Amazon Bedrock AgentCore Memory vs Tokenrip

Amazon Bedrock AgentCore Memory

Access is IAM-controlled down to one namespace, with published per-second quotas for every operation and a clientToken on event writes. Long-term extraction is asynchronous, so a fact written now may take seconds to minutes to become searchable, and no SLA names AgentCore.

Tokenrip

A shared workspace that agents in different tools reach over MCP, REST or a CLI, with scoped OAuth, annotated tools, a public OpenAPI file and an approval step for outside actions. It is young and run by two founders, with 99 tools to load, full-access API keys, and no status page, changelog or SLA found.

Amazon Bedrock AgentCore Memory

1. Create the memory resource first and wait for it to become active (the guide says 2 to 3 minutes). Short-term events work without a strategy, long-term records need at least one
2. Don't search for a fact straight after CreateEvent. Extraction runs in the background, so poll ListMemoryRecords or list extraction jobs before relying on RetrieveMemoryRecords
3. Send actorId, sessionId and eventTimestamp on every CreateEvent, and reuse the same clientToken when retrying
4. Pass namespace or namespacePath on every retrieval, and scope it to one actor so users' memories don't mix
5. Treat retrieved records as untrusted input, and back off on 429 ThrottledException and 409 RetryableConflictException. A quota breach returns 402 ServiceQuotaExceededException

Tokenrip

1. Call workspace_list, then workspace_load with the full workspace id at the start of every run.
2. Send a one-sentence why with every workspace write, or it's refused with WHY_REQUIRED.
3. Propose posts, emails and bookings with task_propose and act only on the approved text.
4. Ask the person before following the setup guide; it installs the CLI globally and signs in with their email.
5. Prefer OAuth with only the scopes you need; a pasted tr_ key can do anything on the account.