Skip to main content
Lyzr logo
  • Category: ai agents
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 22
  • Triggers: 0
  • Slug: LYZR
  • Version: 20261030_00

Tools

Slug: LYZR_ADD_MEMORY_MESSAGESStore a batch of conversation messages in Lyzr Memory for an owner, session, and optional agent, with optional synchronous fact extraction.

Input Parameters

string
Optional Agent Studio agent ID associated with the conversation.
array
required
One or more conversation messages to add in this batch.
string
required
Stable application user or customer ID that owns these memories.
string
required
Conversation session ID used to group the messages.
string
Optional custom instructions layered onto the memory extraction prompt.
boolean
Whether to store and embed each message verbatim without conversational fact extraction.
string
Memory provider identifier. Use cognis unless an external provider is configured.
boolean
Whether to wait for long-term fact extraction before returning.
string
Existing provider credential ID required only for bring-your-own memory providers.
boolean
Whether assistant messages may also produce extracted facts.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_CHAT_WITH_AGENTSend a message or message history to an active Agent Studio agent and return its synchronous inference response for a session.

Input Parameters

array
Optional Agent Studio asset IDs available during this inference call.
string
Single user message. Provide this or messages, but not both.
string
Stable end-user identifier used by Lyzr for session ownership and memory.
string
required
Active Agent Studio agent ID to run.
array
Chat history for multi-message inference. Provide this or message, but not both.
string
required
Caller-chosen stable session ID used to continue the conversation.
object
Optional metadata filters used by the agent’s knowledge retrieval.
object
Values substituted into variables declared by the agent’s system prompt.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_CLEAR_MEMORY_SESSIONPermanently clear messages and memories for one explicit owner and session in Lyzr Memory. Cross-session deletion is always disabled.

Input Parameters

string
Optional agent ID used to further constrain the session cleanup.
string
required
Owner ID whose session data should be permanently cleared.
string
required
Exact session ID to clear. This tool never clears other sessions.
string
Memory provider identifier used by the session.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_CREATE_AGENTCreate a single-task Agent Studio agent with an LLM provider, model, instructions, and optional tool configuration.

Input Parameters

string
required
Human-readable name for the new agent.
string
Optional Lyzr tool ID assigned to this single-task agent.
string
required
Provider model identifier the agent should use.
number
Nucleus-sampling probability mass.
boolean
Whether inference is enabled immediately after creation.
string
Outcome the agent should optimize for.
string
Role or persona the agent should adopt.
string
Short explanation of the agent’s purpose.
string
required
Lyzr LLM provider ID configured in Agent Studio.
number
Sampling temperature for model responses.
string
Expected output format or content requirements.
string
Background context available on every run.
integer
Optional maximum reasoning or tool iterations per inference run.
boolean
Whether Agent Studio should retain conversation messages.
string
Optional existing Agent Studio credential ID for the selected LLM provider.
string
required
Operational instructions defining how the agent should perform its task.
string
Guidance telling the agent when and how to use its assigned tool.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_CREATE_AGENT_SCHEDULECreate a cron schedule that runs one Agent Studio agent with a message in a specified timezone.

Input Parameters

string
Message supplied to the agent for each scheduled run.
string
required
Stable Lyzr user ID attributed to scheduled executions.
string
required
Agent Studio agent ID to run on schedule.
string
IANA timezone used to interpret the cron expression, for example America/New_York.
integer
Maximum retries after a failed scheduled execution (0-5).
integer
Delay in seconds between retries (10-3600).
string
required
Five-field cron expression in minute, hour, day, month, and weekday order, for example 0 9 * * 1.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_DELETE_AGENTPermanently delete one Agent Studio agent by ID.

Input Parameters

string
required
Agent Studio agent ID to permanently delete.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_DELETE_AGENT_SCHEDULEPermanently delete one agent cron schedule and remove its associated scheduler job.

Input Parameters

string
required
Schedule ID returned by Create Agent Schedule or List Agent Schedules.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_EVALUATE_TEXT_WITH_RAI_POLICYApply one owned Responsible AI policy to text and return processed text, block decisions, warnings, detections, and redactions.

Input Parameters

string
Optional originating user query for contextual checks.
string ("llm_input" | "llm_output")
Whether the text is entering or leaving an LLM.
string
Optional Agent Studio agent ID for audit context.
string
required
RAI policy ID returned by List RAI Policies.
string
required
Text to evaluate and, where configured, redact or transform.
string
Optional conversation session ID for audit context.
string
Optional trusted source text used by groundedness checks.
string
Optional agent instructions used when evaluating policy compliance.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_GET_AGENTReturn the current configuration and status of one Agent Studio agent by ID.

