingestion/add-memories.mdx
similarity index 89%
rename from apps/docs/add-memories.mdx
rename to apps/docs/ingestion/add-memories.mdx
index 7d34221f..39d7c103 100644
--- a/apps/docs/add-memories.mdx
+++ b/apps/docs/ingestion/add-memories.mdx
@@ -1,15 +1,11 @@
---
title: "Ingesting context to supermemory"
-sidebarTitle: "Add context"
+sidebarTitle: "API"
description: "Add text, files, and URLs to Supermemory"
icon: "plus"
---
-Send any raw content to Supermemory — conversations, documents, files, URLs. We extract the memories automatically.
-
-
+
+
+
+
+ + supermemory +
++ Context infrastructure for AI agents. Use it with the API, your tools, your team, or run it yourself. +
+ +
+
+
-
-
-
-
-
- )
-}
-
-{title}
-{description}
-
-
-
diff --git a/apps/docs/list-memories/examples/basic.mdx b/apps/docs/list-memories/examples/basic.mdx
deleted file mode 100644
index e0fa40dc..00000000
--- a/apps/docs/list-memories/examples/basic.mdx
+++ /dev/null
@@ -1,87 +0,0 @@
----
-title: "Basic Listing"
-description: "Simple memory retrieval across languages"
----
-
-Simple memory retrieval examples for getting started with the list memories endpoint.
-
-## Basic Usage
-
-
-
-- supermemory [docs] -
- -- Meet the memory API for the AI era — scalable, powerful, affordable, and production-ready. -
- -
-
- - ```pip install supermemory``` - - ```npm install supermemory``` -
-
- );
-}
-```
-
-## Highlighting Search Results
-
-```tsx
-'use client';
-
-import { MemoryGraph } from '@supermemory/memory-graph';
-import { useState } from 'react';
-
-export default function SearchableGraph() {
- const [documents, setDocuments] = useState([]);
- const [searchResults, setSearchResults] = useState
- 0}
- />
-
- );
-}
-```
-
-## Controlled Space Selection
-
-Control space filtering from outside the component.
-
-```tsx
-'use client';
-
-import { MemoryGraph } from '@supermemory/memory-graph';
-import { useState } from 'react';
-
-export default function ControlledSpaceGraph() {
- const [documents, setDocuments] = useState([]);
- const [selectedSpace, setSelectedSpace] = useState('all');
-
- // Extract available spaces from documents
- const spaces = Array.from(
- new Set(
- documents.flatMap(doc =>
- doc.memoryEntries.map(m => m.spaceId || 'default')
- )
- )
- );
-
- return (
-
- handleSearch(e.target.value)}
- style={{
- padding: '8px 12px',
- borderRadius: 8,
- border: '1px solid #333',
- background: '#1a1a1a',
- color: 'white',
- }}
- />
-
-
-
-
- );
-}
-```
-
-## Embedded Widget
-
-Use the consumer variant for embedded views with custom styling.
-
-```tsx
-'use client';
-
-import { MemoryGraph } from '@supermemory/memory-graph';
-
-export default function EmbeddedGraph({ documents }) {
- return (
-
-
-
- Filters
- - - - -
-
-
-
- );
-}
-```
-
-## With Loading States
-
-```tsx
-'use client';
-
-import { MemoryGraph } from '@supermemory/memory-graph';
-import { useEffect, useState } from 'react';
-
-export default function LoadingGraph() {
- const [documents, setDocuments] = useState([]);
- const [isLoading, setIsLoading] = useState(true);
- const [error, setError] = useState
-
- No memories to display
-
-
-
-
- );
-}
-```
-
-## React Server Component
-
-```tsx
-// Next.js App Router with Server Component
-import { MemoryGraphClient } from './memory-graph-client';
-
-async function getGraphData() {
- const res = await fetch('https://api.supermemory.ai/v3/documents/documents', {
- method: 'POST',
- headers: {
- 'Authorization': `Bearer ${process.env.SUPERMEMORY_API_KEY}`,
- 'Content-Type': 'application/json',
- },
- body: JSON.stringify({
- page: 1,
- limit: 500,
- sort: 'createdAt',
- order: 'desc',
- }),
- cache: 'no-store', // or use revalidation
- });
-
- return res.json();
-}
-
-export default async function GraphPage() {
- const data = await getGraphData();
-
- return
-
-
-
- Welcome to your Memory Graph
-Add some content to get started
- -
-
- );
-}
-```
-
-## Mobile-Responsive Layout
-
-```tsx
-'use client';
-
-import { MemoryGraph } from '@supermemory/memory-graph';
-import { useState, useEffect } from 'react';
-
-export default function ResponsiveGraph({ documents }) {
- const [isMobile, setIsMobile] = useState(false);
-
- useEffect(() => {
