Get started

Lyzr for AI agents

Lyzr is a platform for building, running, and evaluating AI agents, with tools for memory, workflows, and responsible AI checks. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect LyzrSee the 22 actions ↓
AI and modelsAPI keyMCP + RESTlyzr.ai
AUDIT LOG · LYZRPOLICY: acme-support
09:41:07 · claude · u_8f2read
lyzr.list_agents
List Agents✓ allowed · 212ms
09:41:08 · claude · u_8f2read
lyzr.get_agent
Get Agent✓ allowed · 164ms
09:41:09 · claude · u_8f2write
lyzr.create_agent
Create Agent✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
lyzr.delete_agent
Delete Agent✕ blocked · policy: deny
EVERY LYZR CALL, ON THE RECORD
01 · USE CASES

What agents do in Lyzr.

01

Chat with a configured agent

Send a message to an existing agent and get its response for a task.

02

Check an agent's simulation issues

List issues found in an agent's simulation runs before it goes live, read-only.

03

Approve before deleting an agent

Require approval before deleting an agent, since it removes its configuration and schedules.

02 · ACTIONS

22 Lyzr actions, graded by risk.

Every Lyzr action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

13

Look things up. Allowed by default.

  • lyzr.get_agent
    Get Agent
  • lyzr.list_agents
    List Agents
  • lyzr.search_memories
    Search Memories
  • lyzr.list_rai_policies
    List RAI Policies
  • lyzr.list_voice_agents
    List Voice Agents
  • lyzr.get_knowledge_base
    Get Knowledge Base
  • lyzr.list_agent_schedules
    List Agent Schedules
  • lyzr.list_voice_transcripts
    List Voice Transcripts
  • lyzr.get_simulation_overview
    Get Simulation Overview
  • lyzr.list_superflow_workflows
    List SuperFlow Workflows
  • lyzr.list_superflow_executions
    List SuperFlow Executions
  • lyzr.list_agent_simulation_issues
    List Agent Simulation Issues
  • lyzr.retrieve_knowledge
    Retrieve Knowledge

write

6

Create and change things. Allow, or ask the user first.

  • lyzr.create_agent
    Create Agent
  • lyzr.add_memory_messages
    Add Memory Messages
  • lyzr.create_agent_schedule
    Create Agent Schedule
  • lyzr.chat_with_agent
    Chat With Agent
  • lyzr.set_agent_status
    Set Agent Status
  • lyzr.evaluate_text_with_rai_policy
    Evaluate Text With RAI Policy

destructive

3

Delete, cancel or archive. Ask first, or deny outright.

  • lyzr.delete_agent
    Delete Agent
  • lyzr.delete_agent_schedule
    Delete Agent Schedule
  • lyzr.clear_memory_session
    Clear Memory Session
03 · HOW IT WORKS

Lyzr in three steps.

  1. 01Your users connect LyzrThey add their Lyzr api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Agent” can wait for the user, and “delete Agent” can be denied outright.
  3. 03Any agent can actYour agent calls Lyzr through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('lyzr', {
  read: 'allow',
  write: 'ask',        // create_agent
  destructive: 'deny',  // delete_agent
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Lyzr connects.

Users add their Lyzr api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Lyzr connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Lyzr from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

Lyzr and Arc0, answered.

Q01

Can I use Lyzr with Claude, ChatGPT or Cursor?

Yes. Connect Lyzr to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Lyzr actions you allow.

Q02

How do users connect Lyzr?

Users add their Lyzr api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Lyzr actions can my agent take?

22 in total: 13 read, 6 write and 3 destructive, such as “create Agent”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Lyzr?

Yes. Actions like “delete Agent” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Lyzr too?

Yes. The same Lyzr connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Lyzr into your agent.

Your users connect Lyzr once, under your brand. Your agent gets 22 actions behind your policies, with every call on the record.

Connect LyzrBrowse all apps →

Free to build · MCP + REST · Audit log on every plan