Amazon Bedrock AgentCore
Welcome to the Amazon Bedrock AgentCore Data Plane API reference. Data Plane actions process and handle data or workloads within Amazon Web Services services.
Fork copies the collection into your workspace, without the publisher's secrets, so you can add your own key and send requests. Star saves it to your starred APIs (Account › Marketplace) and helps others find it.
Overview
Welcome to the Amazon Bedrock AgentCore Data Plane API reference. Data Plane actions process and handle data or workloads within Amazon Web Services services.
Endpoints 68
Memory
- POSTBatch create memory records
/memories/:memoryId/memoryRecords/batchCreateCreates multiple memory records in a single batch operation for the specified memory with custom content. - POSTBatch delete memory records
/memories/:memoryId/memoryRecords/batchDeleteDeletes multiple memory records in a single batch operation from the specified memory. - POSTBatch update memory records
/memories/:memoryId/memoryRecords/batchUpdateUpdates multiple memory records with custom content in a single batch operation within the specified memory. - POSTCreate event
/memories/:memoryId/eventsCreates an event in an AgentCore Memory resource. Events represent interactions or activities that occur within a session and are associated with specific… - GETGet event
/memories/:memoryId/actor/:actorId/sessions/:sessionId/events/:eventIdRetrieves information about a specific event in an AgentCore Memory resource. To use this operation, you must have the bedrock-agentcore:GetEvent permission. - DELETEDelete event
/memories/:memoryId/actor/:actorId/sessions/:sessionId/events/:eventIdDeletes an event from an AgentCore Memory resource. When you delete an event, it is permanently removed. To use this operation, you must have the… - DELETEDelete memory record
/memories/:memoryId/memoryRecords/:memoryRecordId?namespace=stringDeletes a memory record from an AgentCore Memory resource. When you delete a memory record, it is permanently removed. To use this operation, you must have… - GETGet memory record
/memories/:memoryId/memoryRecord/:memoryRecordId?namespace=stringRetrieves a specific memory record from an AgentCore Memory resource. To use this operation, you must have the bedrock-agentcore:GetMemoryRecord permission. - POSTIngest data
/memories/:memoryId/ingestSubmits content directly for ingestion to generate long-term memory records in a AgentCore Memory resource. To use this operation, you must have the… - POSTList actors
/memories/:memoryId/actorsLists all actors in an AgentCore Memory resource. We recommend using pagination to ensure that the operation returns quickly and successfully. To use this… - POSTList events
/memories/:memoryId/actor/:actorId/sessions/:sessionIdLists events in an AgentCore Memory resource based on specified criteria. We recommend using pagination to ensure that the operation returns quickly and… - POSTList memory extraction jobs
/memories/:memoryId/extractionJobsLists all long-term memory extraction jobs that are eligible to be started with optional filtering. To use this operation, you must have the… - POSTList memory records
/memories/:memoryId/memoryRecordsLists memory records in an AgentCore Memory resource based on specified criteria. We recommend using pagination to ensure that the operation returns quickly… - POSTList sessions
/memories/:memoryId/actor/:actorId/sessionsLists sessions in an AgentCore Memory resource based on specified criteria. We recommend using pagination to ensure that the operation returns quickly and… - POSTRetrieve memory records
/memories/:memoryId/retrieveSearches for and retrieves memory records from an AgentCore Memory resource based on specified search criteria. We recommend using pagination to ensure that… - POSTStart memory extraction job
/memories/:memoryId/extractionJobs/startStarts a memory extraction job that processes events that failed extraction previously in an AgentCore Memory resource and produces structured memory records.…
Evaluation
- GETList aB tests
/ab-tests?maxResults=0&nextToken=stringLists all A/B tests in the account. - POSTCreate aB test
/ab-testsCreates an A/B test for comparing agent configurations. A/B tests split traffic between a control variant and a treatment variant through a gateway, then… - GETGet aB test
/ab-tests/:abTestIdRetrieves detailed information about an A/B test, including its configuration, status, and statistical results. - PUTUpdate aB test
/ab-tests/:abTestIdUpdates an A/B test's configuration, including variants, traffic allocation, evaluation settings, or execution status. - DELETEDelete aB test
/ab-tests/:abTestIdDeletes an A/B test and its associated gateway rules. - GETGet batch evaluation
/evaluations/batch-evaluate/:batchEvaluationIdRetrieves detailed information about a batch evaluation, including its status, configuration, results, and any error details. - DELETEDelete batch evaluation
/evaluations/batch-evaluate/:batchEvaluationIdDeletes a batch evaluation and its associated results. - GETGet recommendation
/recommendations/:recommendationIdRetrieves detailed information about a recommendation, including its configuration, status, and results. - DELETEDelete recommendation
/recommendations/:recommendationIdDeletes a recommendation and its associated results. - POSTEvaluate
/evaluations/evaluate/:evaluatorIdPerforms on-demand evaluation of agent traces using a specified evaluator. This synchronous API accepts traces in OpenTelemetry format and returns immediate… - GETList batch evaluations
/evaluations/batch-evaluate?maxResults=0&nextToken=stringLists all batch evaluations in the account, providing summary information about each evaluation's status and configuration. - POSTStart batch evaluation
/evaluations/batch-evaluateStarts a batch evaluation job that evaluates agent performance across multiple sessions. Batch evaluations pull agent traces from CloudWatch Logs or an… - GETList recommendations
/recommendations?maxResults=0&nextToken=string&status=stringLists all recommendations in the account, with optional filtering by status. - POSTStart recommendation
/recommendationsStarts a recommendation job that analyzes agent traces and generates optimization suggestions for system prompts or tool descriptions to improve agent… - POSTStop batch evaluation
/evaluations/batch-evaluate/:batchEvaluationId/stopStops a running batch evaluation. Sessions that have already been evaluated retain their results.
