ai-setup

Name: ai-setup
Author: caliber-ai-org

2.7kinstalls/mo · npm1.2kstars116forks

How to install ai-setup?

caliber-ai-org/ai-setup

$git clone https://github.com/caliber-ai-org/ai-setup

Installs into the current project.

Summary

Hand-written `CLAUDE.md` files go stale the moment you refactor. Your AI agent hallucinates paths that no longer exist, misses new dependencies, and gives advice based on yesterday's architecture. Caliber generates and maintains your AI context files (CLAUDE.md, `.cursor/ru

Files · 1

View on GitHub

README.md

1	# Caliber
2
3	Hand-written `CLAUDE.md` files go stale the moment you refactor. Your AI agent hallucinates paths that no longer exist, misses new dependencies, and gives advice based on yesterday's architecture. Caliber generates and maintains your AI context files (`CLAUDE.md`, `.cursor/rules/`, `AGENTS.md`, `copilot-instructions.md`) so they stay accurate as your code evolves — and keeps every agent on your team in sync, whether they use Claude Code, Cursor, Codex, OpenCode, or GitHub Copilot.
4
5	<p align="center">
6	<img src="assets/demo-header.gif" alt="Caliber product demo" width="900">
7	</p>
8
9	<p align="center">
10	<a href="https://www.npmjs.com/package/@rely-ai/caliber"><img src="https://img.shields.io/npm/v/@rely-ai/caliber" alt="npm version"></a>
11	<a href="./LICENSE"><img src="https://img.shields.io/npm/l/@rely-ai/caliber" alt="license"></a>
12	<a href="https://nodejs.org"><img src="https://img.shields.io/node/v/@rely-ai/caliber" alt="node"></a>
13	<img src="https://img.shields.io/badge/caliber-94%2F100-brightgreen" alt="Caliber Score">
14	<img src="https://img.shields.io/badge/Claude_Code-supported-blue" alt="Claude Code">
15	<img src="https://img.shields.io/badge/Cursor-supported-blue" alt="Cursor">
16	<img src="https://img.shields.io/badge/Codex-supported-blue" alt="Codex">
17	<img src="https://img.shields.io/badge/OpenCode-supported-blue" alt="OpenCode">
18	<img src="https://img.shields.io/badge/GitHub_Copilot-supported-blue" alt="GitHub Copilot">
19	</p>
20
21	## Before / After
22
23	Most repos start with a hand-written `CLAUDE.md` and nothing else. Here's what Caliber finds — and fixes:
24
25	```
26	Before After /setup-caliber
27	────────────────────────────── ──────────────────────────────
28
29	Agent Config Score 35 / 100 Agent Config Score 94 / 100
30	Grade D Grade A
31
32	FILES & SETUP 6 / 25 FILES & SETUP 24 / 25
33	QUALITY 12 / 25 QUALITY 22 / 25
34	GROUNDING 7 / 20 GROUNDING 19 / 20
35	ACCURACY 5 / 15 ACCURACY 13 / 15
36	FRESHNESS 5 / 10 FRESHNESS 10 / 10
37	BONUS 0 / 5 BONUS 5 / 5
38	```
39
40	Scoring is deterministic — no LLM, no API calls. It cross-references your config files against your actual project filesystem: do referenced paths exist? Are code blocks present? Is there config drift since your last commit?
41
42	```bash
43	caliber score --compare main # See how your branch changed the score
44	```
45
46	## Get Started
47
48	Requires Node.js >= 20.
49
50	```bash
51	npx @rely-ai/caliber bootstrap
52	```
53
54	Then, in your terminal (not the IDE chat), start a Claude Code or Cursor CLI session and type:
55
56	> /setup-caliber
57
58	Your agent detects your stack, generates tailored configs for every platform your team uses, sets up pre-commit hooks, and enables continuous sync — all from inside your normal workflow.
59
60	Don't use Claude Code or Cursor? Run `caliber init` instead — it's the same setup as a CLI wizard. Works with any LLM provider: bring your own Anthropic, OpenAI, or Vertex AI key.
61
62	> Your code stays on your machine. Bootstrap is 100% local — no LLM calls, no code sent anywhere. Generation uses your own AI subscription or API key. Caliber never sees your code.
63
64	<details>
65	<summary><strong>Windows Users</strong></summary>
66
67	Caliber works on Windows with a few notes:
68
69	- Run from your terminal (PowerShell, CMD, or Git Bash) — not from inside an IDE chat window. Open a terminal, `cd` into your project folder, then run `npx @rely-ai/caliber bootstrap`.
70	- Git Bash is recommended. Caliber's pre-commit hooks and auto-sync scripts use shell syntax. Git for Windows includes Git Bash, which handles this automatically. If you only use PowerShell, hooks may be skipped silently.
71	- Cursor Agent CLI: If prompted to install it, download from [curs

People who liked this also viewed

6 picks

Type

ai-setup

2.7kinstalls/mo · npm1.2kstars116forks

View on GitHub

How to install ai-setup?

caliber-ai-org/ai-setup

$git clone https://github.com/caliber-ai-org/ai-setup

Installs into the current project.

