Memori

Engineering

Written by Memori Team

Memori Labs Releases New Agent-Native Memory Infrastructure, Automatically Creating Structured Memory from Agent Trace

We launched the new agent-native memory infrastructure, advancing how AI agents retain, structure, and reuse knowledge over time.

Unlike traditional memory systems that rely primarily on long-form natural language conversation history, Memori enables agents to automatically create structured, long-term memory directly from the agent trace — including execution paths, tool results, workflow steps, outcomes, and decision-making logic.

This allows memory to be generated not only from what an agent says, but from what an agent actually does.

By structuring memory from agent execution, Memori enables agents to learn from completed tasks, avoid repeating prior mistakes, retrieve relevant operational context, and become more efficient over time. The result is a more durable memory layer that can materially reduce inference spend while helping agents optimize as they complete more workflows.

By automating the creation of structured memories from the agent trace instead of limiting the memory knowledge graph to what agents say, we are capturing tool calls, decisions, workflow steps, outcomes, and other trace events that give the agent a complete picture of its prior activities. For the first time, agents can remember and learn from every interaction and execution path, not just the natural language conversation that would otherwise be preserved.

The new agent-native version of Memori is currently available within the OpenClaw harness through version 0.0.11 of the Memori Labs OpenClaw plugin. We also plan to bring this agent-native memory capability to Hermes Agent and other harness infrastructure, including Claude and Codex via MCP.

The new OpenClaw plugin introduces these features

  • Structured, persistent memory for AI agents — Memori replaces flat markdown memory files with a structured knowledge graph that captures facts, decisions, outcomes, and patterns across every session — without bloating the prompt.
  • Grounded in what agents actually do, not just what they say — Memori captures tool calls, execution traces, and real-time agent decisions alongside conversation, giving agents a fuller picture of prior task execution.
  • Agent-controlled intelligent recall — Agents decide when and what to retrieve, scoped precisely by project, session, entity, or time range — eliminating irrelevant context and cross-project noise.
  • Automatic memory building, zero latency impact — Memory is structured and updated asynchronously after each interaction, so it never slows the agent's response.
  • Smarter daily briefs — Memori generates structured daily briefings built from execution traces and structured memory — covering priorities, risks, active goals, open loops, and known failure patterns — far beyond a simple conversation recap.
  • Built for multi-user, multi-project environments — Memory is fully scoped and isolated by project, process, session, and entity, preventing data bleed across users and contexts.
  • Production-ready observability — Full visibility into memory creation, recall activity, retrieval performance, and quota usage via Memori Cloud.

Set up takes 2 minutes for existing OpenClaw users

It requires OpenClaw v2026.3.2 or later. Developers can sign up for a free API key at https://app.memorilabs.ai.

1. Install and enable the plugin

openclaw plugins install @memorilabs/openclaw-memori
openclaw plugins enable openclaw-memori
openclaw gateway restart

2. Configure your Memori API key and Entity ID

You need three values: your Memori API key, an Entity ID, and a Project ID.

Option A: Via CLI (Recommended)

openclaw memori init \
  --api-key "YOUR_MEMORI_API_KEY" \
  --entity-id "your-app-user-id" \
  --project-id "my-project"

Option B: Via openclaw.json

Add the following to ~/.openclaw/openclaw.json:

{
  "plugins": {
    "entries": {
      "openclaw-memori": {
        "enabled": true,
        "config": {
          "apiKey": "your-memori-api-key",
          "entityId": "your-app-user-id",
          "projectId": "my-project"
        }
      }
    }
  }
}

3. Verify

After configuring, restart the gateway and verify your API connectivity:

openclaw gateway restart
openclaw memori status --check

You should see:

Memori Plugin Status
────────────────────────────────────
  API Key:    ****...A3xQ
  Entity ID:  your-app-user-id
  Project ID: my-project

Checking API connectivity... OK
Status: Ready

Industry-Leading LoCoMo Benchmark

The Memori Labs Benchmark results can be downloaded and verified at https://memorilabs.ai/benchmark.