- const checkMobile = () => {
- setIsMobile(window.innerWidth < 768);
- };
-
- checkMobile();
- window.addEventListener('resize', checkMobile);
- return () => window.removeEventListener('resize', checkMobile);
- }, []);
-
- return (
-
-
- );
-}
-```
diff --git a/apps/docs/memory-graph/installation.mdx b/apps/docs/memory-graph/installation.mdx
deleted file mode 100644
index e3a0b2d4..00000000
--- a/apps/docs/memory-graph/installation.mdx
+++ /dev/null
@@ -1,28 +0,0 @@
----
-title: 'Installation'
-description: 'Install and set up the Memory Graph component'
----
-
-## Installation
-
-Install the package using your preferred package manager:
-
-```bash npm
-npm install @supermemory/memory-graph
-```
-
-## Requirements
-
-- **React**: 18.0.0 or higher
-- **react-dom**: 18.0.0 or higher
-
-## Next Steps
-
-
-
- );
-}
-```
-
-## Backend API Route
-
-Create an API route to fetch documents from Supermemory:
-
-
-
-No memories yet
-Add content to see your knowledge graph
-(LoCoMo, LongMemEval..)"] - P["Providers
(Supermemory, Mem0, Zep)"] - J["Judges
(GPT-4o, Claude..)"] - - B --> O[Orchestrator] - P --> O - J --> O - - O --> Pipeline - - subgraph Pipeline[" "] - direction LR - I[Ingest] --> IX[Indexing] --> S[Search] --> A[Answer] --> E[Evaluate] - end - - style B fill:#E0F2FE,stroke:#0369A1,color:#0C4A6E - style P fill:#E0F2FE,stroke:#0369A1,color:#0C4A6E - style J fill:#E0F2FE,stroke:#0369A1,color:#0C4A6E - style O fill:#0369A1,stroke:#0369A1,color:#fff - style I fill:#F1F5F9,stroke:#64748B,color:#334155 - style IX fill:#F1F5F9,stroke:#64748B,color:#334155 - style S fill:#F1F5F9,stroke:#64748B,color:#334155 - style A fill:#F1F5F9,stroke:#64748B,color:#334155 - style E fill:#F1F5F9,stroke:#64748B,color:#334155 -``` - -## Core Components - -| Component | Role | -|-----------|------| -| **Benchmarks** | Load test data and provide questions with ground truth answers | -| **Providers** | Memory services being evaluated (handle ingestion and search) | -| **Judges** | LLM-based evaluators that score answers against ground truth | - -See [Integrations](/memorybench/integrations) for all supported benchmarks, providers, and models. - -## Pipeline - -```mermaid -flowchart LR - A[Ingest] --> B[Index] --> C[Search] --> D[Answer] --> E[Evaluate] --> F[Report] - - style A fill:#E0F2FE,stroke:#0369A1,color:#0C4A6E - style B fill:#E0F2FE,stroke:#0369A1,color:#0C4A6E - style C fill:#E0F2FE,stroke:#0369A1,color:#0C4A6E - style D fill:#E0F2FE,stroke:#0369A1,color:#0C4A6E - style E fill:#E0F2FE,stroke:#0369A1,color:#0C4A6E - style F fill:#DCFCE7,stroke:#16A34A,color:#166534 -``` - -| Phase | What Happens | -|-------|--------------| -| **Ingest** | Load benchmark sessions → Push to provider | -| **Index** | Wait for provider indexing | -| **Search** | Query provider → Retrieve context | -| **Answer** | Build prompt → Generate answer via LLM | -| **Evaluate** | Compare to ground truth → Score via judge | -| **Report** | Aggregate scores → Output accuracy, latency, token metrics, and [MemScore](/memorybench/memscore) | - -Each phase checkpoints independently. Failed runs resume from last successful point. - -## Advanced Checkpointing - -Runs persist to `data/runs/{runId}/`: - -``` -data/runs/my-run/ -├── checkpoint.json # Run state and progress -├── results/ # Search results per question -└── report.json # Final report -``` - -Re-running same ID resumes. Use `--force` to restart. - -## File Structure - -``` -src/ -├── cli/commands/ # run, compare, test, serve, status... -├── orchestrator/phases/ # ingest, search, answer, evaluate, report -├── benchmarks/ -│ └──
- ```bun run src/index.ts serve``` -
-
-
-
-
-
-
-
-
- Free Tier
-100k tokens stored at no cost
-
-
- Standard Plan
-$20/month fixed cost after exceeding free tier
-
-
- Usage-Based
-Each thread includes 20k free tokens, then $1 per million tokens thereafter
-
-
-
-
-
- | - Feature - | -- Free - | -- Standard - | -
|---|---|---|
| - Tokens Stored - | -- 100k - | -- Unlimited - | -
| - Conversations - | -- 10 - | -- Unlimited - | -
+
+
+With supermemory, developers can provide perfect recall about their users to build AI agents that are more intelligent, more personalized, and more consistent.
