---
canonical_url: "https://docs.composio.dev/toolkits/lyzr"
markdown_url: "https://docs.composio.dev/toolkits/lyzr.md"
product: "platform"
version: null
last_updated: null
---

# Lyzr

Build, run, evaluate, and manage AI agents and related Lyzr Studio services, including voice, responsible AI, simulation, memory, scheduling, workflows, and knowledge bases.

- **Category:** ai agents
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 22
- **Triggers:** 0
- **Slug:** `LYZR`
- **Version:** 00000000_00

## Tools

### Add Memory Messages

**Slug:** `LYZR_ADD_MEMORY_MESSAGES`

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

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `agent_id` | string | No | Optional Agent Studio agent ID associated with the conversation. |
| `messages` | array | Yes | One or more conversation messages to add in this batch. |
| `owner_id` | string | Yes | Stable application user or customer ID that owns these memories. |
| `session_id` | string | Yes | Conversation session ID used to group the messages. |
| `instructions` | string | No | Optional custom instructions layered onto the memory extraction prompt. |
| `document_mode` | boolean | No | Whether to store and embed each message verbatim without conversational fact extraction. |
| `provider_type` | string | No | Memory provider identifier. Use cognis unless an external provider is configured. |
| `sync_extraction` | boolean | No | Whether to wait for long-term fact extraction before returning. |
| `memory_credential_id` | string | No | Existing provider credential ID required only for bring-your-own memory providers. |
| `extract_assistant_facts` | boolean | No | Whether assistant messages may also produce extracted facts. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Chat With Agent

**Slug:** `LYZR_CHAT_WITH_AGENT`

Send a message or message history to an active Agent Studio agent and return its synchronous inference response for a session.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `assets` | array | No | Optional Agent Studio asset IDs available during this inference call. |
| `message` | string | No | Single user message. Provide this or messages, but not both. |
| `user_id` | string | No | Stable end-user identifier used by Lyzr for session ownership and memory. |
| `agent_id` | string | Yes | Active Agent Studio agent ID to run. |
| `messages` | array | No | Chat history for multi-message inference. Provide this or message, but not both. |
| `session_id` | string | Yes | Caller-chosen stable session ID used to continue the conversation. |
| `filter_variables` | object | No | Optional metadata filters used by the agent's knowledge retrieval. |
| `system_prompt_variables` | object | No | Values substituted into variables declared by the agent's system prompt. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Clear Memory Session

**Slug:** `LYZR_CLEAR_MEMORY_SESSION`

Permanently clear messages and memories for one explicit owner and session in Lyzr Memory. Cross-session deletion is always disabled.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `agent_id` | string | No | Optional agent ID used to further constrain the session cleanup. |
| `owner_id` | string | Yes | Owner ID whose session data should be permanently cleared. |
| `session_id` | string | Yes | Exact session ID to clear. This tool never clears other sessions. |
| `provider_type` | string | No | Memory provider identifier used by the session. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Agent

**Slug:** `LYZR_CREATE_AGENT`

Create a single-task Agent Studio agent with an LLM provider, model, instructions, and optional tool configuration.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | Yes | Human-readable name for the new agent. |
| `tool` | string | No | Optional Lyzr tool ID assigned to this single-task agent. |
| `model` | string | Yes | Provider model identifier the agent should use. |
| `top_p` | number | No | Nucleus-sampling probability mass. |
| `is_active` | boolean | No | Whether inference is enabled immediately after creation. |
| `agent_goal` | string | No | Outcome the agent should optimize for. |
| `agent_role` | string | No | Role or persona the agent should adopt. |
| `description` | string | No | Short explanation of the agent's purpose. |
| `provider_id` | string | Yes | Lyzr LLM provider ID configured in Agent Studio. |
| `temperature` | number | No | Sampling temperature for model responses. |
| `agent_output` | string | No | Expected output format or content requirements. |
| `agent_context` | string | No | Background context available on every run. |
| `max_iterations` | integer | No | Optional maximum reasoning or tool iterations per inference run. |
| `store_messages` | boolean | No | Whether Agent Studio should retain conversation messages. |
| `llm_credential_id` | string | No | Optional existing Agent Studio credential ID for the selected LLM provider. |
| `agent_instructions` | string | Yes | Operational instructions defining how the agent should perform its task. |
| `tool_usage_description` | string | No | Guidance telling the agent when and how to use its assigned tool. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Agent Schedule

