docs: update multi-engine integration status

README.md

@@ -32,7 +32,22 @@ Open source · Local first · Provider neutral · Zero mandatory runtime depende
 
 MARGINAL does not assume that more calls are wasteful. Missing or ambiguous evidence fails open.
 
-## Install for Codex
+## Current integrations
+
+| Engine | Capability | Integration |
+|---|---|---|
+| **Codex** | **Tool Enforcement** | Native plugin. Shadow Mode by default; enforcement requires local Earned Enforcement evidence. |
+| **Claude Code** | **Observe** | Native plugin using Claude Code hooks. Records engine-declared success/failure without changing the next model action. |
+| **OpenCode** | **Observe** | In-process JavaScript plugin with a persistent stdio bridge to the provider-neutral runtime. |
+| **PrivacyCode** | **Observe** | OpenCode-compatible install target with a distinct engine identity, ledger root, and trust evidence. |
+
+`Observe` integrations record evidence and recommendations but cannot block. A compatible install target
+may share an adapter, but it never shares earned trust: **same adapter does not mean same enforcement
+evidence**.
+
+## Native integrations
+
+### Codex
 
 Install the native plugin from the repository:
 
@@ -61,6 +76,43 @@ marginal install codex --autopilot-consent
 Installation alone never enables enforcement. Earned Enforcement requires verified evidence and
 explicit promotion.
 
+### Claude Code
+
+With the Python CLI installed:
+
+```bash
+marginal install claude-code
+marginal uninstall claude-code
+```
+
+Claude Code is **Observe-only** today. Its hooks expose separate success and failure events, so those
+outcomes are engine-declared rather than inferred from tool output.
+
+### OpenCode
+
+```bash
+marginal install opencode
+marginal uninstall opencode
+```
+
+OpenCode is **Observe-only**. The JavaScript plugin runs in the engine process and communicates with one
+long-running local MARGINAL bridge over stdio. Shell exit codes can prove shell success/failure; outcomes
+without a reliable engine signal remain `unknown`.
+
+### PrivacyCode
+
+```bash
+marginal install privacycode
+marginal uninstall privacycode
+```
+
+PrivacyCode reuses the OpenCode plugin contract but keeps a distinct engine label, installation path,
+ledger root, and evidence history. Compatibility is validated, not assumed permanently; a protocol
+divergence requires a separate adapter.
+
+See the [integration overview](docs/integrations/overview.md), [Claude Code guide](docs/integrations/claude-code.md),
+and [OpenCode / PrivacyCode guide](docs/integrations/opencode.md).
+
 ## How Autopilot works
 
 1. **Observe.** Hooks collect derived state, outcome, and coverage signals in Shadow Mode.
@@ -200,6 +252,8 @@ evidence semantics. See the [architecture guide](docs/product/architecture.md).
 | Getting started | [Quickstart](docs/getting-started/quickstart.md) |
 | Product | [Concepts](docs/product/concepts.md) · [Architecture](docs/product/architecture.md) |
 | Codex | [Plugin guide](docs/integrations/codex.md) · [Benchmark readiness](docs/integrations/codex-benchmark-readiness.md) |
+| Claude Code | [Observe plugin](docs/integrations/claude-code.md) |
+| OpenCode / PrivacyCode | [Observe plugin and compatible targets](docs/integrations/opencode.md) |
 | Evaluation | [Benchmarking](docs/evaluation/benchmarking.md) · [Public benchmarks](docs/evaluation/public-benchmarks.md) |
 | Operations | [Privacy](docs/operations/privacy.md) · [Governance](docs/project/governance.md) |
 | Reference | [API](docs/reference/api.md) · [Roadmap](ROADMAP.md) |

ROADMAP.md

@@ -41,7 +41,7 @@ This roadmap is milestone-driven rather than date-driven. GitHub Issues and pull
 | **v0.2 — Learning Loop Foundation** | Complete | Universal protocol, non-blocking observation, versioned evidence, privacy and replay |
 | **Community hardening** | In progress | Governance tax, false-stop accounting, diminishing-return control and clearer evidence UX |
 | **v0.3 — Codex Reference Integration** | Validation | Native plugin, one-command install, Earned Enforcement, and measured smoke |
-| **v0.4 — Multi-Engine Developer Preview** | Planned | Shared core across materially different coding agents |
+| **v0.4 — Multi-Engine Developer Preview** | In progress | Codex, Claude Code and OpenCode-family surfaces sharing one governance core |
 | **v0.5 — One-Command Universal Installation** | Planned | Detection, installation, diagnostics and rollback across engines |
 | **v0.6 — Adaptive and Causal Allocation** | Planned | Calibrated learning, exploration and stronger identification strategies |
 | **v0.7 — Ecosystem and Operational Scale** | Planned | Persistence, observability, team controls and more engines |
@@ -196,11 +196,22 @@ See [Codex benchmark readiness](docs/integrations/codex-benchmark-readiness.md).
 
 ## v0.4 — Multi-Engine Developer Preview
 
-**Status:** Planned
+**Status:** In progress
+
+The multi-engine layer is now real rather than roadmap-only:
 
-Build OpenCode, Claude Code and GitHub Copilot integrations where official control surfaces permit them. Reuse the same protocol, policy, governance accounting, privacy boundaries and reports. Publish a capability matrix and label each engine as Observe, Tool Enforcement or Full Compute Enforcement.
+- [x] Claude Code native plugin, labeled **Observe**, mapped through the engine-neutral hook core.
+- [x] OpenCode plugin, labeled **Observe**, using one persistent stdio bridge for interleaved sessions.
+- [x] PrivacyCode supported as an OpenCode-compatible target with separate engine identity and ledger state.
+- [x] Keep economic policy in `UniversalRuntime`; adapters normalize native events and declare only capabilities they can prove.
+- [x] Preserve fail-open behavior and record unavailable/unknown evidence instead of inventing measurements.
+- [ ] Migrate older duplicated hook logic onto the shared integration core only after conformance coverage is sufficient.
+- [ ] Add another materially different engine surface where its official API supports a defensible adapter.
+- [ ] Publish cross-engine conformance and paired evidence before expanding enforcement claims.
 
-**Exit criteria:** at least four environments pass protocol conformance; economic logic remains centralized; at least two integrations support real enforcement; each engine documents limitations and fail-open behavior.
+**Exit criteria:** at least four environments pass protocol conformance; economic logic remains centralized;
+at least two integrations support real enforcement backed by engine-specific Earned Enforcement evidence;
+each engine documents outcome limits, privacy boundaries and fail-open behavior.
 