Summary

Files · 1

View on GitHub

README.md

1	# Caliber
2
3	Hand-written `CLAUDE.md` files go stale the moment you refactor. Your AI agent hallucinates paths that no longer exist, misses new dependencies, and gives advice based on yesterday's architecture. Caliber generates and maintains your AI context files (`CLAUDE.md`, `.cursor/rules/`, `AGENTS.md`, `copilot-instructions.md`) so they stay accurate as your code evolves — and keeps every agent on your team in sync, whether they use Claude Code, Cursor, Codex, OpenCode, or GitHub Copilot.
4
5	<p align="center">
6	<img src="assets/demo-header.gif" alt="Caliber product demo" width="900">
7	</p>
8
9	<p align="center">
10	<a href="https://www.npmjs.com/package/@rely-ai/caliber"><img src="https://img.shields.io/npm/v/@rely-ai/caliber" alt="npm version"></a>
11	<a href="./LICENSE"><img src="https://img.shields.io/npm/l/@rely-ai/caliber" alt="license"></a>
12	<a href="https://nodejs.org"><img src="https://img.shields.io/node/v/@rely-ai/caliber" alt="node"></a>
13	<img src="https://img.shields.io/badge/caliber-94%2F100-brightgreen" alt="Caliber Score">
14	<img src="https://img.shields.io/badge/Claude_Code-supported-blue" alt="Claude Code">
15	<img src="https://img.shields.io/badge/Cursor-supported-blue" alt="Cursor">
16	<img src="https://img.shields.io/badge/Codex-supported-blue" alt="Codex">
17	<img src="https://img.shields.io/badge/OpenCode-supported-blue" alt="OpenCode">
18	<img src="https://img.shields.io/badge/GitHub_Copilot-supported-blue" alt="GitHub Copilot">
19	</p>
20
21	## Before / After
22
23	Most repos start with a hand-written `CLAUDE.md` and nothing else. Here's what Caliber finds — and fixes:
24
25	```
26	Before After /setup-caliber
27	────────────────────────────── ──────────────────────────────
28
29	Agent Config Score 35 / 100 Agent Config Score 94 / 100
30	Grade D Grade A
31
32	FILES & SETUP 6 / 25 FILES & SETUP 24 / 25
33	QUALITY 12 / 25 QUALITY 22 / 25
34	GROUNDING 7 / 20 GROUNDING 19 / 20
35	ACCURACY 5 / 15 ACCURACY 13 / 15
36	FRESHNESS 5 / 10 FRESHNESS 10 / 10
37	BONUS 0 / 5 BONUS 5 / 5
38	```
39
40	Scoring is deterministic — no LLM, no API calls. It cross-references your config files against your actual project filesystem: do referenced paths exist? Are code blocks present? Is there config drift since your last commit?
41
42	```bash
43	caliber score --compare main # See how your branch changed the score
44	```
45
46	## Get Started
47
48	Requires Node.js >= 20.
49
50	```bash
51	npx @rely-ai/caliber bootstrap
52	```
53
54	Then, in your terminal (not the IDE chat), start a Claude Code or Cursor CLI session and type:
55
56	> /setup-caliber
57
58	Your agent detects your stack, generates tailored configs for every platform your team uses, sets up pre-commit hooks, and enables continuous sync — all from inside your normal workflow.
59
60	Don't use Claude Code or Cursor? Run `caliber init` instead — it's the same setup as a CLI wizard. Works with any LLM provider: bring your own Anthropic, OpenAI, or Vertex AI key.
61
62	> Your code stays on your machine. Bootstrap is 100% local — no LLM calls, no code sent anywhere. Generation uses your own AI subscription or API key. Caliber never sees your code.
63
64	<details>
65	<summary><strong>Windows Users</strong></summary>
66
67	Caliber works on Windows with a few notes:
68
69	- Run from your terminal (PowerShell, CMD, or Git Bash) — not from inside an IDE chat window. Open a terminal, `cd` into your project folder, then run `npx @rely-ai/caliber bootstrap`.
70	- Git Bash is recommended. Caliber's pre-commit hooks and auto-sync scripts use shell syntax. Git for Windows includes Git Bash, which handles this automatically. If you only use PowerShell, hooks may be skipped silently.
71	- Cursor Agent CLI: If prompted to install it, download from [curs

People who liked this also viewed

6 picks

Type