**Slug:** `LYZR_CREATE_AGENT_SCHEDULE`

Create a cron schedule that runs one Agent Studio agent with a message in a specified timezone.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `message` | string | No | Message supplied to the agent for each scheduled run. |
| `user_id` | string | Yes | Stable Lyzr user ID attributed to scheduled executions. |
| `agent_id` | string | Yes | Agent Studio agent ID to run on schedule. |
| `timezone` | string | No | IANA timezone used to interpret the cron expression, for example America/New_York. |
| `max_retries` | integer | No | Maximum retries after a failed scheduled execution (0-5). |
| `retry_delay` | integer | No | Delay in seconds between retries (10-3600). |
| `cron_expression` | string | Yes | Five-field cron expression in minute, hour, day, month, and weekday order, for example 0 9 * * 1. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Delete Agent

**Slug:** `LYZR_DELETE_AGENT`

Permanently delete one Agent Studio agent by ID.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `agent_id` | string | Yes | Agent Studio agent ID to permanently delete. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Delete Agent Schedule

**Slug:** `LYZR_DELETE_AGENT_SCHEDULE`

Permanently delete one agent cron schedule and remove its associated scheduler job.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `schedule_id` | string | Yes | Schedule ID returned by Create Agent Schedule or List Agent Schedules. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Evaluate Text With RAI Policy

**Slug:** `LYZR_EVALUATE_TEXT_WITH_RAI_POLICY`

Apply one owned Responsible AI policy to text and return processed text, block decisions, warnings, detections, and redactions.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | No | Optional originating user query for contextual checks. |
| `stage` | string ("llm_input" | "llm_output") | No | Whether the text is entering or leaving an LLM. |
| `agent_id` | string | No | Optional Agent Studio agent ID for audit context. |
| `policy_id` | string | Yes | RAI policy ID returned by List RAI Policies. |
| `input_text` | string | Yes | Text to evaluate and, where configured, redact or transform. |
| `session_id` | string | No | Optional conversation session ID for audit context. |
| `grounding_source` | string | No | Optional trusted source text used by groundedness checks. |
| `agent_instructions` | string | No | Optional agent instructions used when evaluating policy compliance. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Agent

**Slug:** `LYZR_GET_AGENT`

Return the current configuration and status of one Agent Studio agent by ID.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `agent_id` | string | Yes | Agent Studio agent ID returned by List Agents or Create Agent. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Knowledge Base

**Slug:** `LYZR_GET_KNOWLEDGE_BASE`

Return one Lyzr Knowledge Base configuration by its known RAG configuration ID.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `config_id` | string | Yes | Known Lyzr RAG configuration ID. Lyzr does not provide a list endpoint for discovering this value. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Simulation Overview

**Slug:** `LYZR_GET_SIMULATION_OVERVIEW`

Return aggregate Agent Simulation counts and average evaluation pass rate for the connected workspace.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Agents

**Slug:** `LYZR_LIST_AGENTS`

Return all Agent Studio agents owned by the connected API key, including IDs needed by lifecycle and inference tools.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Agent Schedules

**Slug:** `LYZR_LIST_AGENT_SCHEDULES`

Return one page of agent cron schedules, optionally filtered by user, agent, or active state.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum schedules to return in this page (1-100). |
| `user_id` | string | No | Return schedules attributed to this Lyzr user ID. |
| `agent_id` | string | No | Return schedules for this Agent Studio agent ID. |
| `is_active` | boolean | No | True for active schedules, false for paused schedules, or omit for both. |
| `next_cursor` | string | No | Continuation cursor returned by a previous call. Omit for the first page. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Agent Simulation Issues

**Slug:** `LYZR_LIST_AGENT_SIMULATION_ISSUES`

Return recent performance, error, and Responsible AI issues across monitored agents, optionally filtered by resolution and severity.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum recent issues to return (1-100). |
| `resolved` | boolean | No | True for acknowledged issues, false for unresolved issues, or omit for both. |
| `severity` | string ("critical" | "medium" | "low") | No | Restrict results to one severity. Critical also includes legacy high-severity issues. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List RAI Policies