 ---
 

docs/getting-started/quickstart.md

@@ -1,6 +1,25 @@
 # Quickstart
 
-## Install
+## Native agent integrations
+
+MARGINAL starts conservatively. Codex installs in Shadow Mode before any earned tool enforcement;
+Claude Code, OpenCode, and PrivacyCode are **Observe-only** and cannot block.
+
+```bash
+# Codex native plugin
+codex plugin marketplace add SignalLayerLabs/Marginal --ref main
+codex plugin add marginal@marginal
+
+# With the MARGINAL Python CLI installed
+marginal install claude-code
+marginal install opencode
+marginal install privacycode
+```
+
+Remove an integration with its matching uninstall command. See the
+[integration overview](../integrations/overview.md) for capability and evidence limits.
+
+## Python library / development install
 
 ```bash
 python -m pip install -e ".[dev]"

docs/index.md

@@ -16,6 +16,8 @@ MARGINAL documentation is organized by user intent instead of keeping every guid
 
 - [Integration overview](integrations/overview.md)
 - [Codex plugin](integrations/codex.md)
+- [Claude Code plugin](integrations/claude-code.md)
+- [OpenCode and PrivacyCode](integrations/opencode.md)
 - [Codex benchmark readiness](integrations/codex-benchmark-readiness.md)
 
 ## Evaluation and research

docs/integrations/overview.md

@@ -85,6 +85,12 @@ child process over pipes. Its outcome evidence is weaker than Claude Code's: the
 exit code, most other tools prove nothing, and those outcomes stay `unknown`. See
 [OpenCode plugin](opencode.md).
 
+PrivacyCode is an **Observe** install target for the same OpenCode adapter because its validated plugin
+surface is currently compatible. It keeps a distinct engine label, configuration path, ledger root, and
+evidence history. Target compatibility does not transfer Earned Enforcement authority: trust remains
+engine-specific. If the plugin/event contract diverges, PrivacyCode becomes a separate adapter rather
+than accumulating target-specific governance semantics.
+
 GitHub Copilot remains roadmap work. Codex is labeled Tool Enforcement,
 not Full Compute Enforcement, because specialized and hosted tool paths can fall outside local
 hook coverage.

site/index.html

@@ -5,7 +5,7 @@
   <meta name="viewport" content="width=device-width,initial-scale=1">
   <title>MARGINAL — Evidence-Driven Compute Governance for AI Agents</title>
   <meta name="description" content="MARGINAL is an open-source, local-first compute governance layer for AI agents that measures net value, governance overhead, diminishing returns and false stops.">
-  <meta name="keywords" content="AI agents, coding agents, compute governance, token optimization, Codex, agent observability, AI FinOps, LLM cost optimization">
+  <meta name="keywords" content="AI agents, coding agents, compute governance, Codex, Claude Code, OpenCode, PrivacyCode, agent observability, AI FinOps, LLM cost optimization">
   <meta name="author" content="SignalLayer Labs">
   <meta name="robots" content="index,follow">
   <link rel="canonical" href="https://signallayerlabs.github.io/Marginal/">
@@ -29,6 +29,7 @@
       <button class="nav-toggle" type="button" aria-expanded="false" aria-controls="nav-links">Menu</button>
       <div class="nav-links" id="nav-links">
         <a href="#benchmark">Benchmark</a>
+        <a href="#integrations">Integrations</a>
         <a href="#trace">Concrete trace</a>
         <a href="#proof">Proof standard</a>
         <a href="#irrelevance">Graceful irrelevance</a>
@@ -94,6 +95,29 @@ <h2 class="hero-title">The next action should add evidence, not just activity.</
       </div>
     </section>
 
+    <section class="section shell" id="integrations">
+      <div class="section-heading">
+        <p class="eyebrow">Multi-engine runtime</p>
+        <h2>One governance core. Engine-specific evidence boundaries.</h2>
+        <p>Adapters translate native lifecycle events into the same provider-neutral runtime. Capability labels stay conservative: sharing an adapter never transfers earned trust between engines.</p>
+      </div>
+      <div class="metric-grid">
+        <article class="accent-card"><span>Codex</span><h3>Tool Enforcement</h3><p>Native plugin. Shadow Mode first; narrow blocking requires repository-local Earned Enforcement evidence.</p></article>
+        <article><span>Claude Code</span><h3>Observe</h3><p>Native hooks with engine-declared success/failure events. Recommendations go to the ledger and never alter the next model action.</p></article>
+        <article><span>OpenCode</span><h3>Observe</h3><p>JavaScript plugin plus a persistent stdio bridge. Shell exit codes are provable; unsupported outcomes remain unknown.</p></article>
+        <article><span>PrivacyCode</span><h3>Observe</h3><p>OpenCode-compatible target with its own engine label, install path, ledger root and evidence history.</p></article>
+      </div>
+      <div class="evidence-banner">
+        <span class="evidence-key">Current rule</span>
+        <strong>Same adapter ≠ same trust. Enforcement evidence stays engine- and repository-specific.</strong>
+      </div>
+      <div class="benchmark-links">
+        <a href="https://github.com/SignalLayerLabs/Marginal/blob/main/docs/integrations/overview.md">Integration matrix</a>
+        <a href="https://github.com/SignalLayerLabs/Marginal/blob/main/docs/integrations/claude-code.md">Claude Code</a>
+        <a href="https://github.com/SignalLayerLabs/Marginal/blob/main/docs/integrations/opencode.md">OpenCode / PrivacyCode</a>
+      </div>
+    </section>
+
     <section class="section thesis" id="trace"><div class="shell split compact-gap">
       <div>
         <p class="eyebrow">The actual thesis</p>
@@ -173,11 +197,11 @@ <h2>What if GPT-5.7 — or any future model — is already efficient?</h2>
     </section>
 
     <section class="section roadmap-section"><div class="shell">
-      <div class="section-heading"><p class="eyebrow">Measured milestone</p><h2>Codex Reference Integration</h2><p>The auditable adapter and first matched smoke are implemented. The next evidence gate is a preregistered repeated canary large enough to estimate trajectory variance.</p></div>
+      <div class="section-heading"><p class="eyebrow">Current milestone</p><h2>Multi-Engine Developer Preview</h2><p>Codex, Claude Code, OpenCode and PrivacyCode now reach the same governance core through capability-aware integrations. The next gate is cross-engine conformance and causal intervention evidence, not broader claims.</p></div>
       <div class="roadmap-line">
-        <div class="done"><span>v0.2</span><b>Learning Loop Foundation</b><small>universal protocol · ledger · privacy · replay</small></div>
-        <div class="current"><span>Hardening</span><b>Net-value evidence layer</b><small>governance tax · false stops · diminishing returns</small></div>
-        <div class="done"><span>v0.3 foundation</span><b>Codex integration smoke</b><small>pinned runtime · telemetry · matched OFF/ON · Modal verification</small></div>
+        <div class="done"><span>v0.3</span><b>Codex reference integration</b><small>Tool Enforcement · evidence receipts · matched smoke</small></div>
+        <div class="done"><span>Multi-engine</span><b>Observe surfaces landed</b><small>Claude Code · OpenCode · PrivacyCode</small></div>
+        <div class="current"><span>Next</span><b>Counterfactual validation</b><small>paired continuations · regret · engine-specific earned trust</small></div>
       </div>
       <div class="center"><a class="button button-secondary" href="https://github.com/SignalLayerLabs/Marginal/blob/main/ROADMAP.md">Read the roadmap</a></div>
     </div></section>
@@ -186,7 +210,7 @@ <h2>What if GPT-5.7 — or any future model — is already efficient?</h2>
       <p class="eyebrow">Build the evidence first</p>
       <h2>Observe. Measure. Let intervention earn enforcement.</h2>
       <div class="hero-actions center">
-        <a class="button" href="https://github.com/SignalLayerLabs/Marginal#install">Install for Codex</a>
+        <a class="button" href="https://github.com/SignalLayerLabs/Marginal#native-integrations">Install MARGINAL</a>
         <a class="button button-secondary" href="https://github.com/SignalLayerLabs/Marginal/issues">Challenge the project</a>
       </div>
     </div></section>