DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to point the TypeSafe SDK at your own Kev server with Kev

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

Short answer: Start a Kev server as in the quick start; then create a TypeSafeClient with api_key local and base_url http://127.0.0.1:8009 as in the README; call client.system_one with your existing questions. All steps.

Who it is forA team already using Jev through TypeSafe that wants a self-hosted option.

The problemHosted decision APIs cost per call and send your data to a third party.

The outcomeThe same client code calling Kev locally, with the API key set to local.

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

  1. Start a Kev server as in the quick start
  2. Create a TypeSafeClient with api_key local and base_url http://127.0.0.1:8009 as in the README
  3. Call client.system_one with your existing questions
  4. Compare answers and probabilities with your hosted results on a sample
  5. Pick a model size: Kev-4B to start, Kev-9B or Kev-27B for more accuracy

Prompt for your agent

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.

Caveat.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for jaredpalmer/kev and "Point the TypeSafe SDK at your own Kev server"

Add Deduped to Claude Code once

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

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer