Fix link formatting in retrieval-patterns.md#2
Closed
sunchuljung wants to merge 2 commits into
Closed
Conversation
Rune is a complete, installable Claude plugin that provides zero-knowledge organizational memory for teams using Fully Homomorphic Encryption (FHE). - **Vault MCP Server** (mcp/vault/) - FHE key management and decryption - **enVector MCP Server** (mcp/envector-mcp-server) - Encrypted vector operations - **Agent Specifications** (agents/) - Scribe (capture) and Retriever (search) - **Pattern Libraries** (patterns/) - 250+ capture triggers, 265+ retrieval patterns - **Automated Setup** (scripts/install.sh) - Python venv, dependency installation - **MCP Configuration** (scripts/configure-claude-mcp.sh) - Claude integration - **Infrastructure Validation** (scripts/check-infrastructure.sh) - Health checks - **Server Management** (scripts/start-mcp-servers.sh) - Background MCP servers - **SKILL.md** - Claude skill definition with conditional activation logic - **README.md** - Complete installation and usage guide - **CHANGELOG.md** - Version history and roadmap - **Pattern files** - Comprehensive trigger and query patterns - pyenvector (1.2.0+) - FHE encryption SDK - fastmcp (2.2.0+) - MCP server framework - Additional: psutil, prometheus-client, httpx, pydantic, fastembed ```bash /plugin install github.com/CryptoLabInc/rune ```bash git clone https://github.com/CryptoLabInc/rune.git cd rune ./scripts/install.sh ./scripts/configure-claude-mcp.sh ``` ``` /rune configure # In Claude ``` Claude + Rune Plugin Cloud Infrastructure ├─ Vault MCP Server → Rune-Vault (team-shared) ├─ enVector MCP Server → enVector Cloud (encrypted) ├─ Scribe Agent └─ Retriever Agent - Conditional Activation - Validates infrastructure before activating - Fail-Safe Behavior - Auto-switches to dormant on failures - Token Efficiency - No wasted operations when dormant - Lightweight Checks - Local file validation only (no network pings) - Zero-Knowledge Privacy - All data FHE-encrypted before leaving client - Team Sharing - Same Vault = shared organizational memory - Automatic Redaction - Secrets, API keys, PII filtered - Local Credentials - Stored in ~/.rune/config.json (600 permissions) - Technical decisions and architecture rationale - Security requirements and compliance policies - Performance optimizations and scalability decisions - Product requirements and customer insights - Design decisions and user research findings - Semantic search on encrypted vectors - Decision rationale and implementation history - Team attribution and timeline queries - Natural language query understanding - `/rune configure` - Set up Vault and enVector credentials - `/rune status` - Check plugin activation and infrastructure health - `/rune remember <context>` - Manually store organizational context - `/rune recall <query>` - Search organizational memory - `/rune activate` - Activate after infrastructure is ready - `/rune reset` - Clear configuration and return to dormant 1. Rune-Vault Access (from team admin) - Vault URL: https://vault-TEAM.oci.envector.io - Vault Token: evt_xxx 2. enVector Cloud Credentials - Cluster Endpoint: https://cluster-xxx.envector.io - API Key: envector_xxx Deployment Guide: https://github.com/CryptoLabInc/rune-admin v0.2.0 - Complete plugin with infrastructure (2026-02-02) - Initial release with full MCP server integration - Smart activation with fail-safe behavior - Comprehensive pattern libraries (250+ triggers, 265+ queries) - Automated installation and configuration scripts MIT License - Copyright (c) 2026 CryptoLab Inc. - Issues: https://github.com/CryptoLabInc/rune/issues - Email: zotanika@cryptolab.co.kr - Docs: https://github.com/CryptoLabInc/rune-admin/tree/main/docs Signed-off-by: Sunchul Jung <zotanika@cryptolab.co.kr>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes a link formatting issue in the retrieval-patterns.md documentation file by correcting the relative path to the capture-triggers.md file.
Changes:
- Updated the relative link path from
patterns/capture-triggers.mdtocapture-triggers.md
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
couragehong
added a commit
that referenced
this pull request
Apr 22, 2026
heeyeon01
added a commit
that referenced
this pull request
May 15, 2026
…ndex size, plain prose, focus on essentials 5/12 측정 시작 시 production 인덱스의 정확한 행 수 (1건) 반영. §시나리오별 insert 표 에서 X 같은 미정값을 모두 구체 수치로 치환하고, 누적 행 수도 명시 (recall 시작 시 42건, 측정 종료 시 142건). 표현·구조 정리: - 회귀(regression) framing 제거 — 본 리포트가 두 측정값을 있는 그대로 비교하도록. 내부 baseline (v1.4.3 5/12) 대비 해석은 외부 (원본 5/14 리포트) 에 위임 - ÷N / ×N 같은 수학 기호 표기를 "N배 빠름/느림" 평어로 일괄 치환 - "사실상", "압도적", "면역", "구조적", "주범" 같은 모호 수식어 제거 → 측정값·메커니즘 으로 대체 - §6 주목할 점 7개 → 3개 (vault_topk 격차, recall 두 변수 합산, searchable 측정 시점) - §8 후속 조사 5개 → 4개. #2 항목을 "vault_topk 가 왜 20배 빨라졌나" 라는 질문 중심으로 재서술 부록: - 14개 시나리오 전체 × 두 측정 × phase 별 n/p50/p95/p99/mean 원본 데이터 추가 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.