User repository on GitHub
Documentation hub for Hermes Agent + Jev (TypeSafe System One Model) integration
- Forks
- 1
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Agents & MCP
Hermes TypeSafe Jev
Documentation hub for wiring Jev into Hermes Agent, Nous Research's autonomous agent framework: Choice, Noul and Score arrive as MCP-style tools, with context curation, turn admission and receipt-backed verification described end to end.
- Stars
- 1
- Reading time
- 2 min
- Published by
- Community
- Author
- andyholst
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Platforms
- MCP
- Capabilities
- Open source
Highlights
- Documents eight built-in Hermes tools, including jev_assess, jev_decide, jev_rank, jev_verify and jev_context_curate.
- The community hermes-jev plugin by keeltrace adds a context engine with 75% context reduction versus 55% for Hermes's default compressor.
- A nervous system watches agent behavior for repeated failures and triggers local replanning without waiting for remote supervision.
- Turn admission uses Jev confidence to decide whether a turn is worth taking before the expensive LLM call runs.
- Compares Jev to frontier LLMs: 70-500 ms latency and $0.042 per MTok input against 3-329 s and $0.20-$10 per MTok.
Watch out
Grounded in the truncated repository README and GitHub metadata reviewed on 2026-10-15; the README cuts off at the start of its benchmarks section, no license is listed, and the GitHub description calls the repo a documentation hub while the madewithjev listing describes an MCP server exposing Choice, Noul and Score.
Questions about this entry
Short answers drawn from the linked project or page.
It is a documentation hub for integrating Jev with Hermes Agent, Nous Research's autonomous AI agent framework. It is meant for people wiring typed, probabilistic decisions into an agent loop rather than reading generated text.
Hermes has native Jev integration in its core, exposing eight jev_* tools in every session: jev_assess, jev_decide, jev_rank, jev_verify, jev_nervous_event, jev_context_curate, jev_context_rehydrate and jev_stats. No plugin is required for basic usage.
The keeltrace plugin replaces the default ContextCompressor with Jev-powered context governance (75% reduction versus 55%) while preserving every user and agent message verbatim, and adds a nervous system, turn admission, receipt-backed verification and adaptive routing.
The README's comparison table puts Jev at 70-500 ms latency and $0.042 per MTok of input with free output, against 3-329 seconds and $0.20-$10 per MTok for frontier models, with calibrated probabilities instead of overconfident answers.
It is an asynchronous decision loop that monitors agent behavior, detects repeated failures and triggers local replanning without waiting for remote supervision. Material decisions are emitted with jev_nervous_event so choices are logged.
The README says Hermes has native Jev integration built in, so no plugin is required for basic usage and the community plugin only extends it. The digest does not state API key requirements for this repository, so check the Hermes and TypeSafe documentation before deploying.
The README cuts off at the start of a TypeSafe benchmarks section, so no benchmark numbers are visible, and the repository lists no license. Claims about the integration come from the README's own tables and architecture diagram, not from measurements this repo publishes.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev in front of the HeyGen MCP
X: Playwright CLI + Jev vs Playwright MCP
X: A local MCP server that cuts computer use from 23s to 0.8s. Cartwright built Cortex, a local MCP server where…
X: A side panel that drives any site's WebMCP tools
More Jev resources like this
Jev-backed web search for Claude Code and Codex in three forms: a function-hook plugin that answers the built-in WebSearch with Jev, an MCP server, and a CLI. Jev picks sources and time window, then ranks results by relevance; zero runtime dependencies.
Jev Agents & MCP#community#catalog-import#madewithjev
Community
mukiwu/jev-search-mcpJavaScript
mukiwu/jev-search-mcpJavaScriptMCP server that lets Claude Code, Codex and other agents drive a real Chrome browser while JEV makes the small typed decisions — which element, which suggestion, did the click work — with calibrated confidence driving act, verify or ask.
Jev Agents & MCP#community#catalog-import#logicrw
Community
legostin/jev-mcpTypeScript
legostin/jev-mcpTypeScriptA portable Agent Skill that teaches coding agents - Claude Code, OpenAI Codex, Cursor and other compatible hosts - to use Jev as a bounded judgment layer, plus an optional MCP bridge and workflows for code, browser research, Blender and Unreal.
Jev Agents & MCP#community#catalog-import#logicrw
An MCP stdio server that judges every research step: guarded_search, guarded_fetch and research_report score each query, result and fetched page with Jev for relevance, credibility and steering risk, with budgets, SSRF-guarded fetching and a live SSE dashboard.
Jev Agents & MCP#community#catalog-import#cobanov
Community
kierandotai/jev-scoutTypeScript
kierandotai/jev-scoutTypeScriptA local stdio MCP server that adds a jev_decide tool to OpenCode agents, supporting noul, choice and score questions so an agent can route or gate work on structured answers and probabilities instead of prose.
Jev Agents & MCP#community#catalog-import#logicrw
Official MCP server for JevGuard and TypeSafe AI: zero-dependency guardrails over JSON-RPC 2.0 on stdio, gating shell commands and code patches, caching decisions in local SQLite and pruning state.
Jev Agents & MCP#community#catalog-import#cobanov
Community
seb4ez/jevguard-mcpPython
seb4ez/jevguard-mcpPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.