+
+It is the [state of the art](https://supermemory.ai/research) across multiple different benchmarks, like LongMemEval and LoCoMo. It's also the best in a lot of independantly run benchmarks, like the [SWEContext](https://arxiv.org/pdf/2602.08316) bench.
+
+## How does it work? (at a glance)
+
+
+
+- You send Supermemory raw data in any format - text, files, and chats, or connect it to the data sources
+- Supermemory [intelligently indexes them](/concepts/how-it-works) using our user understanding model and builds a semantic understanding graph on top of an entity (e.g., a user, a document, a project, an organization). We call these entities `containerTag`
+- This knowledge is now traversed by the agent, and an automatic profile is built for it. The agent may now use it for memory operations or for retrieval.
+
+## Why add memory to your agent?
+
+Without memory, every session starts from zero. The model cannot know what the user preferred last week, which project they are on, or that a fact has changed since yesterday.
+
+**Memory** gives an agent durable understanding of *people and entities over time* — preferences, decisions, relationships, corrections. **Retrieval (RAG)** grounds answers in *documents and knowledge bases*. You usually want both.
+
+By adding memory to your agent, you can:
+
+- **Personalize** — remember preferences, roles, and history across sessions without stuffing the full chat log into every prompt
+- **Stay correct as facts change** — “I love Adidas” then “switching to Puma” should not leave both preferences equally true
+- **Ground answers** — pull the right policy, ticket, or doc when the question needs source material
+- **Ship multi-tenant products** — isolate each user or workspace so one customer’s memory never leaks into another’s
+
+You can think of memory as the always-on context a skilled teammate would carry — not a search box over raw logs.
+
+For the full category argument (vs DIY vectors, thin memory wrappers, pure RAG), see [Comparison](/overview/comparison) and [Memory vs RAG](/concepts/memory-vs-rag).
+
+## Why Supermemory?
+
+- **State of the art on long-horizon memory** — #1 on [LongMemEval](https://supermemory.ai/research), [LoCoMo](https://supermemory.ai/research), and [ConvoMem](https://supermemory.ai/research), plus independent benches like [SWEContext](https://arxiv.org/pdf/2602.08316)
+- **Memory is a graph, not a blob store** — facts [update, connect, and forget](/concepts/graph-memory) in real time; not nearest-neighbor chunks alone
+- **User profiles built in** — static + dynamic context the agent should [always know](/concepts/user-profiles), ~ready for the prompt
+- **Memory + SuperRAG in one engine** — personalize *and* ground on the same `containerTag` / context pool
+- **Every door, one store** — API, [MCP](/supermemory-mcp/mcp), plugins, [SMFS](/smfs/overview), connectors, and Company Brain share the same memories
+- **Multimodal by default** — text, chats, PDFs, images, video, code via [extractors](/concepts/content-types) and [connectors](/connectors/overview)
+- **Run it your way** — managed cloud or [self-host](/self-hosting/overview) as a single binary (including offline)
+
+
+
