Jev directory
CommunityJev Agents & MCP
GoGoJevMCP
Go agent that runs a local model through Ollama and uses Jev to pick the relevant skill and MCP tool for each request. The LLM generates tool arguments, which are validated against the tool schema before the MCP client executes them.
- Stars
- 0
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Uses Jev to select a skill from available skill definitions, or none.
- Uses Jev again to choose an MCP tool, or decide that no tool is needed.
- Ollama runs the language model locally; llama3.2 is the example model.
- Generated tool arguments are validated against the tool input schema before execution.
- Conversation history is kept so follow-up requests can reference earlier tool results.
Questions about this entry
Short answers drawn from the linked project or page.
Clone the repository, run go mod tidy, create a .env file with JEV_API_KEY, start Ollama and pull the configured model (for example llama3.2), then run go run .
Jev selects the relevant skill and the MCP tool for a request. Ollama's local model generates the JSON arguments for the chosen tool and writes the final natural-language answer.
Go, a running Ollama install with a locally available model, a Jev API key, and an MCP server implementation that exposes the tools the agent can call.
Language model inference runs locally through Ollama. Skill and tool selection calls go to the Jev API using your JEV_API_KEY, so request content used for selection is sent there.
After the LLM generates JSON arguments, the agent validates them against the selected tool's input schema before the MCP client sends them to the MCP server.
No license is specified yet in the provided material. Without one, default copyright applies, so confirm terms with the author before reuse.
The author lists ongoing work on more reliable tool argument generation, better handling of conversation history and previous tool results, improved context management, and more robust error handling.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.
FacebookClinicnotes
X: OpenRouter Decision Model Rankings
X: herdr + jev, an agent router
X: A group chat bot with decision room routing
More Jev resources like this
A lightweight self-hosted System 1 decision daemon and MCP server for AI agents and multi-agent swarms: it evaluates state text against typed choice, score and noul questions in one forward pass, with Laya, Ollama and OpenAI-compatible backends.
Jev Agents & MCP#community#github#mcp
Community
axiomantic/local-systemonePython
axiomantic/local-systemonePythonReusable project context and specialist workflows for the AI tools you already use: agents, skills, rules, and MCP tools for Claude Code, Codex, Copilot, and Cursor, plus Jev decision support that offloads bounded LLM decisions to save tokens.
Jev Agents & MCP#community#github#agents
Community
jmagly/aiwgTypeScript
jmagly/aiwgTypeScriptDjaevin, a calibrated, local-first decision layer from Icaro0310 that runs behind a Devin ACP backend with no API key. It ships as an MCP server published in the official MCP Registry and installs from PyPI as poordjaevin; the repo topics name calibration, conformal prediction and NLI.
Jev Agents & MCP#community#github#python
Community
icaro0310/devin-judgePython
icaro0310/devin-judgePythonA plugin-based agent harness (FastAPI + Vue 3) bundling a chat GUI, multi-provider model access, an MCP client and marketplace, skills, workflow studio, sandboxed execution and a Tauri desktop shell. It integrates TypeSafe AI's Jev for structured Choice, Score and Noul decisions.
Jev Agents & MCP#community#github#agents
Community
andyqiuqiubo/andy-harnessTypeScript
andyqiuqiubo/andy-harnessTypeScriptAn event-driven multi-agent network where JEV observes live state and assigns pending work to available agents. Its AgentRouter reference implementation routes on every completion event instead of waiting for a round to end, while general-purpose agents with OpenAI Responses API tools execute work concurrently.
Jev Agents & MCP#community#github#agents
Community
Kelly-Leeee/AgentNetwork-jevPython
Kelly-Leeee/AgentNetwork-jevPythonA local System One decision layer for AI coding agents, shipped as an MCP server and Agent Skill, that offloads high-volume classification, checks, scores and ranking from frontier LLMs to sub-50ms local models with calibrated output.
Jev Agents & MCP#community#github#mcp
Community
aktonay/snapdecPython
aktonay/snapdecPythonFrom 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.