# caliber-ai-org/ai-setup

Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files for Claude Code, Cursor, and Codex.

Repository: https://github.com/caliber-ai-org/ai-setup
Canonical: https://ross.abutalabs.com/products/ai-setup
Homepage: https://trycaliber.ai
Language: TypeScript
License: MIT
License Family: permissive
Topics: agent-config, ai-agents, anthropic, claude-code, claude-md, cli, cursor, cursorrules, developer-tools, llm, openai, skills, codex, mcp, openai-codex
Last push: 2026-07-26T12:08:51+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 94, release rhythm 83, longevity 12
- inputs: {"age_days": 176, "days_push": 38, "days_rel": 38, "gap_med": 0.0, "n_releases_24m": 199}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1251, forks 122 (observed 2026-08-28T04:04:08.321618+00:00)

## What it is
Caliber is a Node.js CLI that generates, scores, and continuously syncs AI agent context files (CLAUDE.md, .cursor/rules/, AGENTS.md, copilot-instructions.md) so they stay accurate as your codebase evolves. It supports Claude Code, Cursor, Codex, OpenCode, and GitHub Copilot, with deterministic config scoring and pre-commit hooks for drift detection.

## Use cases
- keep CLAUDE.md in sync with my codebase
- generate cursor rules automatically from my repo
- sync AI agent configs across Claude Code, Cursor, and Codex
- score the quality of my AI agent config files
- stop my AI agent from hallucinating stale paths
- manage MCP configs and agent skills across a team
- detect config drift in agent instruction files

## When to choose
- your team uses multiple AI coding agents and configs keep drifting
- hand-written CLAUDE.md or cursor rules go stale after refactors
- you want deterministic, no-LLM scoring of agent context files

## When to avoid
- you use a single AI editor and are happy with a static config file
- you need a hosted enterprise AI governance or ROI platform rather than a repo-level CLI
- your project is not Node.js >= 20 based or you cannot run npx

## Facets
- artifact type: cli-tool
- maturity: active
- function: developer-tools, cli, configuration-management, agent-framework, mcp, prompt-engineering
- domain: developer-tools, large-language-models
- platform: cli, cross-platform
- tags: claude-code, cursor, codex, agent-config, context-files, claude-md, cursorrules, config-sync, pre-commit-hooks, ai-agents, automation, command-line, nodejs

## Member repositories
- caliber-ai-org/ai-setup (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:08.321618+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:07:38.442863+00:00, confidence not recorded.
  - readme: https://github.com/caliber-ai-org/ai-setup (fetched 2026-08-28T04:04:08.321618+00:00, sha 9dff5176e2cf)
  - homepage: https://trycaliber.ai (fetched 2026-08-29T12:18:30.770805+00:00, sha f4ffee3dcf5e)
  - site_page: https://trycaliber.ai/roi (fetched 2026-08-29T12:18:30.773468+00:00, sha 6f59a8704653)
- Data as of 2026-08-30T08:39:29.467469+00:00.