Payment instrument
- POSTCreate payment instrument
/payments/createPaymentInstrumentCreate a new payment instrument for a connector. - POSTDelete payment instrument
/payments/deletePaymentInstrumentDeletes a payment instrument. This is a soft delete operation that preserves the record for audit and compliance purposes. - POSTGet payment instrument
/payments/getPaymentInstrumentGet a payment instrument by ID. - POSTGet payment instrument balance
/payments/getPaymentInstrumentBalanceGet the balance of a payment instrument. - POSTList payment instruments
/payments/listPaymentInstrumentsList payment instruments for a manager.
Payment session
- POSTCreate payment session
/payments/createPaymentSessionCreate a new payment session. - POSTDelete payment session
/payments/deletePaymentSessionDeletes a payment session. This permanently removes the payment session record. - POSTGet payment session
/payments/getPaymentSessionGet a payment session. - POSTList payment sessions
/payments/listPaymentSessionsList payment sessions.
Capacity provider
- DELETEDelete capacity provider session
/capacity-providers/:capacityProviderId/sessions/:sessionIdDeletes a session associated with a capacity provider in Amazon Bedrock AgentCore and makes the session unavailable for further use. To delete a capacity…
Agentic
- GETGet agent card
/runtimes/:agentRuntimeArn/invocations/.well-known/agent-card.json?qualifier=stringRetrieves the A2A agent card associated with an AgentCore Runtime agent. - POSTInvoke agent runtime
/runtimes/:agentRuntimeArn/invocations?qualifier=string&accountId=stringSends a request to an agent or tool hosted in an Amazon Bedrock AgentCore Runtime and receives responses in real-time. To invoke an agent, you can specify… - POSTInvoke agent runtime command
/runtimes/:agentRuntimeArn/commands?qualifier=string&accountId=stringExecutes a command in a runtime session container and streams the output back to the caller. This operation allows you to run shell commands within the agent… - POSTStop runtime session
/runtimes/:agentRuntimeArn/stopruntimesession?qualifier=stringStops a session that is running in an running AgentCore Runtime agent.
Browser session
- GETGet browser session
/browsers/:browserIdentifier/sessions/get?sessionId=stringRetrieves detailed information about a specific browser session in Amazon Bedrock AgentCore. This operation returns the session's configuration, current… - POSTInvoke browser
/browsers/:browserIdentifier/sessions/invokeInvokes an operating system-level action on a browser session in Amazon Bedrock AgentCore. This operation provides direct OS-level control over browser… - POSTList browser sessions
/browsers/:browserIdentifier/sessions/listRetrieves a list of browser sessions in Amazon Bedrock AgentCore that match the specified criteria. This operation returns summary information about each… - PUTStart browser session
/browsers/:browserIdentifier/sessions/startCreates and initializes a browser session in Amazon Bedrock AgentCore. The session enables agents to navigate and interact with web content, extract… - PUTStop browser session
/browsers/:browserIdentifier/sessions/stop?sessionId=stringTerminates an active browser session in Amazon Bedrock AgentCore. This operation stops the session, releases associated resources, and makes the session… - PUTUpdate browser stream
/browsers/:browserIdentifier/sessions/streams/update?sessionId=stringUpdates a browser stream. To use this operation, you must have permissions to perform the bedrock:UpdateBrowserStream action.
Code interpreter session
- GETGet code interpreter session
/code-interpreters/:codeInterpreterIdentifier/sessions/get?sessionId=stringRetrieves detailed information about a specific code interpreter session in Amazon Bedrock AgentCore. This operation returns the session's configuration,… - POSTList code interpreter sessions
/code-interpreters/:codeInterpreterIdentifier/sessions/listRetrieves a list of code interpreter sessions in Amazon Bedrock AgentCore that match the specified criteria. This operation returns summary information about… - PUTStart code interpreter session
/code-interpreters/:codeInterpreterIdentifier/sessions/startCreates and initializes a code interpreter session in Amazon Bedrock AgentCore. The session enables agents to execute code as part of their response… - PUTStop code interpreter session
/code-interpreters/:codeInterpreterIdentifier/sessions/stop?sessionId=stringTerminates an active code interpreter session in Amazon Bedrock AgentCore. This operation stops the session, releases associated resources, and makes the…
Process payment
- POSTProcess payment
/payments/processPaymentProcesses a payment using a payment instrument within a payment session.
