Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By cwensel
Index your local PDFs, markdown files, and source code into a searchable dual-index (Qdrant for semantic vector search, MeiliSearch for full-text keyword search) via the arc CLI, then query across corpora with conceptual or exact-term lookups — including agent memory persistence.
npx claudepluginhub cwensel/arcaneum --plugin arcManage Qdrant collections (semantic search only)
Configuration and cache management
Manage container services (Qdrant, MeiliSearch)
Manage dual-index corpora (recommended)
Check that all Arcaneum prerequisites are met and the system is ready for use.
Qdrant collection management for semantic search. Use when user mentions managing collections, creating collection, listing collections, verifying collection integrity, exporting or importing collections, or viewing indexed items in Qdrant.
Docker container management for Qdrant and MeiliSearch services. Use when user mentions starting services, stopping services, checking container status, viewing logs, restarting containers, or resetting database services.
Dual-index corpus management for combined semantic and full-text search. Use when user mentions corpus, dual indexing, syncing content to both Qdrant and MeiliSearch, checking parity between systems, deleting corpora, or managing content that needs both search types.
MeiliSearch index management for full-text search. Use when user mentions managing indexes, creating index, listing indexes, verifying index health, exporting or importing indexes, or viewing indexed items in MeiliSearch.
Search indexed corpora using semantic (vector) OR full-text (keyword) search via the arc CLI. Use when the user asks to search, find, look up, or query a corpus, collection, knowledge base, codebase, docs, PDFs, or markdown. Covers both conceptual queries and exact-term lookups.
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Search your local documents with natural language. Index folders of PDFs, Word docs, markdown, and more — then ask questions in English or German and get answers with source citations.
Document search with hybrid BM25/semantic retrieval, GraphRAG knowledge graphs, and pluggable providers for Claude Code. Index documentation and code, then search using keyword matching, semantic similarity, graph relationships, or comprehensive multi-mode fusion.
Optimized file search, semantic indexing, and persistent memory for Claude Code — with optional sync to a self-hosted web dashboard
Precise local semantic code search via MCP. Indexes your codebase with Go AST parsing, embeds with Ollama or LM Studio, and exposes vector search to Claude through an MCP server — no cloud, no npm.
Beacon — semantic code search for Claude Code
A vector-powered CLI for semantic search over files (Vexor skill bundle).
CLI tools and Claude Code plugins for semantic and full-text search.
pipx install "https://github.com/cwensel/arcaneum/releases/download/v0.7.0/arcaneum-0.7.0-py3-none-any.whl"
Arcaneum helps you discover and understand project dependencies, documentation, and reference implementations. By indexing libraries, frameworks, and technical papers, you can semantically search for patterns, APIs, and concepts when building new projects. Works especially well with the RDR (Recommendation Data Record) model for AI-assisted development planning.
The system supports PDF documents and source code with git-aware, AST-based chunking.
Currently Available:
arc corpus sync --max-embedding-batch, --text-workers, --cpu-workers, and
single-system indexing flags such as --embedding-batch-size and --process-priorityarcaneum[sentence-transformers]arcaneum[sentence-transformers]arcaneum[sentence-transformers]arcaneum[sentence-transformers]arcaneum[sentence-transformers]See arc models list for complete model information and recommendations.
Use arc models list --json for the LLM-readable catalog: it includes backend,
recommended and default corpus uses, support/risk tier, prompt policy, context
limit, hardware support, runtime-aligned batch guidance, and reindex warnings.
Arcaneum records each collection's embedding prompt policy when it is indexed. Reindex a corpus after changing model query/document prompts, tasks, or prompt-aware model defaults; semantic search rejects collections whose stored prompt policy no longer matches the current model registry.
--gpu to opt into accelerator embeddingARC_EXPERIMENTAL_COREML=1/arc:search, /arc:index, /arc:collection, etc.)/help or /commands in Claude CodeGet started with Arcaneum in just a few commands:
# 1. Install
pipx install "https://github.com/cwensel/arcaneum/releases/download/v0.7.0/arcaneum-0.7.0-py3-none-any.whl"
# 2. Install Claude Code plugin (optional, in Claude Code)
# /plugin install cwensel/arcaneum
# 3. Verify and start services
arc doctor
arc container start
# 4. Create a corpus and sync content (indexes to both Qdrant and MeiliSearch)
arc corpus create Frameworks --type code
arc corpus sync Frameworks ~/libs/fastapi ~/libs/sqlalchemy