**Slug:** `LYZR_LIST_RAI_POLICIES`

Return Responsible AI policies owned by the authenticated user, including policy IDs and enabled guardrail configuration.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List SuperFlow Executions

**Slug:** `LYZR_LIST_SUPERFLOW_EXECUTIONS`

Return one page of SuperFlow execution records, optionally filtered by workflow and execution status.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum executions to return in this page (1-200). |
| `status` | string ("running" | "completed" | "failed" | "cancelled" | "paused") | No | Restrict results to one execution status. |
| `next_cursor` | string | No | Offset cursor returned by a previous call. Omit for the first page. |
| `workflow_id` | string | No | Return executions for this SuperFlow workflow ID. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List SuperFlow Workflows

**Slug:** `LYZR_LIST_SUPERFLOW_WORKFLOWS`

Return all SuperFlow workflow definitions accessible to the connected API key, including workflow IDs and graph data.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Voice Agents

**Slug:** `LYZR_LIST_VOICE_AGENTS`

Return saved Voice agents accessible to the connected organization, including IDs used to filter transcripts.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Voice Transcripts

**Slug:** `LYZR_LIST_VOICE_TRANSCRIPTS`

Return one page of accessible Voice call transcripts, optionally filtered by agent, session, organization, or date range.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum transcripts to return in this page (1-200). |
| `to_time` | string | No | Inclusive ISO date or ISO date-time upper bound. |
| `agent_id` | string | No | Return transcripts for this Voice agent ID. |
| `from_time` | string | No | Inclusive ISO date or ISO date-time lower bound. |
| `session_id` | string | No | Return only the transcript for this Voice session ID. |
| `sort_order` | string ("asc" | "desc") | No | Sort transcripts by time ascending or descending. |
| `next_cursor` | string | No | Continuation cursor returned by a previous call. Omit for the first page. |
| `organization_id` | string | No | Restrict results to an accessible organization ID. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Retrieve Knowledge

**Slug:** `LYZR_RETRIEVE_KNOWLEDGE`

Retrieve relevant documents from a known Lyzr Knowledge Base using configurable basic, MMR, hypothetical-document, or time-aware retrieval.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | Yes | Natural-language query used to rank stored documents. |
| `top_k` | integer | No | Maximum relevant documents to return (1-100). |
| `retrieval_type` | string ("basic" | "mmr" | "hyde" | "time_aware") | No | Retrieval strategy: basic, MMR, hypothetical-document, or time-aware. |
| `score_threshold` | number | No | Minimum document relevance score from 0.0 to 1.0. |
| `knowledge_base_id` | string | Yes | Known 24-character hexadecimal Lyzr RAG configuration ID to query. |
| `time_decay_factor` | number | No | Non-negative weight applied to document recency for time-aware retrieval. |
| `mmr_relevance_diversity_balance` | number | No | 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Search Memories

**Slug:** `LYZR_SEARCH_MEMORIES`

Semantically 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum matching memories to return (1-100). |
| `query` | string | Yes | Natural-language memory search query. |
| `agent_id` | string | No | Optional Agent Studio agent ID filter. |
| `category` | string | No | Optional provider-defined memory category filter. |
| `owner_id` | string | Yes | Stable application user or customer ID whose memories should be searched. |
| `session_id` | string | No | Session whose memories should be searched. Required unless cross_session is true. |
| `cross_session` | boolean | No | Whether to search across all sessions belonging to the owner. |
| `provider_type` | string | No | Memory provider identifier used when the memories were stored. |
| `include_historical` | boolean | No | Whether archived or superseded memories may be returned. |
| `memory_credential_id` | string | No | Existing provider credential ID required only for bring-your-own memory providers. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Set Agent Status

**Slug:** `LYZR_SET_AGENT_STATUS`

Activate or deactivate an Agent Studio agent. Deactivated agents reject inference until reactivated.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `agent_id` | string | Yes | Agent Studio agent ID to activate or deactivate. |
| `is_active` | boolean | Yes | True to allow inference, or false to reject inference while preserving the agent. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |