jev-layer
Provides a System-1 decision layer for the Hermes agent harness, with routing, receipts, replay, and fail-open integration.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@jev-layerRoute the current action to the most appropriate candidate tool."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
jev-layer routes bounded choices and records evidence; the host keeps execution, permissions, approvals, retries, recovery, and final results.
Architecture
Jev never executes a selected capability. A provider can be deterministic demo, OpenRouter Decisions, or TypeSafe; provider-backed tests are not required for normal CI.
Related MCP server: AIOrc MCP Server
Quick Start
Requirements: Node.js 20 or newer. There are no mandatory runtime dependencies.
Install the published CLI:
npm install --global jev-layerOr use a local clone:
npm install
npm link
jev install --project /path/to/workspace
jev add generic --project /path/to/workspace
jev doctor --project /path/to/workspacenpm link is local only. It does not publish the package. Use node /path/to/jev-layer/bin/jev.mjs ... instead if a global link is not wanted. The default demo provider is offline and deterministic.
To call the stdio MCP server directly:
jev mcpTo use a provider with credentials, keep keys outside the repository:
export JEV_LAYER_PROVIDER=openrouter
export OPENROUTER_API_KEY='provided-by-your-secret-store'
jev doctor --project /path/to/workspaceCore surfaces
Routing:
jev_routeselects one capability from the host-supplied candidate set. Selection is advisory; the host validates the id and permissions.Receipts/replay:
jev_record_executionjoins the host result to the originalcorrelation_id. JSONL cases live in.jev/replay/cases.jsonland can be evaluated offline withnpm run replay:evaluate.Supervision:
jev_supervisereturns bounded work-state judgments; deterministic host policy maps them tocontinue,verify,retry,finish, orescalate. Jev does not perform those actions.Context filtering: optional deterministic
shadoworconservativefiltering reduces stale context without LLM summarization.Experimental browser fast-path:
jev_browser_stepchooses one bounded action from a host observation. The host supplies observations, approval, native execution, and recovery. It is opt-in and does not start a browser worker.Fail-open: disabled, unavailable, invalid, or inconclusive Jev calls return control to the host's normal path. Jev never widens permissions or guesses execution.
All optional surfaces are disabled by default:
JEV_BROWSER_FAST_PATH=1 jev mcp
JEV_SUPERVISION=1 jev mcp
JEV_CONTEXT_FILTER=shadow jev cli --input examples/route-request.jsonHarness adapters
Current examples live under integrations/:
integrations/hermes/integrations/omp/integrations/codex/integrations/template/
The release baseline records OMP 18.2.6, Hermes 0.21.3 (b675e6de), and Codex CLI 0.155.1 observed in the preparation environment. This is a version/contract baseline, not a claim of full provider/model coverage; see docs/COMPATIBILITY.md.
Adapters are intentionally thin. They may call the CLI or stdio MCP, but the host must retain native capability lookup, permissions, approvals, execution, retries, recovery, and final output.
Adding a new harness
The shortest PR path is:
copy
integrations/template/adapter.mjs;add
integrations/<harness>/and a secret-free config/example;call
jev_route, preservecorrelation_id, execute only through the host registry, then calljev_record_execution;add an offline smoke fixture for success, fail-open, approval denial, and execution receipt;
document supported versions and run CI.
See CONTRIBUTING.md for the adapter contract and docs/SCHEMA-VERSIONING.md for compatibility rules.
Browser status
Browser fast-path reliability is validated against the current real-browser fixtures, including action sequencing, visible-link navigation, native select execution, approval denial, and recovery. Performance optimization remains experimental. No browser speedup claim is made.
Security and compatibility
MIT licensed; see LICENSE.
jev-layer is not a security boundary. Host permissions and approvals are authoritative; see SECURITY.md.
Schema, MCP tool, receipt, replay, and adapter contracts are currently version 1. Prefer additive changes; do not break v1 silently.
Do not commit credentials, logs containing secrets,
.envfiles, or machine-specific paths.
Verification
npm test
npm run smoke
npm run fail-open-smoke
npm run clean-install-smoke
npm pack --dry-runThe GitHub Actions matrix runs these checks on Node.js 20, 22, and 24. Provider-backed tests require an explicitly configured secret-managed environment and are not part of ordinary PR CI.
Release documents
This server cannot be deployed
Maintenance
Related MCP Connectors
A paid remote MCP for agent memory MCP, built to return verdicts, receipts, usage logs, and audit-re
- gatewayOAuthai.sealgate
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Remote MCP for A2A failure replay MCP, structured receipts, audit logs, and reviewer-ready evidence.
Workflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceAn MCP server for agent authorization that tests the full effect surface and enforces control over consequential actions before dispatch, emitting verifiable execution evidence.2Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables MCP-compatible LLM clients to execute server-verified agent workflows, with enforced transitions, invocation caps, and signed audit trails.MIT
- AlicenseNot gradedqualityBmaintenanceEnables transparent MCP proxying with a hash-chained effect ledger, classifying agent actions by reversibility, enforcing approval gates, and dry-run previews of sessions.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to screen proposed actions, enforce deterministic policies and limits, and produce tamper-proof signed audit receipts before any external side effect is executed.4 npmMIT