docs: add hybrid and keyword search references across documentation

README.md

@@ -13,7 +13,7 @@ A memory layer for AI agents.
 - **Dual Interface**: REST API and Model Context Protocol (MCP) server
 - **Two-Tier Memory**: Working memory (session-scoped) and long-term memory (persistent)
 - **Configurable Memory Strategies**: Customize how memories are extracted (discrete, summary, preferences, custom)
-- **Semantic Search**: Vector-based similarity search with metadata filtering
+- **Semantic, Keyword & Hybrid Search**: Vector-based similarity, full-text keyword, and combined hybrid search with metadata filtering
 - **Flexible Backends**: Pluggable memory vector database factory system
 - **Multi-Provider LLM Support**: OpenAI, Anthropic, AWS Bedrock, Ollama, Azure, Gemini via [LiteLLM](https://docs.litellm.ai/)
 - **AI Integration**: Automatic topic extraction, entity recognition, and conversation summarization
@@ -268,10 +268,10 @@ See **[LLM Providers](https://redis.github.io/agent-memory-server/llm-providers/
 ```
 Working Memory (Session-scoped)  →  Long-term Memory (Persistent)
     ↓                                      ↓
-- Messages                         - Semantic search
-- Structured memories              - Topic modeling
-- Summary of past messages         - Entity recognition
-- Metadata                         - Deduplication
+|- Messages                        - Semantic, keyword & hybrid search
+|- Structured memories             - Topic modeling
+|- Summary of past messages        - Entity recognition
+|- Metadata                        - Deduplication
 ```
 
 ## Use Cases

agent-memory-client/README.md

@@ -165,7 +165,7 @@ working_memory = WorkingMemory(
 response = await client.put_working_memory("user-session-123", working_memory)
 
 # Retrieve working memory
-memory = await client.get_working_memory("user-session-123")
+created, memory = await client.get_or_create_working_memory("user-session-123")
 
 # Convenience method for data storage
 await client.set_working_memory_data(
@@ -201,6 +201,21 @@ results = await client.search_long_term_memory(
     user_id=UserId(eq="user-123"),
     limit=20
 )
+
+# Keyword search - full-text matching
+results = await client.search_long_term_memory(
+    text="science fiction",
+    search_mode="keyword",
+    limit=20
+)
+
+# Hybrid search - combines semantic and keyword matching
+results = await client.search_long_term_memory(
+    text="science fiction",
+    search_mode="hybrid",
+    hybrid_alpha=0.7,  # 0.0=keyword, 1.0=semantic
+    limit=20
+)
 ```
 
 ## Enhanced Features
@@ -328,14 +343,15 @@ results = await client.search_long_term_memory(
 from agent_memory_client.exceptions import (
     MemoryClientError,
     MemoryValidationError,
-    MemoryNotFoundError,
     MemoryServerError
 )
 
 try:
-    memory = await client.get_working_memory("nonexistent-session")
-except MemoryNotFoundError:
-    print("Session not found")
+    created, memory = await client.get_or_create_working_memory("my-session")
+    if created:
+        print("New session created")
+except MemoryValidationError as e:
+    print(f"Validation error: {e}")
 except MemoryServerError as e:
     print(f"Server error {e.status_code}: {e}")
 except MemoryClientError as e:

agent-memory-client/agent-memory-client-js/README.md

@@ -90,14 +90,29 @@ await client.createLongTermMemory([
   },
 ]);
 
-// Search with filters
+// Search with filters (default: semantic search)
 const results = await client.searchLongTermMemory({
   text: "science fiction",
   topics: new Topics({ any: ["books", "entertainment"] }),
   userId: new UserId({ eq: "user-123" }),
   limit: 20,
 });
 
+// Keyword search - full-text matching
+const keywordResults = await client.searchLongTermMemory({
+  text: "science fiction",
+  searchMode: "keyword",
+  limit: 20,
+});
+
+// Hybrid search - combines semantic and keyword matching
+const hybridResults = await client.searchLongTermMemory({
+  text: "science fiction",
+  searchMode: "hybrid",
+  hybridAlpha: 0.7, // 0.0=keyword, 1.0=semantic
+  limit: 20,
+});
+
 // Get by ID
 const memory = await client.getLongTermMemory("memory-id");
 

docs/README.md

@@ -75,7 +75,7 @@ For contributors and advanced users:
 
 | Feature | REST API | MCP Server | CLI | Documentation |
 |---------|----------|------------|-----|---------------|
-| **Memory Search** | ✅ `/v1/long-term-memory/search` | ✅ `search_long_term_memory` | ❌ | [REST API](api.md), [MCP](mcp.md) |
+| **Memory Search** (semantic, keyword, hybrid) | ✅ `/v1/long-term-memory/search` | ✅ `search_long_term_memory` | ✅ `agent-memory search` | [REST API](api.md), [MCP](mcp.md), [CLI](cli.md) |
 | **Memory Editing** | ✅ `PATCH /v1/long-term-memory/{id}` | ✅ `edit_long_term_memory` | ❌ | [Memory Editing](memory-lifecycle.md#memory-editing) |
 | **Query Optimization** | ✅ `optimize_query` param | ✅ `optimize_query` param | ❌ | [Query Optimization](query-optimization.md) |
 | **Recency Boost** | ✅ Default enabled | ✅ Available | ❌ | [Recency Boost](recency-boost.md) |

docs/agent-examples.md

@@ -93,7 +93,7 @@ A comprehensive travel assistant that demonstrates the most complete integration
 - **Automatic Tool Discovery**: Uses `MemoryAPIClient.get_all_memory_tool_schemas()` to automatically discover and integrate all available memory tools
 - **Unified Tool Resolution**: Leverages `client.resolve_tool_call()` to handle all memory tool calls uniformly across different LLM providers
 - **Working Memory Management**: Session-based conversation state and structured memory storage
-- **Long-term Memory**: Persistent memory storage and semantic search capabilities
+- **Long-term Memory**: Persistent memory storage with semantic, keyword, and hybrid search capabilities
 - **Optional Web Search**: Cached web search using Tavily API with Redis caching
 
 ### Available Tools
@@ -402,7 +402,7 @@ from agent_memory_client import create_memory_client
 client = await create_memory_client(base_url="http://localhost:8000")
 
 # Get only the 3 most recent messages
-memory = await client.get_working_memory(
+_created, memory = await client.get_or_create_working_memory(
     session_id="my-session",
     namespace="demo",
     context_window_max=3

docs/index.md

@@ -38,7 +38,7 @@ Transform your AI agents from goldfish 🐠 into elephants 🐘 with Redis-power
 Redis Agent Memory Server is a production-ready memory system for AI agents and applications that:
 
 - **🧠 Remembers everything**: Stores conversation history, user preferences, and important facts across sessions
-- **🔍 Finds relevant context**: Uses semantic search to surface the right information at the right time
+- **🔍 Finds relevant context**: Uses semantic, keyword, and hybrid search to surface the right information at the right time
 - **📈 Gets smarter over time**: Automatically extracts, organizes, and deduplicates memories from interactions
 - **🔌 Works with any AI model**: REST API and MCP interfaces compatible with OpenAI, Anthropic, and others
 - **🌐 Multi-provider support**: Use [100+ LLM providers](llm-providers.md) via LiteLLM (OpenAI, Anthropic, AWS Bedrock, Ollama, Azure, Gemini, and more)
@@ -95,11 +95,11 @@ print(f"Found: {results.memories[0].text}")
 
 !!! success "Long-Term Memory (Persistent)"
     - User preferences, facts, and important information
-    - Semantic search with vector embeddings
+    - Flexible search: semantic (vector embeddings), keyword (full-text), and hybrid (combined)
     - Advanced filtering by time, topics, entities, users
 
 ### 🔍 Intelligent Search
-- **Semantic similarity**: Find memories by meaning, not just keywords
+- **Multiple search modes**: Semantic (vector similarity), keyword (full-text), and hybrid (combined) search
 - **Advanced filters**: Search by user, session, time, topics, entities
 - **Query optimization**: AI-powered query refinement for better results
 - **Recency boost**: Time-aware ranking that surfaces relevant recent information

docs/java-sdk.md

@@ -144,6 +144,21 @@ MemoryRecordResults results = client.longTermMemory().searchLongTermMemories(req
 // Simple text search
 MemoryRecordResults simpleResults = client.longTermMemory()
     .searchLongTermMemories("user preferences");
+
+// Keyword search - full-text matching
+SearchRequest keywordRequest = SearchRequest.builder()
+    .text("TechCorp engineer")
+    .searchMode("keyword")
+    .limit(10)
+    .build();
+
+// Hybrid search - combines semantic and keyword matching
+SearchRequest hybridRequest = SearchRequest.builder()
+    .text("user preferences")
+    .searchMode("hybrid")
+    .hybridAlpha(0.7)  // 0.0=keyword, 1.0=semantic
+    .limit(10)
+    .build();
 ```
 
 ### Get, Edit, and Delete

docs/long-term-memory.md

@@ -4,24 +4,24 @@ Long-term memory is **persistent**, **cross-session** storage designed for knowl
 
 ## Overview
 
-Long-term memory provides persistent storage that survives server restarts and session expiration. It's optimized for semantic search, deduplication, and rich metadata to enable intelligent retrieval of relevant information.
+Long-term memory provides persistent storage that survives server restarts and session expiration. It's optimized for semantic, keyword, and hybrid search, deduplication, and rich metadata to enable intelligent retrieval of relevant information.
 
 | Feature | Details |
 |---------|---------|
 | **Scope** | Cross-session, persistent |
 | **Lifespan** | Permanent until manually deleted |
-| **Storage** | Redis with vector indexing |
-| **Search** | Semantic vector search |
+| **Storage** | Redis with vector and full-text indexing |
+| **Search** | Semantic, keyword, and hybrid search |
 | **Capacity** | Unlimited (with compaction) |
 | **Use Case** | Knowledge base, user preferences |
-| **Indexing** | Vector embeddings + metadata |
+| **Indexing** | Vector embeddings + full-text index + metadata |
 | **Deduplication** | Hash-based and semantic |
 
