Why your AI coding agent is working with bad context/skills and how to make AI setup tailored for your codebase.

#opensource #cli #productivity #ai

npx @rely-ai/caliber init
That's it. On first run, Caliber walks you through provider setup interactively.

Or install globally:

npm install -g @rely-ai/caliber
caliber init
Already have an API key? Skip the interactive setup:

export ANTHROPIC_API_KEY=sk-ant-...
npx @rely-ai/caliber init
⚙️ 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 Analyze languages, frameworks, dependencies, file structure,
│ and existing agent configs via LLM
│
├─ 3. 🛠️ Generate Create CLAUDE.md + skills in parallel (core docs via smart
│ model, skills via fast model). Auto-polishes for max score
│
├─ 4. 👀 Review See a diff of proposed changes — accept, refine via
│ chat, or decline. All changes are backed up automatically
│
└─ 5. 🧩 Skills Search community skill registries and install relevant
skills for your tech stack
Caliber works on any codebase — TypeScript, Python, Go, Rust, Terraform, Java, Ruby, and more. Language and framework detection is fully LLM-driven, not hardcoded.

What makes it different

Private & local — runs on your machine with your own API key. Your code never leaves your environment.
Always up-to-date — run it again after any refactor. It catches the drift.
Multi-platform — one command sets up Claude Code, Cursor, and Codex together.
Fully open source — MIT licensed. Audit every line, fork it, contribute back.

Try it

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

That's the entire CLI. Three commands.