claude-fable 开源项目推荐（34 个）

thewaltero /mythos-router

泄露的 Anthropic 推理协议。本地运行。通过严格写入纪律和自适应 Claude Opus 4.8 思维实现零漂移编码。Mythos

edvardgrishin27 /nativeprompt

Проверяет промпты и файлы инструкций (CLAUDE.md, AGENTS.md, скиллы) по правилам вашей модели: Claude Fable 5.2, Opus 5.5, Sonnet 5.5, Haiku 5.5, GPT-6 и 6.1, Codex, Gemini CLI. Советует уровень усилий. Каждый совет со ссылкой на документацию вендора. Без API-ключей и зависимостей, офлайн.

heyxiaoc /not-fade-away

在自己的 Mac 上搭一套常驻、自愈、走订阅、墙内也能用的自托管 AI 伴侣 · 人看版讲思路，机看版给完整规格 · 文 / 小C & Grace

yihui-dev /awesome-fable5-5-videos

A growing collection of videos people made with Claude Fable 5.5, with the prompts creators shared. Every video credited and linked to its post. Updated regularly.

Rylaa /fable5.2-opus5.5-orchestrator

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code: tier routing (Sonnet 5 does the work), Requirements Ledger, enforced guard hooks, automatic teammate reaping

Millijethwani18 /fable-opus-desktop-kit

Claude Fable 5 Desktop 2026 – Ultimate AI Storytelling & Code Assistant Tool

SihyeonJeon /why-was-fable-banned

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.

SamBWarren /parable

A pseudo-Fable mode for Claude Opus — Fable-style planning, verification, and multi-agent discipline as a Claude Code skill set. Unofficial; not affiliated with Anthropic.

fengyiqicoder /awesome-fable-5.2

Games, 3D worlds and web pages built with Claude Fable 5.2 that you can actually open — 57 live works (every link checked) + 61 video demos, each with a GIF preview and creator credit.

Anil-matcha /awesome-claude-fable-5-1

Curated Claude Fable 5.1 use cases, API migration notes, prompting patterns, integrations, demos, and benchmark evidence.

ajantoniou /fable-design-system

Bring Fable-style design taste to any AI coding agent. Free MIT design system for Claude, Opus 4.8, Codex, Cursor, Gemini & Antigravity. By Dr. Antoniou, free from UploadCheck.

yihui-dev /awesome-fable5-2-videos

A growing collection of videos people made with Claude Fable 5.2, with the prompts creators shared. Every video credited and linked to its post. Updated regularly.

liang8989 /awesome-fable5-2-videos

Videos people made with Claude Fable 5.2, with credits, source posts and any prompts their makers shared.

pagepop /awesome-ai-prompts-and-use-cases

Daily-curated AI creative examples and prompts for video, images, e-commerce, presentations and social media, with growing model collections including Claude Fable 5.5.

kgraph57 /claude-code-doctor

Health checkup for your Claude Code setup: read-only parallel audit, A-E grades with radar chart, red flags, HTML dashboard. Battle-tested with Claude Fable 5 / Opus. Zero changes before you approve.

motionvideohq /awesome-fable-5-5-motion-design

A growing collection of viral motion design videos made with Claude Fable 5.5 and the prompts behind them. Updated regularly.

claudeanthropic-free /Claude-Code-Free

Claude Code Free v2.1.266 is the Anthropic cli window, free to run. It covers how claude code ai handles skills and terminal work, where the haiku lane fits, and which prompt hooks matter most.

novalidesignl-ship-it /fable-like-skill

A Claude Code skill that brings Claude Fable 5's engineering discipline to Claude Opus 4.8 and other models: act decisively, ground progress claims in tool output, verify with fresh context, avoid over-engineering. Distilled from Anthropic's public Fable 5 migration guidance.

jx-grxf /claude-code-todo-fix

Claude Code todo list missing? Bring back the task list (TodoWrite, TaskCreate, Ctrl+T) on Opus 5.5, Sonnet 5.5, Haiku 5.5, Opus 5, Fable and Mythos. One-paste fix via CLAUDE_CODE_ENABLE_TODO_TOOLS, plus installers for macOS, Linux and Windows.

hamza-ali-shahjahan /local-llm-setup

Zero to a running local LLM on your machine, in one command — covers Mac, Linux, and Windows. Detects your hardware, picks the right models, installs Ollama, and smoke-tests it.