Agent Memory Server (deprecated)
Deprecated. The opensource-agent-memory backend is no longer maintained. Migrate existing deployments to Redis Agent Memory.
Deprecated. Do not use for new work.
The opensource-agent-memory backend and the
Agent Memory Server it targets
are deprecated and are not maintained going forward. Its capabilities are not
being carried forward, and support for it will be removed from adk-redis.
New agents should use
Redis Agent Memory
with backend="redis-agent-memory", on
Redis Cloud or
self-managed
on your own Kubernetes cluster.
This page exists only to help existing deployments migrate.
What it was
Agent Memory Server is a separate open source memory server, documented in
its own repository. It is not
Redis Agent Memory and does not speak the
Agent Memory Data Plane API.
adk-redis reached it with backend="opensource-agent-memory", an
api_base_url pointing at the server, and the agent-memory-client>=0.14.0
dependency.
A handful of capabilities existed only on this backend: auto-summarization,
extraction strategies, recency-boosted search, and an MCP endpoint. They are
configured through model_name, context_window_max, extraction_strategy,
extraction_strategy_config, and recency_boost, none of which have any effect
with redis-agent-memory. See the
Agent Memory Server repository
for the server's own setup and reference material.
backend="redis-agent-memory" just
like Redis Cloud. You choose a deployment with api_base_url, not with
backend.Migrate to Redis Agent Memory
- Provision a Redis Agent Memory store, on Redis Cloud or self-managed. Either gives you a Data Plane endpoint, an API key, and a store ID.
- Change
backendfromopensource-agent-memorytoredis-agent-memoryon every service and tool config, or drop the field, since it is the default. - Point
api_base_urlat the Data Plane endpoint, and addapi_keyandstore_id. - Remove the backend-only settings listed above. They are silently inert on
redis-agent-memory. - Replace any MCP memory wiring with the REST memory tools, which work the same way on both backends.
- Drop
agent-memory-clientfrom your dependencies. Thememoryextra requiresredis-agent-memory>=0.2.0.
# Before: deprecated backend
config = RedisSessionMemoryServiceConfig(
backend="opensource-agent-memory",
api_base_url="http://localhost:8088",
default_namespace="my_app",
model_name="gemini-2.5-flash",
context_window_max=8000,
)
# After: Redis Agent Memory, on Redis Cloud or self-managed
config = RedisSessionMemoryServiceConfig(
backend="redis-agent-memory",
api_base_url="https://your-endpoint.redis.io",
api_key="your-api-key",
store_id="your-store-id",
default_namespace="my_app",
)
Changing configuration does not copy existing memories. Plan for a re-extraction window, or run both backends while long-term memory repopulates.
Examples still on this backend
Three examples in the adk-redis repository have not yet moved: simple_redis_memory, travel_agent_memory_hybrid, and fitness_coach_mcp (which uses the MCP endpoint this backend alone provides).
For a supported starting point, use
managed_memory_quickstart.
travel_agent_memory_tools
switches backends with REDIS_MEMORY_BACKEND, so it already runs on
redis-agent-memory.
More info
- Redis Agent Memory: the supported backend
- Self-managed Agent Memory: run Agent Memory on your own Kubernetes cluster
- Agent Memory Server on GitHub: the deprecated server's own documentation