KirishAkkaunt yaratish
KirishAkkaunt yaratish

ai-setup

Ochiq manbalardan

Bitta buyruq bilan AI sozlamalaringizni uzluksiz sinxronlashtiring. Kod bazangizga moslashtirilgan agent koʻnikmalari, MCP va konfiguratsiya fayllarini Claude Code, Cursor va Codex uchun tanlang.

Mashina tarjimasi · Asl matnni koʻrsatish

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

CLI vositaKategoriya: Dasturchi vositalari · Kod uchun AI · Muharrirlar va IDEOpen sourcemaʼlumot tekshirilgan: 16-okt, 2026
SolishtirishToʻplamga

Sharh

  • agent-config
  • ai-agents
  • anthropic
  • claude-code
  • claude-md
  • cli
  • codex
  • cursor
  • cursorrules
  • developer-tools
  • llm
  • mcp

Oʻrnatish

Buyruqlar faqat koʻrsatiladi, marketpleys ularni bajarmaydi. Rasmiy hujjatlar bilan solishtiring.
  • Rasmiy saytOchiq manbalardankatalog metamaʼlumotlaridan
    trycaliber.ai/ ↗
  • Til paketlari reyestrinodejsOchiq manbalardanpaket manifestidan — reyestrda chop etilgani tekshirilmagan
    npm install -g @rely-ai/caliber

    Tekshirilmagan: oʻrnatishdan oldin reyestrdagi paket aynan shu loyihaga tegishli ekanini tekshiring.

    www.npmjs.com/package/@rely-ai/caliber ↗
  • Manbadan yigʻishOchiq manbalardankatalog metamaʼlumotlaridan

    Manbadan yigʻish: tekshirilgan yigʻish retsepti yoʻq — repozitoriy koʻrsatmalariga amal qiling.

    github.com/caliber-ai-org/ai-setup ↗

Moslik

«Nomaʼlum» dalil topilmaganini bildiradi, mahsulot mos emasligini emas.
PlatformaHolatArxitekturaDalilIshonchlilik
WindowsNomaʼlum———
macOSNomaʼlum———
LinuxNomaʼlum———
Container (OCI)Nomaʼlum———
Node.jsMos—paket manifesti: package.json name0.60

Relizlar

tekshirilgan: 30-okt, 2026
v1.55.2Oxirgi24-sen, 2026Rasmiy manba ↗

1.55.2 versiyasi fayllari

Relizga fayllar biriktirilmagan.

Relizlar tarixi

Sifat profili

algoritm quality-v1.0 · baholangan 16-okt, 2026
Sifat bahosi94
Xavf bahosi0
Ishonchlilik 1.00
Sifat bahosi va xavf bahosi — turli koʻrsatkichlar. Yuqori sifat xavfsizlikni kafolatlamaydi.

Baho tarkibi

Qoʻllab-quvvatlash · 2020
last activity 22 days ago
Hujjatlar · 1515
README 4293 chars, description present
Foydalanishga tayyorlik · 1515
install instructions: yes; releases: yes
Metamaʼlumotlar · 1010
4/4 of description, homepage, license, topics
Relizlar · 1010
10 release(s), latest 22 days ago
Kategoriya aniqligi · 106
classifier confidence 0.6
Ommaboplik · 108
1306 stars (log-dampened, 10k = max)
Litsenziya aniqligi · 55
SPDX MIT
Hamjamiyat · 55
issues enabled, 126 forks

Litsenziya

MIT
Litsenziya maʼlumrepozitoriy xostingi maʼlumotlariga koʻra

Bu katalog siyosati holati, yuridik xulosa emas.

Manbalar

github.com/caliber-ai-org/ai-setupAsosiy★ 1 306 yulduzfaollik: 24-sen, 2026Asosiy repozitoriy · Ishonchlilik 1.00

Sharhlar

Sharh yozish uchun kiring

Hali sharhlar yoʻq.