Browser profile
- PUTSave browser session profile
/browser-profiles/:profileIdentifier/saveSaves the current state of a browser session as a reusable profile in Amazon Bedrock AgentCore. A browser profile captures persistent browser data such as…
Registry record
- POSTSearch registry records
/registry-records/searchSearches for registry records using semantic, lexical, or hybrid queries. Returns metadata for matching records ordered by relevance within the specified…
- POSTComplete resource token auth
/identities/CompleteResourceTokenAuthConfirms the user authentication session for obtaining OAuth2.0 tokens for a resource. - POSTGet resource api key
/identities/api-keyRetrieves the API key associated with an API key credential provider. - POSTGet resource oauth2 token
/identities/oauth2/tokenReturns the OAuth 2.0 token of the provided resource. - POSTGet resource payment token
/identities/payment/tokenGenerates authentication tokens for payment providers that use vendor-specific authentication mechanisms. - POSTGet workload access token
/identities/GetWorkloadAccessTokenObtains a workload access token for agentic workloads not acting on behalf of a user. - POSTGet workload access token for jWT
/identities/GetWorkloadAccessTokenForJWTObtains a workload access token for agentic workloads acting on behalf of a user, using a JWT token. - POSTGet workload access token for user id
/identities/GetWorkloadAccessTokenForUserIdObtains a workload access token for agentic workloads acting on behalf of a user, using the user's ID. - POSTInvoke code interpreter
/code-interpreters/:codeInterpreterIdentifier/tools/invokeExecutes code within an active code interpreter session in Amazon Bedrock AgentCore. This operation processes the provided code, runs it in a secure… - POSTInvoke harness
/harnesses/invoke?harnessArn=string&qualifier=stringOperation to invoke a Harness. - POSTInvoke web search
/web-search/:webSearchId/invokeSearches the web and returns a ranked list of results. Each result includes a text extract from the page. You can filter the results by domain and by…
API details
- Base URL
https://bedrock-agentcore.{region}.amazonaws.com- Authentication
- AWS Signature Version 4 (requests signed with your AWS access key)
- Operations
- 68 operations on 60 pathsPOST 44GET 11PUT 7DELETE 6
- Main resources
- Memory 16Evaluation 15Browser session 6Payment instrument 5Agentic 4Code interpreter session 4Payment session 4Browser profile 1Capacity provider 1Process payment 1
- Description format
- AWS Smithy model, API version
2024-02-28 - Links
- Documentation · OpenAPI document
- Listed from
- AWS Smithy API model (aws/api-models-aws) (Apache-2.0)
How to test the Amazon Bedrock AgentCore in Swastik Codes
- Open the APISelect “Fork & run in Swastik Codes” on this page. Sign in or create a free account if asked.
- Fork it into your workspaceChoose a workspace. You get your own copy of the Amazon Bedrock AgentCore collection, without the publisher's secrets.
- Add your credentialsThis API uses AWS Signature Version 4 (requests signed with your AWS access key). Add yours in the collection's variables or an environment; the requests already reference it.
- Send a requestPick an endpoint, for example “Batch create memory records” (POST /memories/:memoryId/memoryRecords/batchCreate), and press Send. Check the response, add tests and run the whole collection with the runner.
Frequently asked questions
What is the Amazon Bedrock AgentCore?
Welcome to the Amazon Bedrock AgentCore Data Plane API reference. Data Plane actions process and handle data or workloads within Amazon Web Services services. It is listed under AI & machine learning and has 68 endpoints.
Who publishes the Amazon Bedrock AgentCore?
It is listed from Amazon Web Services, Inc.'s public API description (an OpenAPI document), not published by Amazon Web Services, Inc. on Swastik Codes. Anyone who controls amazonaws.com can claim the profile by adding a DNS TXT record.
What is the base URL of the Amazon Bedrock AgentCore?
Requests go to https://bedrock-agentcore.{region}.amazonaws.com. Endpoint paths are added to this base URL.
How do I authenticate with the Amazon Bedrock AgentCore?
With AWS Signature Version 4 (requests signed with your AWS access key).
How many endpoints does the Amazon Bedrock AgentCore have?
68 operations on 60 paths (44 POST, 11 GET, 7 PUT, 6 DELETE). The largest groups are Memory, Evaluation, Browser session, Payment instrument.
Is forking the Amazon Bedrock AgentCore free?
Yes. Forking copies the collection into your workspace for free. It has been starred 0 times and forked 0 times.