Input Parameters

string
required
Agent Studio agent ID returned by List Agents or Create Agent.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_GET_KNOWLEDGE_BASEReturn one Lyzr Knowledge Base configuration by its known RAG configuration ID.

Input Parameters

string
required
Known Lyzr RAG configuration ID. Lyzr does not provide a list endpoint for discovering this value.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_GET_SIMULATION_OVERVIEWReturn aggregate Agent Simulation counts and average evaluation pass rate for the connected workspace.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_LIST_AGENTSReturn all Agent Studio agents owned by the connected API key, including IDs needed by lifecycle and inference tools.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_LIST_AGENT_SCHEDULESReturn one page of agent cron schedules, optionally filtered by user, agent, or active state.

Input Parameters

integer
Maximum schedules to return in this page (1-100).
string
Return schedules attributed to this Lyzr user ID.
string
Return schedules for this Agent Studio agent ID.
boolean
True for active schedules, false for paused schedules, or omit for both.
string
Continuation cursor returned by a previous call. Omit for the first page.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_LIST_AGENT_SIMULATION_ISSUESReturn recent performance, error, and Responsible AI issues across monitored agents, optionally filtered by resolution and severity.

Input Parameters

integer
Maximum recent issues to return (1-100).
boolean
True for acknowledged issues, false for unresolved issues, or omit for both.
string ("critical" | "medium" | "low")
Restrict results to one severity. Critical also includes legacy high-severity issues.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_LIST_RAI_POLICIESReturn Responsible AI policies owned by the authenticated user, including policy IDs and enabled guardrail configuration.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_LIST_SUPERFLOW_EXECUTIONSReturn one page of SuperFlow execution records, optionally filtered by workflow and execution status.

Input Parameters

integer
Maximum executions to return in this page (1-200).
string ("running" | "completed" | "failed" | "cancelled" | "paused")
Restrict results to one execution status.
string
Offset cursor returned by a previous call. Omit for the first page.
string
Return executions for this SuperFlow workflow ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_LIST_SUPERFLOW_WORKFLOWSReturn all SuperFlow workflow definitions accessible to the connected API key, including workflow IDs and graph data.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_LIST_VOICE_AGENTSReturn saved Voice agents accessible to the connected organization, including IDs used to filter transcripts.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_LIST_VOICE_TRANSCRIPTSReturn one page of accessible Voice call transcripts, optionally filtered by agent, session, organization, or date range.

Input Parameters

integer
Maximum transcripts to return in this page (1-200).
string
Inclusive ISO date or ISO date-time upper bound.
string
Return transcripts for this Voice agent ID.
string
Inclusive ISO date or ISO date-time lower bound.
string
Return only the transcript for this Voice session ID.
string ("asc" | "desc")
Sort transcripts by time ascending or descending.
string
Continuation cursor returned by a previous call. Omit for the first page.
string
Restrict results to an accessible organization ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_RETRIEVE_KNOWLEDGERetrieve relevant documents from a known Lyzr Knowledge Base using configurable basic, MMR, hypothetical-document, or time-aware retrieval.

Input Parameters

string
required
Natural-language query used to rank stored documents.
integer
Maximum relevant documents to return (1-100).
string ("basic" | "mmr" | "hyde" | "time_aware")
Retrieval strategy: basic, MMR, hypothetical-document, or time-aware.
number
Minimum document relevance score from 0.0 to 1.0.
string
required
Known 24-character hexadecimal Lyzr RAG configuration ID to query.
number
Non-negative weight applied to document recency for time-aware retrieval.
number
MMR balance from 0.0 to 1.0 between query relevance and result diversity. Used only when retrieval_type is mmr; keep the default 0.5 unless retrieval behavior has been calibrated.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_SEARCH_MEMORIESSemantically search stored memories for one owner, within one session or across that owner’s sessions, using Lyzr’s hybrid vector and BM25 retrieval.

Input Parameters

integer
Maximum matching memories to return (1-100).
string
required
Natural-language memory search query.
string
Optional Agent Studio agent ID filter.
string
Optional provider-defined memory category filter.
string
required
Stable application user or customer ID whose memories should be searched.
string
Session whose memories should be searched. Required unless cross_session is true.
boolean
Whether to search across all sessions belonging to the owner.
string
Memory provider identifier used when the memories were stored.
boolean
Whether archived or superseded memories may be returned.
string
Existing provider credential ID required only for bring-your-own memory providers.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: LYZR_SET_AGENT_STATUSActivate or deactivate an Agent Studio agent. Deactivated agents reject inference until reactivated.

Input Parameters

string
required
Agent Studio agent ID to activate or deactivate.
boolean
required
True to allow inference, or false to reject inference while preserving the agent.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not