Thriving Thriving Kotlin KT
↑ 50
splice torad-labs/splice

Run Claude Code on your ChatGPT, Grok, Kimi or Muse plan, on OpenRouter, or on a local model, and let sessions on different models work as a team. Unofficial; use at your own risk.

HEALTH 98 / Healthy
// solo builder// hidden gem// release machine

// momentum

tracking since W47

// why it's here

  • Active: last commit today
  • Built almost entirely by one person
  • Health 98/100 with only 20 stars
  • 7 releases in the last 90 days

// how to help

// readme

Use Claude Code with the models and subscriptions you already use.

ChatGPT · Grok · Kimi · Muse · API backends · Claude

Why splice · Install · Quick start · Providers · Trade-offs · Changelog · Security

splice puts Claude Code in front of the backend you choose.

  Requests are translated for your chosen backend.
  Interrupted compactions can resume from their saved answer.
  Retries stop at a set limit, and keys and sign-ins are never saved half-written.
  Your tools, permissions and shared Claude Code configuration stay yours.
  You see usage and what priced turns would cost at API rates.
  Doctor gives a remedy for failing checks.
  Sessions on different heads can discover and message each other.
Read the full README on GitHub ↗

Health score

Is the project alive and maintained right now? A 0–100 pulse recomputed nightly from commit recency, rhythm, how fast issues close, and how quickly PRs get merged.

How it's calculated

Undervalued score

Activity relative to attention (stars + watchers). Above 50 means a lot of activity for a project its size. Recomputed nightly from commit velocity, contributor effort, issue resolution, fork utility, release cadence, and project maturity — divided by a logarithmic reach factor.

How it's calculated

Tags

Tags are independent behavioral signals computed nightly. A project can hold multiple at once. They drive the home page sections.

How it's calculated