 ## Characteristics
 
 - **Cross-Session**: Accessible from any session
 - **Persistent**: Survives server restarts and session expiration
-- **Vector Indexed**: Semantic search with configurable embeddings (OpenAI, Bedrock, Ollama, and more via [LiteLLM](llm-providers.md))
+- **Multi-Modal Search**: Semantic (vector), keyword (BM25 full-text), and hybrid search — configurable embeddings (OpenAI, Bedrock, Ollama, and more via [LiteLLM](llm-providers.md))
 - **Deduplication**: Automatic hash-based and semantic deduplication
 - **Rich Metadata**: Topics, entities, timestamps, memory types
 - **Compaction**: Automatic cleanup and merging of duplicates
@@ -126,17 +126,38 @@ POST /v1/long-term-memory/search
 
 ## Search Capabilities
 
-Long-term memory provides powerful search features:
+Long-term memory supports three search modes: **semantic** (vector similarity), **keyword** (full-text matching), and **hybrid** (combined).
 
-### Semantic Vector Search
+### Semantic Search (Default)
 ```json
 {
   "text": "python programming help",
+  "search_mode": "semantic",
   "limit": 10,
   "distance_threshold": 0.8
 }
 ```
 
+### Keyword Search
+```json
+{
+  "text": "TechCorp engineer",
+  "search_mode": "keyword",
+  "limit": 10
+}
+```
+
+### Hybrid Search
+Combines vector similarity with full-text keyword matching. Use `hybrid_alpha` to control the balance (0.0 = pure keyword, 1.0 = pure semantic, default 0.7).
+```json
+{
+  "text": "python programming help",
+  "search_mode": "hybrid",
+  "hybrid_alpha": 0.7,
+  "limit": 10
+}
+```
+
 ### Advanced Filtering
 ```json
 {

docs/quick-start.md

@@ -178,7 +178,7 @@ await memory_client.create_long_term_memory([
 
 ## Step 7: Search Your Memories
 
-Search across all stored memories with semantic similarity:
+Search across all stored memories using semantic similarity, keyword matching, or hybrid search:
 
 ```python
 # Search for work-related information
@@ -331,7 +331,7 @@ You've just worked with both types of memory:
 - **Scope**: Cross-session, persistent
 - **Lifetime**: Permanent until deleted
 - **Use case**: User preferences, facts, knowledge
-- **Search**: Semantic vector search with advanced filtering
+- **Search**: Semantic, keyword, and hybrid search with advanced filtering
 
 ## Next Steps
 
@@ -537,7 +537,7 @@ redis-cli -h localhost -p 6379
 
 You now have a working AI agent memory system! Your memories will:
 - ✅ Persist across sessions
-- ✅ Be searchable with semantic similarity
+- ✅ Be searchable with semantic, keyword, or hybrid search
 - ✅ Automatically extract context from conversations
 - ✅ Provide relevant context to AI responses
 

docs/typescript-sdk.md

@@ -106,12 +106,27 @@ import {
   MemoryType,
 } from "agent-memory-client";
 
-// Basic search
+// Basic semantic search (default)
 const results = await client.searchLongTermMemory({
   text: "user preferences",
   limit: 10,
 });
 
+// Keyword search - full-text matching
+const keywordResults = await client.searchLongTermMemory({
+  text: "TechCorp engineer",
+  searchMode: "keyword",
+  limit: 10,
+});
+
+// Hybrid search - combines semantic and keyword matching
+const hybridResults = await client.searchLongTermMemory({
+  text: "user preferences",
+  searchMode: "hybrid",
+  hybridAlpha: 0.7, // 0.0=keyword, 1.0=semantic
+  limit: 10,
+});
+
 // With filters
 const filtered = await client.searchLongTermMemory({
   text: "programming languages",

docs/use-cases.md

@@ -701,7 +701,7 @@ guidance = await health.get_contextual_health_guidance(
 ### Search Optimization
 - **Enable recency boost**: For time-sensitive domains like support or health
 - **Use query optimization**: For natural language queries from end users
-- **Filter strategically**: Combine semantic search with metadata filters
+- **Filter strategically**: Combine semantic, keyword, or hybrid search with metadata filters
 
 ### Privacy and Security
 - **User isolation**: Always filter by user_id for personal data

examples/README.md

@@ -51,7 +51,7 @@ A comprehensive travel assistant that demonstrates:
 - **Automatic Tool Discovery**: Uses `MemoryAPIClient.get_all_memory_tool_schemas()` to automatically discover and integrate all available memory tools
 - **Unified Tool Resolution**: Leverages `client.resolve_tool_call()` to handle all memory tool calls uniformly across different LLM providers
 - **Working Memory Management**: Session-based conversation state and structured memory storage
-- **Long-term Memory**: Persistent memory storage and semantic search capabilities
+- **Long-term Memory**: Persistent memory storage with semantic, keyword, and hybrid search capabilities
 - **Optional Web Search**: Cached web search using Tavily API with Redis caching
 
 ### Available Tools