User repository on GitHub
CLI tool for configuring and monitoring Claude Code
- Forks
- 3.7k
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
CommunityJev Agents & MCP
Claude Code Templates
A Claude Code configuration CLI shipping Jev modules for model routing, skill suggestion, tool guardrails, auto-mode gates, and sandbox hooks.
- Stars
- 32.5k
- Language
- Python
- License
- MIT
- Published by
- Community
- Author
- davila7
- Last verified
- Oct 2026
About this project
Bright Data proudly supports this project. Connect Claude Code to live web data — try their Skills and MCPs for web search, scraping, and structured data feeds. Ready-to-use configurations for Anthropic's Claude Code. A comprehensive collection of AI agents, custom commands, settings, hooks, external integrations (MCPs), and project templates to enhance your development workflow. Browse All Templates - Interactive web interface to explore and install 100+ agents, commands, settings, hooks, and MCPs.
Quoted from the project's README. Read the full README.
- Languages
- TypeScript
- Platforms
- CLI
- Capabilities
- Open sourceRequires API key
Highlights
- cli-tool/mods include jev-model-router, jev-guardrails, jev-auto-mode, and jev-vercel-sandbox READMEs.
- Four separate mods cover model routing, skill suggestion, guardrails, and auto-mode gating, each optional.
- MIT CLI for installing and monitoring Claude Code templates rather than a standalone agent runtime.
Watch out
Large template collection; each Jev mod is optional and needs TypeSafe or gateway credentials when enabled.
Questions about this entry
Short answers drawn from the linked project or page.
Separate optional modules. The main README documents only agents, commands, settings, hooks, MCPs and skills, with no mention of Jev. The Jev pieces live under cli-tool/mods as jev-model-router, jev-guardrails, jev-auto-mode and jev-vercel-sandbox, each with its own README.
Only for the Jev modules. The base CLI installs ordinary Claude Code configuration, including agents, commands, settings, hooks and MCPs, with no Jev involvement. Each Jev module needs TypeSafe or gateway credentials when you enable it.
Nothing documented suggests it does. You install specific named agents, commands, settings, hooks or MCPs with --yes, or run the CLI interactively and choose. Merge and overwrite behaviour for files that already exist is not described in the README.
An installer plus a monitor. It scaffolds Claude Code configuration and then adds session analytics, a conversation monitor with an optional tunnel, a health check and a plugin dashboard. There is no agent loop of its own to embed in your product.
npx claude-code-templates@latest installs named components: agents, commands, settings, hooks, MCPs and skills. Use explicit flags such as --agent development-tools/code-reviewer or --mcp database/postgresql-integration with --yes, or run it interactively to browse the 100-plus templates.
Session analytics (--analytics), a mobile-friendly conversation monitor (--chats, with --tunnel for secure remote access through Cloudflare Tunnel), a health check (--health-check) and a plugin dashboard (--plugins) for marketplaces, installed plugins and permissions.
Multiple sources, each keeping its original license and attribution: K-Dense scientific skills and obra/superpowers under MIT, official Anthropic skills, alirezarezvani/claude-skills and wshobson/agents under MIT, and commands from awesome-claude-code under CC0, among others.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: jevmem keeps Claude Code project memory by asking Jev which turns are worth saving.
avinashjetwani61 pointsJevmem – automatic project memory for Claude Code, built on JevRead the thread on Hacker NewsX: A usage router for Grok Bot
X: The compaction plugin, in Chinese
X: A prompt box that fills itself in
More Jev resources like this
34.9kGitHub stars
Stencil Labs' coding agent embeds TypeSafe Jev for typed checks, routing, and workflow decisions, with measured Jev tokenizer probes in pi-natives.
Jev Agents & MCP#community#typescript#coding-agent
Community
can1357/oh-my-piTypeScript
can1357/oh-my-piTypeScript22GitHub stars
An MCP proxy and hooks adapter that screens an agent's tool calls before they run and the tool results before the agent reads them, with thresholds in a policy file.
Jev Agents & MCP#community#mcp#security
45GitHub stars
Five typed tools — classify, check, score, rank, and ask — plus a skill, wired into Claude Code, Codex, Pi, and OpenCode in one setup command.
Jev Agents & MCP#community#typescript#mcp
Community
FrancoisChastel/jev-codeTypeScript
FrancoisChastel/jev-codeTypeScript20GitHub stars
Claude Code hooks that narrow a roster in YAML, ask Jev which handler owns a prompt, and log the band before anything is blocked.
Jev Agents & MCP#community#python#coding-agent
Community
AgriciDaniel/gatekeeperPython
AgriciDaniel/gatekeeperPython2.6kGitHub stars
A CLI that asks Jev which files and declarations answer a repository question, then prints verbatim excerpts for a coding agent to use.
Jev Tools & CLIs#community#typescript#cli
Community
dzhng/jevgrepTypeScript
dzhng/jevgrepTypeScript349GitHub stars
A single-binary MCP tool named evaluate that sends Noul, Choice, and Score questions to hosted Jev or a local System One server.
Jev Agents & MCP#community#go#mcp
Community
itsmostafa/system-one-connectorGo
itsmostafa/system-one-connectorGoFrom the Jev community
Posts from builders shipping with Jev right now.