How to use Kev: what you can do with it

3 use cases

• Serve a local decision model that routes support tickets

  Run Kev-4B locally and send a ticket with department, escalate and frustration questions in one request.

  • REPO jaredpalmer/kev
  • Claude Code
  • Codex
  • Cursor
  • Work and operations
  • Intermediate
  View prompt

  Set up jaredpalmer/kev with Kev-4B on port 8009, then write a script that sends each ticket in <file> with a department choice, an escalate noul and a frustration score, and writes the answers and probabilities to a CSV.

  Share Email me this

• Point the TypeSafe SDK at your own Kev server

  Keep your existing TypeSafe client code and switch its base URL to a local Kev server.

  • REPO jaredpalmer/kev
  • Claude Code
  • Codex
  • Cursor
  • Work and operations
  • Intermediate
  View prompt

  Change my TypeSafe client code in <file> to use a local jaredpalmer/kev server at 127.0.0.1:8009, run 50 sample inputs through both the hosted API and Kev, and report agreement and latency.

  Share Email me this

• Fine-tune Kev on your own support tickets with an agent skill

  Install the kev-finetune skill and ask your agent to fine-tune Kev on your data.

  • REPO jaredpalmer/kev
  • Claude Code
  • Codex
  • Work and operations
  • Advanced
  View prompt

  Use the kev-finetune skill from jaredpalmer/kev to fine-tune Kev-4B on my labeled tickets in <file>. Report accuracy before and after on a held-out split, and stop before deploying if the gain is within noise.

  Share Email me this

Quick start with Kev

1. Check you have what it needs: Python with uv; install from source (pip install kev is a different package); A GPU (CUDA) or an Apple Silicon Mac with MLX; Kev-0.8B runs on a laptop; Optional: a Modal account for fine-tuning and hosted endpoints.
2. Open jaredpalmer/kev on GitHub and read the README and license.
3. Run git clone https://github.com/jaredpalmer/kev.git && cd kev
4. Install the server extras with uv sync --extra serve
5. Start the server: uv run --extra serve python -m kev.serve --run jaredpalmer/kev-4b --port 8009
6. POST a ticket with choice, noul and score questions to localhost:8009/v1/systemone as in the README curl example

These steps come from our top use case, Serve a local decision model that routes support tickets, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for jaredpalmer/kev

claude mcp add --transport http deduped https://dedupedai.com/mcp

Kev alternatives · Best AI repos for Work and operations

About this repo

• Who it is forDevelopers who route tickets, flag escalations or score text and want a self-hosted, calibrated decision model instead of prompting a chat model.
• Why it is hot9.6k stars, launched 39 days ago, picked up by one AI source we track
• LanguagePython
• Sourcegithub.com/jaredpalmer/kev · Back to Hot repos

Requirements

• Python with uv; install from source (pip install kev is a different package)
• A GPU (CUDA) or an Apple Silicon Mac with MLX; Kev-0.8B runs on a laptop
• Optional: a Modal account for fine-tuning and hosted endpoints

Related repos

• Trended earlier REPO tangency-labs/solidcraft Solidcraft SolidCraft is an open-source parametric 3D CAD application written in pure Rust, with desktop, browser, headless CLI and MCP server versions.
• Trended earlier REPO seacen/meetcap Meetcap MeetCap is a Mac meeting assistant that records and transcribes meetings on your computer, writes live summaries and minutes, and lets an AI agent start recordings and search past meetings.
• Trended earlier REPO StartLuxLabs/StartLux-Decision Start Lux Decision StartLux-Decision is an open inference engine and HTTP server for a family of decision models that return a calibrated probability for every option of typed questions.