Muqobillar

Trail-CodeOʻxshash
Claude Code, Cursor, Codex, Gemini va har qanday kodlash agentini kuchaytiring: tezroq, arzonroq, loyihangizning kodbazasiga xos kontekstni tushunish bilan.MIT · Dasturchi vositalari
gentle-aiOʻxshash
Gentle-AI siz allaqachon ishlatayotgan AI kodlash agentlarini sozlaydi: Claude Code, Cursor, OpenCode, Codex, Pi va boshqalar. Doimiy xotira, Organic-Driven Development, tanlangan koʻnikmalar, MCP serverlari, personalar va ixtiyoriy chegaralangan tekshiruvni tanlang. Ochiq manba kodi, hech qanday agentga bogʻlanmagan.MIT · Dasturchi vositalari
agentacctOʻxshash
Kodlash agentlaringiz nima qilganini va bu qancha turganini koʻring. Har bir vazifani ish bosqichlariga ajratadi — ishlatilgan vositalar, oʻzgartirilgan fayllar, bajarilgan testlar, sarflangan vaqt va tokenlar. Claude Code, Codex, OpenCode va boshqalar uchun mahalliy boshqaruv paneli. Kirish talab qilinmaydi, telemetriya yoʻq.MIT · Dasturchi vositalari
genieOʻxshash
Istaklar kiradi, PR lar chiqadi. CLI agenti sizdan soʻraydi, ishni rejalashtiradi, izolyatsiyalangan worktree larda parallel agentlarni ishga tushiradi va kodni siz koʻrishingizdan oldin tekshiradi.MIT · Dasturchi vositalari
graphifyOʻxshash
Istalgan kod bazasini, uning hujjatlari, SQL sxemalari, konfiguratsiyalari va PDF fayllari bilan birga soʻrov berish mumkin boʻlgan bilimlar grafigiga aylantiradi. Claude Code, Cursor, Codex va Gemini CLI uchun /graphify koʻnikmasi: lokal deterministik AST tahlili, har bir bogʻlanishning izohi, vektor saqlagichisiz.Apache-2.0 · Dasturchi vositalari
lazycodexOʻxshash
Murakkab kod bazalari uchun yagona agent garovi. Loyiha xotirasi, rejalashtirish, bajarish va Codex ichida tekshirilgan yakunlash.MIT · Dasturchi vositalari

README

caliber-ai-org/ai-setup dan · litsenziya MIT · yuklangan 30-okt, 2026

Start

npx @rely-ai/caliber bootstrap

Then, in Claude Code or the Cursor CLI, run /setup-caliber. Your agent writes CLAUDE.md, Cursor rules, AGENTS.md and Copilot instructions, shows you the diff, and installs the hooks that keep them current. No agent handy? caliber init does the same as a wizard.

Node 20+. Runs on your Claude Code or Cursor seat, or your own Anthropic, OpenAI, MiniMax or Vertex key. Bootstrap, scoring and sync run fully local.

Fresh

A pre-commit hook reads your diff and refreshes the context files your agents read. caliber score checks them against the repo, with no LLM: do the paths exist, are the commands real, has anything drifted.

caliber score --compare main

Shared

Write a skill, rule, plugin or MCP server in one agent and caliber sync puts it in every other one. It's deterministic, degrades where an agent lacks a feature (a skill becomes a Copilot instruction file), and never overwrites a file you edited by hand.

caliber sync --status

Lean: Jev compaction new

/compact summarizes, and summaries forget the file path, the error and the constraint you gave an hour ago. TypeSafe's Jev scores every tool call, drops the stale ones, and keeps everything else byte-for-byte.

Claude Code: a plugin that replaces /compact.

export CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1
export AI_GATEWAY_API_KEY=...        # or TYPESAFE_API_KEY
claude plugin marketplace add caliber-ai-org/ai-setup
claude plugin install caliber-jev-compaction@caliber

Cursor, Codex and any other agent: the same scoring from the CLI.

caliber compact --provider cursor  --transcript <jsonl>
caliber compact --provider generic --transcript ./session.json --write

Bring your own Vercel AI Gateway or TypeSafe key. If Jev is unavailable, Claude Code falls back to its built-in compaction. Setup and verification: FUNCTIONAL_CHECKLIST.md.

Commands

Command
caliber bootstrap / initSet up (agent skill or CLI wizard)
caliber scoreAudit config quality, no LLM
caliber refreshUpdate configs from recent changes
caliber syncMirror skills, rules, plugins and MCP across agents
caliber compactJev compaction report (--write for generic transcripts)
caliber plugin installInstall the Jev plugin into this project
caliber learnLearn patterns from your sessions into CALIBER_LEARNINGS.md
caliber hooksManage refresh and sync hooks
caliber configChoose provider, key and model
caliber undo / uninstallRevert changes / remove everything Caliber added

Every write is shown as a diff first and backed up to .caliber/backups/. Anonymous usage analytics (command names, never code) can be turned off with CALIBER_TELEMETRY_DISABLED=1.

Contributing

git clone https://github.com/caliber-ai-org/ai-setup.git && cd ai-setup
npm install && npm run test

See CONTRIBUTING.md. MIT licensed.

Repozitoriyni ochish ↗