Memory (MCP reference server) vs TencentDB Agent Memory

Memory (MCP reference server)

Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. read_graph returns everything and search_nodes every match.

TencentDB Agent Memory

A self-hosted team memory stack with layered recall, per-asset visibility and ACLs, documented HTTP APIs and frequent releases, 2.0.0 to 2.0.3 since August. The default deployment publishes its ports on all host interfaces with the core's bearer gate off, data-plane deletes trust a service-ID header, and the proxy's rate-limit and session admin routes have no authentication.

Memory (MCP reference server)

1. Set MEMORY_FILE_PATH to an absolute path. The default sits inside the npx cache
2. Use search_nodes or open_nodes instead of read_graph once the graph has more than a few hundred entities
3. Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31
4. Create both entities before create_relations. A missing endpoint fails the whole batch
5. Keep observations short and factual. They come back verbatim in every later read

TencentDB Agent Memory

1. Set MEMORY_CORE_GATEWAY_API_KEY, KNOWLEDGE_SERVICE_KEY and a non-default admin key before exposing ports 8420, 8424, 8096 or 8125 beyond the host
2. In headless runs send x-team-id, x-agent-id and x-task-id headers to the proxy. Without all three it falls back to an interactive picker and skips memory
3. Expect every proxied turn to be stored. The proxy records upstream messages and model replies to Memory Core, and injected memory lands in your system prompt
4. Check data.valid on /v3/meta/auth/verify and data.isError on /v3/tools/call. Both can fail inside a success envelope
5. Retry /v3/session/add only on 500, 503 or a network error. The API reference says it isn't idempotent and writes a new object each call