+metadata, categories, containerTags] - G --> H{Rerank?} - H -->|Yes| I[Apply Reranking] - H -->|No| J[Build Results with Chunks] - I --> J - J --> K[Return Documents + Chunks + Scores] -``` - -### Memory Search (`/v4/search`) Flow - -```mermaid -graph TD - A[Query Input] --> B[Query Rewriting + Embedding] - B --> C[Parallel Search Execution] - C --> D[Apply Filtering] - D --> E[Merge Results] - E --> F[Deduplication] - F --> G{Rerank?} - G -->|Yes| H[Apply Reranking] - G -->|No| I[Return Memories + Similarity] - H --> I -``` - -## Key Concepts You Need to Understand - -### 1. Thresholds (Sensitivity Control) - -Thresholds control result quality vs quantity: - -- **0.0** = Least sensitive (more results, lower quality) -- **1.0** = Most sensitive (fewer results, higher quality) - -```typescript -// Different threshold strategies -const broadSearch = await client.search.documents({ - q: "machine learning", - chunkThreshold: 0.2, // Return more chunks - documentThreshold: 0.1 // From more documents -}); - -const preciseSearch = await client.search.documents({ - q: "machine learning", - chunkThreshold: 0.8, // Only highly relevant chunks - documentThreshold: 0.7 // From closely matching documents -}); -``` - -### 2. Chunk Context vs Exact Matching - -By default, Supermemory returns chunks **with context** (surrounding text): - -```typescript -// Default: includes surrounding chunks for context -const contextualResults = await client.search.documents({ - q: "neural networks", - onlyMatchingChunks: false // Default -}); - -// Precise: only the exact matching text -const exactResults = await client.search.documents({ - q: "neural networks", - onlyMatchingChunks: true -}); -``` - -### 3. Query Rewriting & Reranking - -**Query Rewriting** (+400ms latency): -- Expands your query to find more relevant results -- "ML" becomes "machine learning artificial intelligence" -- Useful for abbreviations and domain-specific terms - -**Reranking**: -- Re-scores results using a different algorithm -- More accurate but slower -- Recommended for critical searches - -### 4. Container Tags vs Metadata Filters - -Two different filtering mechanisms: - -When to use container tags: - - The user understanding graph is built on top of container tags. **The graph is formed on top of container tags.** - - Container tags are used for organizational grouping and exact matching. - - They are useful for categorizing content and ensuring precise results. -When to use metadata filters: - - When you need flexible conditions beyond exact matches. - - Useful for filtering by attributes like date, author, or category. - -```typescript -// Container tags: Organizational grouping (exact array matching) -const userContent = await client.search.documents({ - q: "python tutorial", - containerTag "user_123" // Must match exactly -}); - -// Metadata filters: SQL-based queries (flexible conditions) -const filteredContent = await client.search.documents({ - q: "python tutorial", - filters: JSON.stringify({ - AND: [ - { key: "language", value: "python", negate: false }, - { key: "difficulty", value: "beginner", negate: false } - ] - }) -}); -``` diff --git a/apps/docs/search/parameters.mdx b/apps/docs/search/parameters.mdx deleted file mode 100644 index f9df18da..00000000 --- a/apps/docs/search/parameters.mdx +++ /dev/null @@ -1,264 +0,0 @@ ---- -title: "Search Parameters" -description: "Complete reference for all search parameters and their effects" ---- - - -Complete parameter reference for all three search endpoints: document search, memory search, and execute search. - -## Common Parameters - -These parameters work across all search endpoints: - -
+
+ {children}
+
+);
+
+export const JourneyStep = ({ number, title, children }) => (
+
+
+);
+
+export const JourneyItem = ({ icon, title, href }) => (
+
+ {icon && (
+
+ {number}
+
+ + {title} +
+
+ {children}
+
+
+
+);
+
+export const SlackThread = ({
+ type = "channel",
+ channel = "general",
+ private: isPrivate = false,
+ members,
+ dmWith,
+ maxHeight = "70vh",
+ children,
+}) => {
+ const composerLabel =
+ type === "dm"
+ ? `Message ${dmWith?.name || "someone"}`
+ : type === "thread"
+ ? "Reply..."
