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. Model config is now provider-catalog driven. 2026.4.24 moved model rows toward manifest-backed catalogs and deprecated /models add after it briefly shipped in 2026.4.22. Stop telling agents to edit model config from chat.
3. Memory became an operator surface, not just a search tool. 2026.4.29-beta.1 adds people-aware wiki metadata, provenance reports, per-conversation Active Memory filters, partial recall on timeout, and bounded REM previews.
4. Messaging has real run control now. Active-run queueing defaults toward steering, messages.visibleReplies can force visible channel replies through the message tool, and spawned sub-agent events carry routing metadata.
5. Browser and Codex automation got practical. Coordinate clicks, longer action budgets, per-profile headless overrides, Codex Computer Use status/install commands, and fail-closed MCP checks remove a lot of brittle manual setup.

Read Part 33 — Late-April 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

| Do this | For this outcome | |---|---| | Grade your setup → | 50-item Production Readiness Scorecard, score out of 100, shareable. | | Copy the reference config → | Working SOUL / AGENTS / MEMORY / TOOLS templates plus a conservative example config. | | See the numbers → | Reproducible benchmark methodology + harness + run template. | | Browse the ecosystem → | Curated list of skills, tools, papers, talks, adjacent projects. | | Hit a wall? → | Gotchas & FAQ, symptom-indexed. Most questions answered in one page. |

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

| File | Purpose | Size cap | Written by | Read when | |------|---------|---------:|------------|-----------| | SOUL.md | Identity, invariants, non-negotiables | < 1 KB | Human | Every message | | AGENTS.md | Operational rules, decision trees, tool routing | < 2 KB | Human + agent (auditable) | Every message | | MEMORY.md | Durable facts promoted from short-term (pointer index) | < 3 KB | Agent via memory promote | Every message | | DREAMS.md | Human-readable reflection diary | latest N entries | Built-in Dreaming | Every message | | skills/ | Named playbooks | per-skill small | Human + SkillClaw | On activation | | vault/ | Raw source notes, transcripts, links | unbounded | Auto-capture + humans | On memory_search | | memory/YYYY-MM-DD.md | Daily short-term rollup | rolling | Auto-capture | On memory_search |

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)

| Metric | Before | After | Source | |--------|-------:|------:|--------| | Context file size (SOUL + AGENTS + MEMORY) | ~15 KB | ~5 KB | Part 1 | | Memory search latency | 2–5s (cloud) | <100ms (local) | Part 4, Part 10 | | Compaction crash rate | loops on 16K models | fixed in 4.15+ | Part 15 | | Coding-agent token usage | baseline | –60% | Part 19 — Repowise | | Sessions before audit trail | 0 surfaces | all surfaces | Part 24 — Task Brain |

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, research papers, talks, communities, adjacent ecosystems.
• templates/ — A starter kit: tiny SOUL.md / AGENTS.md / MEMORY.md / TOOLS.md templates, a vault/ skeleton, and a