0.12.5

What's Changed

Enhancements

• Add long_term_memory_strategy support to client and MCP by @abrookins in #82
• Store working memory as JSON instead of string data by @fcenedes in #95
• Allow token add to accept pre-generated tokens by @abrookins in #88
• Add JSON output for token CLI token commands by @abrookins in #86
• Support AWS Bedrock Embedding Models and LLM Models by @f4roukb in #94
• Add GHA workflow to publish server to PyPI by @abrookins in #98

Docs

• Document Docker image locations and default to development mode by @abrookins in #77
• Update Memory types link to a working page. by @AllieRays in #84
• Document token CLI JSON output and CI/Terraform bootstrapping by @abrookins in #93

Fixes

• Fix CLI token show command to exit with code 1 on errors in JSON mode by @Copilot in #90
• Fix MCP search_long_term_memory missing background_tasks parameter by @abrookins in #99

New Contributors

• @AllieRays made their first contribution in #84
• @f4roukb made their first contribution in #94
• @fcenedes made their first contribution in #95

Full Changelog: server/v0.12.3...server/v0.12.5

0.12.3

What's Changed

• Fix background task execution in --no-worker mode by using HybridBackgroundTasks directly as type annotation instead of Depends(get_background_tasks)
• Add deduplicate parameter to create_long_term_memory endpoint with default true
• Pass background_tasks parameter through search_long_term_memory and memory_prompt endpoints
• Update MCP server to create HybridBackgroundTasks instance for memory_prompt calls
• Update tests to patch actual functions instead of BackgroundTasks class
• Add test to verify tasks run inline in --no-worker mode

Full Changelog: server/v0.12.2...server/v0.12.3

0.12.2

What's New

• Reconstruct working memory messages from long-term storage by @abrookins in #68
• Add LangChain integration with automatic tool conversion by @abrookins in #73

Bug Fixes

• Calculating remaining context works better now by @abrookins in #68
• Client error handling by @abrookins in #72

Misc.

• Defaults change: Turn off query optimization by default by @abrookins in #68

Full Changelog: server/v0.12.1...server/v0.12.2

0.12.1

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

0.11.0

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

0.10.0

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

0.9.4

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

0.9.3

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

0.9.2

What's Changed

• Token-based authentication by @abrookins in #35

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

0.9.1

What's Changed

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

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