OpenClaw Optimization Guide

Make your OpenClaw AI agent faster, smarter, cheaper, and actually safe to run in production.

June 2026 sweep. Stable baseline: OpenClaw 2026.6.4. Beta tracked: 2026.6.11-beta.1. This refresh advances the late-May guidance to the current line: per-agent budget caps, scheduled Policy attestations with drift gating, provider health checks with automatic failover, Google Meet live capture for Meeting Notes with retention/redaction, recall/dreaming tuning, /context map --diff, sandbox egress allowlists, and openclaw doctor secret-rotation + MCP-scope lint.

By Terp — Terp AI Labs

Start With The June 2026 Reality Check

The late-May betas are now stable, and early-June added four cost/safety levers worth wiring in. If you last read this guide around 2026.5.22/2026.5.24, these are the new rules:

1. Claude subscription-era advice is dead. Anthropic's April 4 policy change broke the old "Claude Pro/Max covers OpenClaw" path. Treat Claude as paid API / Bedrock / provider-routed usage unless your own install proves otherwise.
2. Budgets belong in config. 2026.6.4 makes per-agent agents.list[].budget caps first-class with onExceed: warn|degrade|stop. Give the orchestrator a cap and let degrade reroute routine work to cheap lanes automatically.
3. Policy checks should be scheduled, not one-shot. openclaw policy check --export produces diffable attestations; schedule it (and wire it into CI) so channel-policy drift is caught instead of discovered. Opt-in repair stays a human step.
4. Provider routing now self-heals. Add models.providers.<id>.health checks so a failing lane demotes itself for a bounded window instead of failing every turn — but only if you configured fallback lanes.
5. Voice/meetings need retention, not just capture. Discord voice and the new Google Meet live source feed Meeting Notes; set meetingNotes.retentionDays and redaction rules before auto-capture so transcripts expire and scrub sensitive fields.
6. Memory and context got tunable. memory.recall.maxParallel, scheduled dreaming, memory promote --dry-run, and /context map --diff let you tune recall, consolidation, and context regressions deliberately instead of by feel.

Read Part 33 — June 2026 Field Guide first if you want the latest tricks before the deep dives.

The Harness Thesis

Most agent capability comes from the harness, not the weights.

The exact percentage is rhetoric. The operator lesson is concrete: model swaps help, but the big wins come from context budgets, memory discipline, tool permissions, flow control, provider routing, hooks, and verification loops.

flowchart LR
    subgraph Model["The Model (weights)"]
        M[Claude Opus 4.7<br/>or your choice]
    end
    subgraph Harness["The Harness (operator-controlled) — this guide"]
        direction TB
        Inst[Instructions<br/>SOUL/AGENTS/MEMORY/skills]
        Ctx[Context engineering<br/>budgets + progressive disclosure]
        Tools[Tools + approvals<br/>semantic categories]
        Guard[Guardrails<br/>hooks, Task Brain, redaction]
        Mem[Memory layer<br/>memory-core + LightRAG + dreaming]
        Orch[Orchestration<br/>5 coordination patterns]
    end
    Model -.-> Harness
    Harness -.-> Results[Production results]

You usually cannot change the weights. You can change everything else: context, memory, tools, approvals, verification, cost controls, and orchestration. The rest of this guide is that operator-controlled layer.

Jump straight to the payoff

File Hierarchy At A Glance

OpenClaw's file layout maps 1:1 to Karpathy's three-tier LLM Wiki pattern published April 10, 2026. If you only remember one diagram from this guide, make it this one:

flowchart TB
    subgraph Raw["Raw sources — immutable, agent read-only"]
        Vault["vault/*"]
        Daily["memory/YYYY-MM-DD.md"]
    end
    subgraph Curated["Curated summaries — injected on every message"]
        Soul["SOUL.md<br/>identity"]
        Agents["AGENTS.md<br/>operational rules"]
        Mem["MEMORY.md<br/>durable facts"]
        Dreams["DREAMS.md<br/>reflection diary"]
        Skills["skills/*<br/>on-demand playbooks"]
    end
    subgraph Artifacts["Generated artifacts — one-shot output"]
        PRs["PRs / commits"]
        Reports["Reports / transcripts"]
    end
    Raw -. memory_search .-> Agent((Agent))
    Curated --> Agent
    Agent --> Artifacts
    Agent -. Deep-phase promote .-> Mem
    Artifacts -. auto-capture .-> Daily

Full reasoning and update rules in Part 31 — The LLM Wiki Pattern In OpenClaw.

Who This Is For

• Running any OpenClaw agent in production. If your bot handles real work, the speed, memory, and security parts are non-optional.
• Just hit "why is my agent slow?" for the first time. Part 1 and Part 2 are where to start.
• Coming from v3.x or early v4.0. Start with Part 26 — Migration Guide, then Part 25 — Architecture Overview.
• Building multi-agent systems. Part 5 — Orchestration and Part 24 — Task Brain are your backbone.
• Already read half the guide and forget what's where. Jump to Part 27 — Gotchas & FAQ or the themed map below.

Start Here (In This Order)

1. Part 25 — Architecture Overview — 15-minute primer on what OpenClaw actually is under the hood (gateway, Task Brain, memory layer, skills, surfaces).
2. Part 14 — Quick Checklist — 30-minute setup checklist covering the 80/20.
3. Part 17 — The One-Shot Prompt — copy-paste prompt that automates the whole setup.
4. Part 27 — Gotchas & FAQ — keep this open while you work. Half your questions are here.

What You Get (Numbers From Our Production Deployment)

Full numbers in benchmarks/.

Companion resources shipped with the guide

Alongside the 33 parts themselves, this repo now includes the tooling that turns "I read the guide" into "I can audit and reproduce the results":

• SCORECARD.md — The OpenClaw Production Readiness Scorecard. 50 items across Speed / Memory / Orchestration / Security / Observability, 2 points each, max 100. Designed to be copy-pasted into your own repo and shared publicly.
• AWESOME.md — A curated, opinionated list of OpenClaw resources: skills worth installing, memory and orchestration tools, observability stacks,