Reka — Claude Code Plugin

RAG-powered AI development for any codebase
Semantic search · Project memory · Architecture decisions · Coding workflows

---

Overview

Reka is a Claude Code plugin that connects your AI assistant to a shared RAG (Retrieval-Augmented Generation) infrastructure. It gives Claude persistent project memory, semantic codebase search, architecture awareness, and structured development workflows — across sessions and team members.

What you get

Capability	How it works
Semantic search	Search code, docs, and Confluence by meaning, not just keywords
Project memory	Decisions, patterns, and insights persist across sessions via Ebbinghaus-inspired retention
Architecture awareness	ADRs, dependency graphs, blast radius analysis before every change
Structured workflows	5-phase coding, deep investigation, tribunal debates, and more
Auto session lifecycle	Hooks start/end RAG sessions automatically, trigger memory consolidation
Quality gates	Auto-format with Prettier, TypeScript type-check on every edit

---

Quick Start

1. Add marketplace

/plugin marketplace add getreka/reka-plugin

2. Install plugin

/plugin install reka@reka-plugins

3. Configure

On first enable, Claude Code prompts for three settings:

Setting	Description	Example
RAG API URL	Your RAG API server	http://localhost:3100
RAG API Key	Authentication key (stored in OS keychain)	e699194c-...
Project Name	Collection namespace	myapp

Team auto-install

Add to your project's .claude/settings.json so everyone gets it automatically:

{
  "extraKnownMarketplaces": {
    "reka-plugins": {
      "source": { "source": "github", "repo": "getreka/reka-plugin" }
    }
  },
  "enabledPlugins": {
    "reka@reka-plugins": true
  }
}

---

Commands

Coding & Review

Command	Description
/reka:code	5-phase workflow: context → plan → implement → verify → remember
/reka:investigate	Deep research — find, trace, debug. Saves to memory, never modifies code
/reka:review	Architecture-aware code review against patterns and ADRs

Architecture

Command	Description
/reka:arch	Record and analyze architecture decisions (ADRs)
/reka:debate	Adversarial tribunal debate for complex decisions (2-4 positions)

Session & Memory

Command	Description
/reka:start	Start a RAG session, display project stats
/reka:end	Save knowledge, close session, trigger memory consolidation
/reka:memory-review	Triage quarantine queue, promote/reject auto-extracted memories

Setup

Command	Description
/reka:onboard	Set up RAG for a new project: configure, index, verify
/reka:restart-api	Rebuild and restart local rag-api server

---

Agents

Agent	Model	Purpose
reka:feature-builder	Sonnet	Implements features with RAG context (patterns, ADRs, graph)
reka:code-reviewer	Sonnet	Reviews code against project patterns and ADRs
reka:test-writer	Sonnet	Generates tests (auto-detects vitest/jest/mocha)
reka:rag-researcher	Haiku	Researches codebase via semantic search and graph traversal
reka:rag-ops	Haiku	Operations: indexing, collections, memory maintenance

All agents have persistent memory (memory: project) — they learn your codebase patterns across sessions.

---

Hooks

Event	Action
SessionStart	Auto-starts RAG session, injects RAG_SESSION_ID env var
PreToolUse (Edit/Write)	Warns if no RAG session is active
PostToolUse (Edit/Write)	Runs Prettier + TypeScript type-check (auto-detects tsconfig.json)
Stop	Ends RAG session, triggers consolidation agent for LTM extraction

---

Skills

Reference skills loaded automatically by commands and agents:

• memory-protocol — Session lifecycle, smart remember with relationship detection, memory type selection, structured facts
• rag-workflows — Search tool priority guide (Grep → find_symbol → hybrid_search → search_graph → context_briefing)
• obsidian-sync — Bidirectional sync between RAG memories and Obsidian vault

---

Architecture

Claude Code
  │
  └── Reka Plugin
        ├── 10 Commands (/reka:code, /reka:investigate, ...)
        ├── 5 Agents (feature-builder, code-reviewer, ...)
        ├── 3 Skills (memory-protocol, rag-workflows, obsidian-sync)
        ├── 4 Hooks (session lifecycle, quality gates)
        │
        └── MCP Server (@getreka/mcp)
              │  35 core tools: search, memory, architecture, sessions, agents
              │
              └── RAG API
                    ├── Qdrant — vector database
                    ├── BGE-M3 / OpenAI — embeddings (1024d / 1536d)
                    └── Ollama / Claude — LLM (hybrid routing)

---

Prerequisites

• RAG API server running (shared-ai-infra)
• Qdrant vector database
• Embedding service — BGE-M3 (recommended) or OpenAI

Optional but recommended:

• typescript-lsp@claude-plugins-official for TypeScript code intelligence
• Obsidian for memory visualization (via /reka:obsidian-sync skill)

---

Local Development

claude --plugin-dir ./reka-plugin

Use /reload-plugins after making changes to pick up updates without restarting.

---

License

BSL-1.1