docs.terraphim.ai cleanup: Add graph embeddings, quickstart guides, and OpenClaw/KimiClaw integration
@AlexMikhalev がすでに取り組んでいます。
2026年3月10日 から。
評価
この issue はまだ評価されていません。
説明
Proposal: Documentation Cleanup for docs.terraphim.ai
Background
The current documentation at docs.terraphim.ai needs restructuring to better serve new users and showcase Terraphim's unique capabilities. This issue proposes adding several key sections to improve onboarding and highlight the quantum-inspired knowledge graph architecture.
Proposed Additions
1. Why Graph Embeddings? 🧠
Purpose: Explain the core philosophy behind Terraphim's knowledge graph approach
Content to include:
- What are graph embeddings and why they matter for AI
- Comparison: Vector-only RAG vs. Graph-enhanced RAG
- Terraphim's quantum-inspired graph representation
- Real-world benefits: multi-hop reasoning, explainability, relationship preservation
- Performance benchmarks (if available)
Target audience: Technical decision-makers, AI engineers evaluating knowledge systems
2. Quickstart Guide ⚡
Purpose: Get new users up and running in under 5 minutes
Content to include:
- Installation (cargo install, pre-built binaries, Docker)
- Minimal working example: indexing a document
- Querying the knowledge graph
- Basic configuration
- Verification steps
Structure:
# Step 1: Install
$ cargo install terraphim
# Step 2: Index
$ terraphim index ./my-docs
# Step 3: Query
$ terraphim query "What is the main topic?"
3. Quickstart with OpenClaw 🐾
Purpose: Integration guide for OpenClaw users
Content to include:
- What is OpenClaw and why integrate with Terraphim
- Setting up the Terraphim skill for OpenClaw
- Configuration: connecting OpenClaw to local/remote Terraphim instance
- Example: Agent memory persistence via knowledge graph
- Example: Multi-agent coordination using shared graph state
- Troubleshooting common issues
Key integration points:
- OpenClaw's skill system → Terraphim knowledge graph
- Agent session memory → Persistent graph storage
- Cross-agent communication → Meta-cortex formation
4. Quickstart with KimiClaw 🤖
Purpose: Guide for KimiClaw (Kimi K2.5 + OpenClaw) users
Content to include:
- What is KimiClaw (Kimi K2.5 model + OpenClaw runtime)
- Why Kimi K2.5 pairs well with Terraphim's knowledge graph
- Setup instructions specific to KimiClaw environment
- Example: Long-context conversations with graph-backed memory
- Example: Code understanding with semantic code graph
- Performance tips for the K2.5 + Terraphim stack
Unique advantages:
- Kimi K2.5's 256K context + Terraphim graph = best of both worlds
- Structured knowledge extraction from long conversations
- Persistent memory across sessions
Suggested Documentation Structure
docs.terraphim.ai/
├── index.md # Landing page
├── why-graph-embeddings.md # NEW: Philosophy & benefits
├── quickstart/
│ ├── index.md # NEW: Basic quickstart
│ ├── openclaw.md # NEW: OpenClaw integration
│ └── kimiclaw.md # NEW: KimiClaw integration
├── concepts/
│ ├── knowledge-graph.md
│ ├── quantum-fields.md
│ └── meta-cortex.md
└── ...
Additional Considerations
- Cross-references: Link between sections (e.g., OpenClaw guide references "Why Graph Embeddings")
- Code examples: All commands should be copy-paste runnable
- Screenshots: Diagrams for graph structure, meta-cortex formation
- Video: Optional short screencasts for complex setups
Related Work
This documentation effort aligns with:
- Terraphim's positioning as "knowledge-centric AI"
- Recent marketing story emphasizing quantum-inspired architecture
- Growing OpenClaw ecosystem integration
Next Steps
- Review and approve scope
- Assign documentation contributors
- Create sub-issues for each section
- Set review milestones
Would love feedback on:
- Priority ordering of these sections
- Additional integration guides (e.g., other agent frameworks)
- Specific use cases to highlight in examples
cc: @AlexMikhalev (KimiClaw perspective)
- 主要言語
- Rust
- スター
- 65
- フォーク
- 5
- 平均マージ
- 1時間 17分
- マージ済み PR（30日）
- 2
環境構築
- Dockerfile・Docker Compose ファイルなし
- プルリクエストのテンプレートあり
- コントリビューションガイドを読む
はじめの一歩
- issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
- 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
- リポジトリをフォークし、ブランチを切って変更します。
- issue 番号を参照したプルリクエストを送ります。
terraphim/terraphim-ai のほかの issue
-
terraphim_rlm: require a per-sub-result verification plan (recheck / control / independent route)オープン
難易度 4/5 3〜5日 初心者へのやさしさ 48/100
terraphim/terraphim-ai#969 · コメント 1 件 ·
-
難易度 5/5 1週間以上 初心者へのやさしさ 35/100
terraphim/terraphim-ai#968 · コメント 1 件 ·
-
難易度 5/5 1週間以上 初心者へのやさしさ 35/100
terraphim/terraphim-ai#967 ·
-
難易度 4/5 3〜5日 初心者へのやさしさ 48/100
terraphim/terraphim-ai#966 ·
-
難易度 5/5 1週間以上 初心者へのやさしさ 30/100
terraphim/terraphim-ai#965 · コメント 2 件 ·
terraphim/terraphim-ai の issue をすべて見る
似ている issue
-
enhancement
難易度 2/5 1〜3時間 初心者へのやさしさ 78/100
zcashlabs/thus-spoke-zakura#153 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 79/100
topgrade-rs/topgrade#2395 ·
メンテナーはふだん 1 日以内に返信
-
app bug windows-os
難易度 2/5 1〜3時間 初心者へのやさしさ 67/100
メンテナーはふだん 1 日以内に返信
-
editor good first issue
難易度 2/5 1〜3時間 初心者へのやさしさ 65/100
funnyboy-roks/inq#54 ·
-
難易度 2/5 1〜3時間 初心者へのやさしさ 72/100
メンテナーはふだん 1 日以内に返信