AI setup tailored for your codebase.

One command continuously scans your project — generates tailored skills, configs, recommended MCPs for your stack.

$npm install -g @rely-ai/caliber
Star us on GitHub
terminal
$

The problem

Bad setup = bad agent.

Without setup

No config, stale context

  • No project context for agents
  • No context retained across sessions
  • Excessive token usage per prompt
  • Missing MCPs that unlock key features
  • Stale configs nobody updates
  • Every dev has a different setup

With setup

Full context, always up to date

  • Full project context generated
  • Persistent context across sessions
  • Minimal token usage
  • Right MCPs recommended and installed
  • Configs stay fresh as code changes
  • Every dev gets the same setup

The challenge

Why is it hard to have a perfect setup?

?

Invisible gaps in your setup

There's a better MCP for your database, a skill that cuts your deploy time in half — and you have no idea they exist.

Best practices change weekly

New tools drop, guides update, community standards shift. What was best practice last month is outdated today.

Configs rot while code evolves

You refactor daily but CLAUDE.md still references last quarter's architecture. Your agent works off a lie.

Every developer has their own setup

One dev has MCPs configured, another doesn't. Rules differ across machines. There's no single source of truth for the team.

repeat forever

Meet Caliber

The best playbooks and practices, generated for your codebase.

We collected and curated the best skills, configs, and MCP recommendations from research and the community — so your AI agents get the setup they deserve.

Caliber Score

Deterministic, offline, no LLM needed. Rates your setup across 6 categories.

$ caliber score
Score: 87/100 Grade: A
Existence 23/25 · Quality 22/25 · Coverage 18/20
Accuracy 13/15 · Freshness 8/10 · Bonus 3/5
Existence25 pts

Config files present, cross-platform parity

Quality25 pts

Commands documented, no bloat, no vague rules

Coverage20 pts

Dependencies & services reflected in configs

Accuracy15 pts

Documented commands & paths actually exist

Freshness10 pts

Config recency, no leaked secrets

Bonus5 pts

Hooks, AGENTS.md, OpenSkills format

Commands

Four commands. That's the entire CLI.

caliber initScan and generate all config files
caliber scoreRate your setup (0–100, no LLM)
caliber recommendDiscover MCPs and skills
caliber configSet provider, API key, model

Works with

Claude CodeNo key needed
CursorNo key needed
OpenAI CodexAPI key

No API key needed with Claude Code or Cursor — use your existing subscription.

Why Caliber

Built for how you actually work.

Continuous

Always up-to-date

Configs stay fresh as your code evolves. Run it again after any change — drift gets caught automatically.

Contextual

Tailored per project

Each app gets its own setup based on its stack, dependencies, and architecture. No generic templates.

Your keys

Private. Local. Safe.

Runs on your machine with your own API key. Your code never leaves your environment.

MIT

Fully open source

MIT licensed. Audit every line, fork it, contribute back. No vendor lock-in, no black boxes.

Get started

Try it in 30 seconds.

$npm install -g @rely-ai/caliber

Then run: caliber init

CALIBER
GitHubnpmDiscordMIT License
© 2026 Rely AI