Who it is forA support engineer who wants routing and escalation decisions without per-call API costs.
The problemChat models give free text that needs parsing and their confidence is not calibrated.
The outcomeStructured answers with calibrated probabilities, such as returns, a 0.93 escalate probability and a frustration score.
What you need first
- 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
Steps
- Run
git clone https://github.com/jaredpalmer/kev.git && cd kev - Install the server extras with
uv sync --extra serve - Start the server:
uv run --extra serve python -m kev.serve --run jaredpalmer/kev-4b --port 8009 - POST a ticket with choice, noul and score questions to localhost:8009/v1/systemone as in the README curl example
- Route tickets by the returned probabilities and thresholds you choose
Prompt for your agent
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.
Caveat. Do not pip install Kev: that name on PyPI is an unrelated ORM. Install from source as shown.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for jaredpalmer/kev and "Serve a local decision model that routes support tickets"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer