moisesfilho/typesafe-jev-opencode
User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Agents & MCP
TypeSafe Jev for OpenCode
A 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.
- Stars
- 3
- Language
- JavaScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- moisesfilho
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Languages
- JavaScript
- Platforms
- MCP
- Capabilities
- Open sourceRuns locallyRequires API key
Highlights
- Exposes one tool, jev_decide, over local stdio; it accepts a state and one or more typed questions and supports TypeSafe noul, choice and score questions.
- Keeps the API key out of OpenCode config: it persists TYPESAFE_API_KEY into ~/.config/typesafe-ai.env with chmod 600 and sources that file from the MCP command.
- The global config example runs the server with bash -lc sourcing the env file then exec node mcp/index.mjs; the tool appears as typesafe-jev_jev_decide.
- Ships a conservative Developer-agent policy: automate only when confidence is at least 0.90 and the decision is technical, objective, reversible and low risk.
- Requires Node.js 20+; verify with `opencode mcp list`, which should report typesafe-jev connected, and restart OpenCode after config changes.
Quickstart
bash
git clone https://github.com/moisesfilho/typesafe-jev-opencode.git
cd typesafe-jev-opencode
npm installWatch out
Grounded on the truncated README and GitHub metadata reviewed 2026-10-15; the security section is cut off mid-sentence. The README stresses Jev is not a conversational replacement for Gemini, Claude or GPT, and it limits what the agent may decide autonomously.
Questions about this entry
Short answers drawn from the linked project or page.
An MCP server that adds TypeSafe Jev to OpenCode agents as a structured decision tool: it evaluates application state against typed questions and returns structured answers and probabilities for routing or gating work.
TypeSafe noul (yes/no with a probability), choice (pick an option) and score (ordered rating), all sent through the single jev_decide tool.
Clone the repository, run npm install, persist the API key, then add the server to ~/.config/opencode/opencode.json as shown in the README and restart OpenCode.
The README's scheme writes TYPESAFE_API_KEY to ~/.config/typesafe-ai.env with chmod 600 and sources it in the MCP launch command, keeping the key out of OpenCode configuration files.
Run `opencode mcp list`; the expected status is typesafe-jev connected. Remember to restart OpenCode after changing global configuration.
Per the shipped policy, only when confidence is at least 0.90 and the decision is technical, objective, reversible and low risk; objectives, plan approval, scope, credentials and irreversible actions stay with the user.
No. The README says Jev is not a conversational replacement; it is a decision tool that returns structured answers and probabilities an agent uses to route or gate work.
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
A 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
A local Python service that keeps your skill catalog out of the main model's context: it reads your SKILL.md library, asks Jev which skills fit, and returns only the selected instructions through a single read-only MCP tool, with Claude Code, Codex, and Cursor adapters.
Jev Agents & MCP#community#catalog-import#logicrw
Community
himomohi/jev-skill-routerPython
himomohi/jev-skill-routerPythonAn open-source Jev-based MCP router: it discovers, catalogs, classifies and deduplicates every MCP server and tool you have, then exposes each agent only the small, authorized subset it needs for the task. Routing decisions are System One Choice/Score/Noul questions, scored by a pluggable engine at the edge or hosted.
Jev Agents & MCP#community#catalog-import#logicrw
Community
amantux/mcp-routerPython
amantux/mcp-routerPythonA local MCP gateway that connects your MCP servers once and exposes just two tools to agents: find_tool discovers a capability through Jev Choice questions and execute_tool runs it with arguments validated against the original schema, managed from a CLI and a local dashboard.
Jev Agents & MCP#community#catalog-import#madewithjev
Community
prasanth263/mazaJavaScript
prasanth263/mazaJavaScriptOpen-source Codex plugin that consults TypeSafe Jev about tools, models, tasks, skills, context, and strategies, diagnoses failed commands, and checks completion claims against evidence. The current package is version 0.4.0.
Jev Agents & MCP#community#catalog-import#logicrw
Lets AI agents use Windows applications through MCP or the command line: hand off a bounded task and Jev observes windows, chooses controls, types supplied text and navigates locally, returning a result or a request for help.
Jev Agents & MCP#community#catalog-import#logicrw
Community
jacks3tr/jev-desktopPython
jacks3tr/jev-desktopPythonFrom 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.