+ : `Message ${isPrivate ? "" : "#"}${channel.replace(/^#/, "")}`;
+
+ return (
+
+ {children}
+
+ {footer ? (
+ {footer}
+ ) : null}
+
+ {type === "thread" ? (
+
+ );
+};
+
+export const SlackReplyDivider = ({ count = 1 }) => (
+
+ Thread
+
+ ) : type === "dm" ? (
+
+
+
+
+
+
+
+ ) : (
+
+ 
+
+
+
+ {dmWith?.name || "Direct message"}
+
+
+
+ )}
+
+
+ {isPrivate ? (
+
+ ) : (
+
+ )}
+
+ {channel.replace(/^#/, "")}
+
+
+ {members ? (
+
+
+ {members}
+
+ ) : null}
+
+
+
+ {
+ if (!el || !maxHeight) return;
+ const wrapper = el.parentElement;
+ const aboveHint = wrapper?.querySelector('[data-hint="above"]');
+ const belowHint = wrapper?.querySelector('[data-hint="below"]');
+ const update = () => {
+ const hasAbove = el.scrollTop > 4;
+ const hasBelow = el.scrollHeight - el.scrollTop - el.clientHeight > 4;
+ if (aboveHint) aboveHint.style.opacity = hasAbove ? "1" : "0";
+ if (belowHint) belowHint.style.opacity = hasBelow ? "1" : "0";
+ };
+ update();
+ el.addEventListener("scroll", update);
+ requestAnimationFrame(update);
+ }}
+ className="overflow-y-auto bg-white dark:bg-[#1A1D21]"
+ style={maxHeight ? { maxHeight } : undefined}
+ >
+ {children}
+
+ {maxHeight ? (
+
+
+
+
+ ↑ More messages above
+
+
+ ) : null}
+ {maxHeight ? (
+
+
+
+
+ More messages below ↓
+
+
+ ) : null}
+
+
+
+ {composerLabel}
+
+
+
+ {count} {count === 1 ? "reply" : "replies"}
+
+
+
+);
+
+export const SlackMessage = ({
+ name,
+ self = false,
+ bot = false,
+ time,
+ color = "#611f69",
+ avatar,
+ badges,
+ reactions,
+ highlighted = false,
+ subtitle,
+ children,
+}) => {
+ const SELF_NAME = "Dhravya Shah";
+ const SELF_AVATAR = "/images/company-brain/dhravya-slack-icon.jpg";
+ const BOT_AVATAR = "/images/company-brain/supermemory-slack-icon.png";
+
+ const resolvedName = bot ? "supermemory" : self ? SELF_NAME : name || SELF_NAME;
+ const resolvedAvatar = bot ? BOT_AVATAR : self ? SELF_AVATAR : avatar;
+ const resolvedBadges = badges || (bot ? ["AGENT"] : null);
+
+ return (
+
+ 
+ ) : (
+
+ );
+};
+
+export const FileAttachment = ({ name, size }) => (
+
+ {["✅", "👀", "🙌", "😊", "↩️", "⋯"].map((icon, i) => (
+
+ {icon}
+
+ ))}
+
+ {resolvedAvatar ? (
+
+ {(resolvedName || "?").slice(0, 1).toUpperCase()}
+
+ )}
+
+
+
+
+ {resolvedName}
+
+ {subtitle ? (
+
+ ({subtitle})
+
+ ) : null}
+ {resolvedBadges
+ ? resolvedBadges.map((b) => (
+
+ {b}
+
+ ))
+ : null}
+ {time ? (
+ {time}
+ ) : null}
+
+
+ {children}
+
+ {reactions ? (
+
+ {reactions.map((r, i) => (
+
+ {r.emoji}
+ {r.count}
+
+ ))}
+
+ ) : null}
+
+
+
+);
+
+export const AgentLink = ({ href, children }) => (
+
+ {children}
+
+);
diff --git a/apps/docs/supermemory-mcp/claude-desktop.mdx b/apps/docs/supermemory-mcp/claude-desktop.mdx
index 837945a8..802fb43f 100644
--- a/apps/docs/supermemory-mcp/claude-desktop.mdx
+++ b/apps/docs/supermemory-mcp/claude-desktop.mdx
@@ -1,64 +1,46 @@
---
title: "Claude Desktop"
-description: "Manual setup for supermemory MCP in Claude Desktop with step-by-step screenshots"
+description: "Connect Supermemory MCP in Claude via Settings → Connectors"
icon: "monitor"
sidebarTitle: "Claude Desktop"
---
-This guide walks through the **manual** install for [Claude Desktop](https://claude.ai/download): edit `claude_desktop_config.json`, add the supermemory server, then finish in **Connectors**. For a one-line CLI install instead, see [Setup and Usage](/supermemory-mcp/setup).
+This guide walks through adding Supermemory as a **custom connector** in [Claude](https://claude.ai) (Desktop or web): open **Settings → Connectors**, add the MCP URL, connect, and authorize. For other clients and API-key auth, see [Setup and Usage](/supermemory-mcp/setup).
-
+
+ {name}
+ {size ? (
+ {size}
+ ) : null}
+ - Optional: scope installs to a project. Then copy and - run the command in your terminal. + Add this remote MCP server URL in your client. + Optional: scope to a project for the config snippet.
+
+
+
- Requires Node/npx. OAuth runs when the CLI prompts - you. + Paste the URL or config into your client. OAuth + starts when you connect.
- Run this command in your terminal. It installs the MCP - for {clients[selectedKey]} and starts OAuth when - needed. + Add this remote MCP server URL in{" "} + {clients[selectedKey]}. Your client will prompt for + OAuth when you connect.
+ Or merge this into your client's MCP config: +
+