一个 Karpathy 风格的 LLM wiki + skill,用于以李宏毅老师的教学风格回答 AI 相关问题。

fable5 开源项目推荐(48 个)
fable5 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 48 个仓库长视线终端基准测试及密集奖励分级
Opus에 근접한 품질을 Sonnet 단가에 — 가성비 AI 운영 모델을 직접 구축한 Claude Code 프로젝트
Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforcement) for Fable-5-grade discipline: plan, self-verify, and route sub-agents, without Fable 5.
Claude Fable 5.1 prompting guide as Claude Code skills (KO/EN/ZH). Output quality goes up on Opus 5 and Sonnet 5 too.
Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.
Proactive 5h use guard for Claude Code (macOS)。在长批次/分代理运行时,在额外钱包前暂停一下。账户层级窗口可视化。/使用-守护技能+守护灵。与Anthropic无关。
AI reasoning skills distilled from 4,665 real Claude Fable 5 chain-of-thought traces. Mathematically tuned. Grade A (100%) emulation accuracy against MiniMax M3.
oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed every step, so a crash is a pause. Zero deps, deterministically testable.
Reverse-engineer the RL reward an LLM was trained on — from black-box agentic coding behavior alone. Tested on Opus 4.8, Fable 5, GPT-5.5.
国内接入 chatGPT 、Claude Opus、Fable5 API教程
A curated monorepo of interactive web experiments, 3D flight simulators, physics engines, web OS emulators, and creative tools.
A complete breakdown of the Fable 5 constitutional AI jailbreak technique for Claude 4.8
After distilling Fable 5, the output is an indexed CLAUDE.md + on-demand rules + skills, an executable specification designed for weaker model sessions.
Pydantic-flavored JSON validation and serialization for F# records, designed for Fable's multi-backend output (BEAM, Python, JavaScript), and , .NET
OpenAI Codex plugin for evidence-first code review, audits, fact checks, run contracts, and bounded subagent workflows.
Research analyst powered by Claude Code. Upload your research materials, run AI agents across industries, find real problems backed by primary sources. Full-stack React dashboard, fully customizable.
A pretty, playable, web-based 3D Flappy Bird game built by Claude Fable 5.
ブラウザで動く軽量マインクラフト風ゲーム
今は亡きFable5が作ったなんかブラックホールっぽい物が見えるツール。なんと中に向かって落下もできる。
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/fable5。
- 该话题在 GitHub 上共有 48 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 2427 Star,覆盖 6 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。