JSPM

Caliber analyzes your codebase — languages, frameworks, dependencies, architecture — and generates tailored, high-quality configs for Claude Code, Cursor, and OpenAI Codex. If configs already exist, it scores them, fixes what's stale, and keeps everything in sync as your code evolves.

npm install -g @rely-ai/caliber
caliber init

No API key required — works with your existing Claude Code or Cursor subscription. Or bring your own key (Anthropic, OpenAI, Vertex AI, any OpenAI-compatible endpoint).

💡 What Caliber Does

⚙️ How It Works

caliber init
│
├─ 1. 🔌 Connect      Choose your LLM provider — Claude Code seat, Cursor seat,
│                      or an API key (Anthropic, OpenAI, Vertex AI)
│
├─ 2. 🔍 Discover     Fingerprint your project: languages, frameworks, dependencies,
│                      file structure, and existing agent configs
│
├─ 3. 🛠️  Generate     Build optimized configs with parallel LLM calls
│                      (heavy model for docs, fast model for skills)
│
├─ 4. 👀 Review       See a diff of every proposed change — accept, refine
│                      via chat, or decline. All originals are backed up
│
└─ 5. 🧩 Skills       Search community registries and install relevant
                       skills for your tech stack

Already have a setup? If your existing config scores 95+, Caliber skips full regeneration and applies targeted fixes to the specific checks that are failing.

📦 What It Generates

Claude Code

• CLAUDE.md — Project context, build/test commands, architecture, conventions
• .claude/skills/*/SKILL.md — Reusable skills (OpenSkills format)
• .mcp.json — Auto-discovered MCP server configurations
• .claude/settings.json — Permissions and hooks

Cursor

• .cursor/rules/*.mdc — Modern rules with frontmatter (description, globs, alwaysApply)
• .cursor/skills/*/SKILL.md — Skills for Cursor
• .cursor/mcp.json — MCP server configurations

OpenAI Codex

• AGENTS.md — Project context for Codex
• .agents/skills/*/SKILL.md — Skills for Codex

If these files already exist, Caliber audits them and suggests improvements — keeping what works, fixing what's stale, adding what's missing.

✨ Key Features

🌍 Any Codebase

TypeScript, Python, Go, Rust, Java, Ruby, Terraform, and more. Language and framework detection is fully LLM-driven — no hardcoded mappings. Caliber works on any project.

🔀 Any AI Tool

Target a single platform or all three at once:

caliber init --agent claude        # Claude Code only
caliber init --agent cursor        # Cursor only
caliber init --agent codex         # Codex only
caliber init --agent all           # All three
caliber init --agent claude,cursor # Comma-separated

💬 Chat-Based Refinement

Not happy with the generated output? During review, refine via natural language — describe what you want changed and Caliber iterates until you're satisfied.

🔗 MCP Server Discovery

Caliber detects the tools your project uses (databases, APIs, services) and auto-configures matching MCP servers for Claude Code and Cursor.

📊 Deterministic Scoring

caliber score evaluates your config quality without any LLM calls — purely by cross-referencing config files against your actual project filesystem.

  Agent Config Score    88 / 100    Grade A

  FILES & SETUP                                17 / 17
  QUALITY                                      21 / 23
  GROUNDING                                    20 / 20
  ACCURACY                                     10 / 15
  FRESHNESS & SAFETY                           10 / 10
  BONUS                                         5 / 5

🔄 Auto-Refresh

Keep configs in sync with your codebase automatically:

caliber hooks --install    # Enable all hooks
caliber hooks --remove     # Disable all hooks

The refresh command analyzes your git diff (committed, staged, and unstaged changes) and updates config files to reflect what changed. Works across multiple repos when run from a parent directory.

🛡️ Fully Reversible

Every change Caliber makes can be undone:

• Automatic backups — originals saved to .caliber/backups/ before every write
• Score regression guard — if a regeneration produces a lower score, changes are auto-reverted
• Full undo — caliber undo restores everything to its previous state
• Dry run — preview changes with --dry-run before applying

📋 Commands

🔌 LLM Providers

No API key? No problem. Caliber works with your existing AI tool subscription:

Override the model for any provider: export CALIBER_MODEL=<model-name> or use caliber config.

Caliber uses a two-tier model system — lightweight tasks (classification, scoring) auto-use a faster model, while heavy tasks (generation, refinement) use the default. This keeps costs low and speed high.

Configuration is stored in ~/.caliber/config.json with restricted permissions (0600). API keys are never written to project files.

# Custom region
export VERTEX_PROJECT_ID=my-gcp-project
export VERTEX_REGION=europe-west1

# Service account credentials (inline JSON)
export VERTEX_PROJECT_ID=my-gcp-project
export VERTEX_SA_CREDENTIALS='{"type":"service_account",...}'

# Service account credentials (file path)
export VERTEX_PROJECT_ID=my-gcp-project
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json

📋 Requirements

• Node.js >= 20
• One LLM provider: your Claude Code or Cursor subscription (no API key), or an API key for Anthropic / OpenAI / Vertex AI

🤝 Contributing

See CONTRIBUTING.md for detailed guidelines.

git clone https://github.com/rely-ai-org/caliber.git
cd caliber
npm install
npm run dev      # Watch mode
npm run test     # Run tests
npm run build    # Compile

Uses conventional commits — feat: for features, fix: for bug fixes.

📄 License

MIT