Highlights

• Simpler local dev: Add --no-worker flag to api and mcp commands. This enables a single-process mode without a Docket worker, using asyncio for background tasks.
• Smoother prompts when sessions are missing: memory_prompt now creates a temporary empty WorkingMemory if a session doesn’t exist, instead of failing.

What’s New

• --no-worker option for api and mcp CLI commands; MCP in stdio mode defaults to no-worker.
• HybridBackgroundTasks class to support dual-mode background work (Docket or FastAPI).

Documentation

• Rewrote Memory Lifecycle docs to reflect server-controlled lifecycle (Docket background tasks, best practices) and tightened language; renamed and linked Memory Integration Patterns; fixed URLs and a mkdocs.yml typo.

Upgrade Notes

• Local development: You can now run without a worker:

  agent-memory-server api --no-worker
  # or
  agent-memory-server mcp --no-worker

What's Changed

• Make compaction schedule configurable by @abrookins in #58
• Add configurable strategy for long-term memory extraction (thread summary, discrete memories, user preferences, custom prompt) by @abrookins in #59
• Update memory documentation patterns to use working memory sessions by @abrookins in #60
• Improve multi-entity contextual grounding in memory extraction by @abrookins in #57
• Change Docker Hub publishing to redislabs/agent-memory-server by @abrookins in #61
• Expand documentation and vector store factory tests by @abrookins in #49
• Docs fixes by @abrookins in #52
• Fix typo in MCP setup by @chrisguidry in #56

New Contributors

• @chrisguidry made their first contribution in #56

Full Changelog: server/v0.9.4...server/0.11.0

What's Changed

• Add query optimization for vector search with configurable models by @abrookins in #44
• Implement contextual grounding by @abrookins in #46
• Add forgetting mechanism and recency boost by @abrookins in #45
• Add memory editing API endpoint, MCP tool, and memory IDs in prompts by @abrookins in #47

Full Changelog: server/v0.9.4...server/v0.10.0

What's Changed

• Make OpenAI and Anthropic API base URLs configurable by @abrookins in #43
• Fix hash-based deduplication FT.AGGREGATE query execution by @abrookins in #41

Full Changelog: server/v0.9.3...server/v0.9.4

What's Changed

• Add remaining context percentage until auto-summarization to working memory endpoints by @abrookins in #38
• Fix authentication event loop corruption by converting get_current_user to async by @abrookins in #40

Full Changelog: server/v0.9.2...server/v0.9.3

What's Changed

• Token-based authentication by @abrookins in #35

Full Changelog: server/v0.9.1...server/v0.9.2

What's Changed

• Fix docker-compose file by @abrookins in #34

Full Changelog: server/v0.9.0...server/v0.9.1

Memory Evolution

• Working Memory (formerly Short-term Memory):

  • Renamed from "short-term memory" to "working memory" to better reflect its purpose
  • Enhanced with automatic promotion system that moves structured memories to long-term storage in background
  • Added support for arbitrary JSON data storage alongside memory structures
  • Improved automatic conversation summarization in working memory, based on token limits

• Long-term Memory Promotion:

  • Implemented seamless flow from working memory to long-term memory via background task processing
  • Agent only has to think about working memory, long-term memory is managed automatically (but can be managed manually, too)
  • Use any LangChain VectorStore subclass for long-term storage, defaults to RedisVectorStore
  • Structured memories are automatically promoted with vector embeddings and metadata indexing
  • Deduplication and compaction systems for long-term memory management
  • Background task worker system using for reliable, scalable memory processing

Client SDK and Tooling

• Working and long-term memory available as tools for LLM integration (LLM can choose to persist a long-term memory or search for long-term memories, etc.)
• Higher-level tools support sending in a user's input and getting back a context-enriched prompt, via /v1/memory/prompt endpoint
• Support for namespace isolation, user separation, and session management

Search and Retrieval

• Vector-based similarity search using OpenAI embeddings
• Rich filtering system by session, namespace, topics, entities, timestamps
• Hybrid search combining semantic similarity with metadata filtering
• RedisVL integration for high-performance vector operations with Redis

Enhanced Memory Classification:

• Semantic memories for facts and preferences
• Episodic memories for time-bound events with event dates (requires a timeframe)
• Message memories for long-term conversation records (optional)
• Automatic topic modeling and entity recognition either using BERTopic or a configured LLM
• Rich metadata extraction and indexing

Authentication and Security

• OAuth2/JWT Bearer token authentication with JWKS validation
• Multi-provider support (Auth0, AWS Cognito, Okta, Azure AD)
• Role-based access control using JWT claims
• Development mode with configurable auth bypass

Operational Features

• Comprehensive CLI Interface:
  • Commands for server management (api, mcp, task-worker)
  • Database operations (rebuild-index)
  • Background task scheduling and management
  • Health monitoring and diagnostics