# OpenClaw + Jev

> Layer OpenClaw plugins jev-claw and jev-harness, plus bundled typesafe/jev-latest decisionModel. Tools, config, and when to route vs gate.

Assistant OS from OpenClaw, decide layer from Jev. Routing, gates, and official decisionModel support.

## Answer

OpenClaw orchestrates sessions, channels, tools, and generative providers. Many steps are still classification: which model tier, whether to run a shell command, whether the agent is stuck. Jev answers those with probabilities; plugins map answers to routes and gates.

## What OpenClaw is

OpenClaw is an assistant operating system: multi-channel agents, tool execution, and pluggable providers. Third-party plugins extend tools and policies without replacing the host runtime. See https://docs.openclaw.ai for host documentation.

## Official TypeSafe decision models in OpenClaw

OpenClaw merged bundled TypeSafe Jev models as an opt-in decisionModel provider (for example typesafe/jev-latest or typesafe/jev-1.13.0). The role stays disabled until selected. An optional typesafe_evaluate tool returns typed scores or probabilities after validation. Credentials use the host SecretRef pattern; billing follows TypeSafe API usage.

## jev-claw: typed model routing

The jev-claw plugin (documented on openclawdir.com) exposes jev_route: a single tool that classifies task_type, complexity, and risk, then returns route, confidence, needs_second_opinion, and reasons. Inputs include task text, changed_files, previous_attempts, and test_status. Routing is a classification problem; Jev returns fixed labels with probabilities rather than free-form routing prose.

## jev-harness: policy and gates

The jev-harness OpenClaw plugin wraps AntonioCoppe/jev-harness (npm library) for the decide layer: shell exec gates, tool allow/deny, model cost routing, inbox triage, browser next action, and stuck-agent recovery. OpenClaw keeps generative work on Claude, Codex, or other providers; this plugin applies Choice/Score/Noul plus confidence thresholds and shadow mode.

```json5
{
  plugins: {
    entries: {
      "jev-harness": {
        enabled: true,
        config: {
          mode: "live",
          gateExec: true,
          gateTools: false,
          toolAllowlist: ["web_search", "read"],
          knownSafeCommands: ["ls", "pwd", "git status", "git diff"],
        },
      },
    },
  },
}
```

## Choose jev-claw vs jev-harness vs decisionModel

Use jev-claw when you need multi-model routing labels (cheap vs frontier, second opinion). Use jev-harness when you need pre-tool or pre-shell gates with recipes and shadow evals. Use the bundled decisionModel provider when you want host-native typed evaluation via typesafe_evaluate without a separate plugin tool surface.

## Environment keys

Create a key at https://console.typesafe.ai/ (or route through Vercel AI Gateway / OpenRouter where the integration documents it). Export TYPESAFE_API_KEY in the environment for OpenClaw plugin processes. Some MCP clients accept AI_GATEWAY_API_KEY when using gateway-hosted Jev models; follow that integration's README. Never commit keys into repos or paste them into chat logs.

```bash
export TYPESAFE_API_KEY="tsk_..."
# Optional pin:
export TYPESAFE_MODEL="jev-latest"
```

## Pitfalls

jev-claw documents OpenClaw >= 2026.9.0 and Node 24+. Prefer TYPESAFE_API_KEY in the environment or ~/.config/typesafe/api_key where the plugin supports it. jev-harness is not affiliated with TypeSafe or OpenClaw Foundation; read license and maintenance on GitHub. Start in shadow mode when tuning policies so Jev logs actions without changing live behavior.

## In the directory

- [All agent guides](https://jev.aitools.fyi/guides/jev-with-ai-agents)
- [System One primer](https://jev.aitools.fyi/learn/system-one)
- [Agent tooling](https://jev.aitools.fyi/categories/agent-tooling)
- [jev-harness](https://jev.aitools.fyi/benchmarks/antoniocoppe-jev-harness)

## FAQ

### Does Jev replace OpenClaw's chat model?

No. Plugins and decisionModel roles handle structured decisions. Generative coding and conversation stay on your selected OpenClaw providers.

### Where is jev-harness source?

The npm package and GitHub repo are github.com/AntonioCoppe/jev-harness. The OpenClaw plugin page describes how it maps recipes to plugin tools.

### What routes does jev_route return?

openclawdir documents route labels such as cheap, main, architect, debugger, reviewer, claude-builder, claude-critic, and frontier, plus task_type and risk enums. Verify the current table in the plugin listing before hard-coding policies.

### Can I run both jev-claw and jev-harness?

Yes, with clear ownership: routing vs gating. Avoid duplicate gates on the same action without coordinating policy order in OpenClaw config.

## Sources

Directory copy checked 2026-09-26. Primary sources:

- [OpenClaw docs](https://docs.openclaw.ai/?ref=jev.aitools.fyi)
- [jev-claw plugin listing](https://openclawdir.com/plugins/jev-claw-zp0spu?ref=jev.aitools.fyi)
- [jev-harness plugin listing](https://openclawdir.com/plugins/jev-harness-7xg6sd?ref=jev.aitools.fyi)
- [jev-harness library README](https://github.com/AntonioCoppe/jev-harness?ref=jev.aitools.fyi)
- [OpenClaw Chronicles: TypeSafe decision models](https://openclawchronicles.com/posts/openclaw-2026-9-19-typesafe-decision-models/?ref=jev.aitools.fyi)

Canonical: https://jev.aitools.fyi/guides/jev-with-ai-agents/openclaw
Markdown: https://jev.aitools.fyi/guides/jev-with-ai-agents/openclaw.md