[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-82997":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":16,"stars30d":16,"stars90d":15,"forks30d":15,"starsTrendScore":17,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":20,"hasPages":20,"topics":22,"createdAt":10,"pushedAt":10,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":15,"starSnapshotCount":15,"syncStatus":13,"lastSyncTime":34,"discoverSource":35},82997,"open-hikmah","Nazm-AI\u002Fopen-hikmah","Nazm-AI","  An AI-powered Quran knowledge graph — place verses on a canvas and discover thematic, linguistic, and theological connections.","https:\u002F\u002Fopenhikmah.com",null,"TypeScript",105,2,6,0,46,1,66.03,"GNU General Public License v3.0",false,"main",[23,24,25,26,27,28,29,30],"anthropic","islam","nextjs","open-source","quran","quran-study","reactflow","typescript","2026-06-12 04:01:39","# Open Hikmah\n\n[![CI](https:\u002F\u002Fgithub.com\u002FNazm-AI\u002Fopen-hikmah\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002FNazm-AI\u002Fopen-hikmah\u002Factions\u002Fworkflows\u002Fci.yml)\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](LICENSE)\n\nAn AI-powered Quran knowledge graph. Search any verse, drop it on an infinite canvas, and let AI surface the connections — shared root words, thematic resonance, theological contrast. The Quran's internal architecture emerges as you explore.\n\n**Live:** [openhikmah.com](https:\u002F\u002Fopenhikmah.com)\n\n---\n\n## Features\n\n- **Canvas** — Infinite graph of verse nodes connected by AI-generated edges. Expand any verse by Theme, Root Word, or Contrast. Click an edge to read the reasoning behind the connection. Connections are **grounded**: canonical data (Arabic roots + meaning-based similarity) discovers the real target verses; the AI only explains *why* — it never invents references.\n- **Search** — Direct reference lookup (`2:255`), full-text keyword search, or **search by meaning** (semantic): find verses about a concept even when they don't contain the literal word. One click adds any verse to the canvas.\n- **Find similar verses** — From any verse, surface the closest verses by meaning (embedding similarity).\n- **Shareable canvases** — Every canvas state serialises to a single URL you can copy and share.\n- **Audio** — Play all canvas verses in Quran order with a single button.\n- **99 Divine Names** — Full Asmaul Husna with Arabic script, root morphology, Maturidi taxonomy, verse feed, and contemplative reflections.\n- **Bookmarks** — Save verses to your account; syncs across devices via the Quran Foundation API.\n- **Social** — Daily engagement streaks, a friends leaderboard, and head-to-head challenges (24h \u002F 48h \u002F 7d).\n\n---\n\n## Tech Stack\n\n| Layer | Choice |\n|-------|--------|\n| Framework | Next.js 16 (App Router), React 19, TypeScript |\n| Canvas | @xyflow\u002Freact |\n| State | Zustand |\n| Styling | Tailwind CSS v4 |\n| AI | Anthropic Claude (adaptive thinking) with Gemini fallback; Gemini embeddings for semantic search |\n| Quran data | alquran.cloud + Quran Foundation API; canonical morphology for root grounding |\n| Auth | Quran Foundation OAuth2 PKCE |\n| Database | PostgreSQL + pgvector + Drizzle ORM |\n| Testing | Vitest |\n| CI | GitHub Actions |\n\n---\n\n## Local Development\n\n**Prerequisites:** Node 20+, PostgreSQL 16 with the **pgvector** extension.\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FNazm-AI\u002Fopen-hikmah\ncd open-hikmah\nnpm install\ncp .env.example .env.local\n# Fill in the values\nnpx drizzle-kit migrate          # creates tables; enables the pgvector extension\n\n# One-time data seeds (idempotent, resumable):\nnode scripts\u002Fseed-quran.mjs       # full Quran corpus → verses\nnode scripts\u002Fembed-corpus.mjs     # verse embeddings → semantic search (needs GEMINI_API_KEY)\nnode scripts\u002Fseed-morphology.mjs  # Arabic roots → grounded \"By Root\" connections\n\nnpm run dev\n```\n\nStart a local Postgres instance if you don't have one (the image must include pgvector):\n\n```bash\ndocker run -d --name openh-db \\\n  -e POSTGRES_DB=open_hikmah \\\n  -e POSTGRES_USER=openh \\\n  -e POSTGRES_PASSWORD=devpassword \\\n  -p 5432:5432 \\\n  pgvector\u002Fpgvector:pg16\n```\n\nThen set `DATABASE_URL=postgresql:\u002F\u002Fopenh:devpassword@localhost:5432\u002Fopen_hikmah` in `.env.local`.\n\n> **Note:** the app runs without the seeds — search falls back to keyword mode and connections\n> to AI-from-memory generation. Run the seeds to enable semantic search and grounded connections.\n> `seed-morphology.mjs` ships with Al-Fatihah (surah 1); the rest of the corpus is a one-time backfill.\n\n---\n\n## Testing\n\n```bash\nnpm run test        # watch mode\nnpm run test:ci     # single run (used in CI)\n```\n\nAll external calls (fetch, Anthropic SDK, database) are mocked — tests run with no network access or API costs.\n\n---\n\n## Contributing\n\nRead [CONTRIBUTING.md](CONTRIBUTING.md) before opening a PR. The project touches sacred content — theological changes (AI prompts, divine name data, verse framing) have extra requirements detailed in [Theological Standards](CONTRIBUTING.md#theological-standards).\n\n## Security\n\nReport vulnerabilities privately to **security@openhikmah.com**. See [SECURITY.md](SECURITY.md).\n\n## License\n\n[MIT](LICENSE)\n","Open Hikmah 是一个基于人工智能的《古兰经》知识图谱项目，允许用户将经文放置在画布上，并探索其主题、语言和神学联系。该项目使用TypeScript编写，核心功能包括无限画布展示经文节点及其AI生成的关联边、全文搜索及语义搜索、相似经文查找、可共享的画布状态链接等。技术栈方面，采用Next.js框架、ReactFlow构建画布、Zustand管理状态、Tailwind CSS进行样式设计，并利用Anthropic Claude与Gemini提供AI支持。适用于希望深入研究《古兰经》文本间内在联系的研究者或学习者，在教育和个人灵性成长场景中尤为有用。","2026-06-11 04:09:49","CREATED_QUERY"]