lumen
PluginPrecise 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.
Install
claude plugin install lumen@claude-plugins-officialWhat is lumen?
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.
What's inside
7 bundled components — installing the plugin installs all of them.
Skills (3)
add-benchmark
doctor
Run a health check on the bundled Lumen semantic search setup for the current project, verify backend reachability and index freshness, and summarize remediation steps.
Name also used by databricks, remember
reindex
Refresh or rebuild the bundled Lumen index for the current project, preferring MCP-driven refreshes and using the CLI only for an explicit clean rebuild.
Subagents (2)
What this can do
Capabilities declared by the plugin's own components — read straight from their frontmatter, not inferred.
Inherit all session tools
5 components declare no tool restrictions
~80 tokens of context used while enabled, before you invoke anything
Trust
87/100 · Excellent2 factors scored below maximum
Documentation
README · ~12 min read
Claude reads entire files to find what it needs. Lumen gives it a map.
Lumen is a 100% local semantic code search engine for AI coding agents. No API keys, no cloud, no external database, just open-source embedding models (Ollama or LM Studio), SQLite, and your CPU. A single static binary and your own local embedding server.
Reviews
Log in to leave a review.
No reviews yet — be the first.
Explore related
Other things in this space — across every part of the ecosystem, not just plugins.
Pluginssimilar to this one
All plugins →feature-dev
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
32.9K stars
code-modernization
Modernize legacy codebases (COBOL, legacy Java/C++, monolith web apps) with a structured preflight / assess / map / extract-rules / brief / reimagine / transform / harden workflow, an interactive topology viewer, and specialist review agents
32.9K stars
clangd-lsp
C/C++ language server (clangd) for code intelligence
32.8K stars
Skills
All skills →plugin-structure
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin director
32.8K stars
Agent-Skills-for-Context-Engineering
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
17.5K stars
ai-setup
Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files for Claude Code, Cursor, and Codex.
1.2K stars
MCP Servers
All mcp servers →dbhub
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
3.3K stars
TinyFish AI Web Agent
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
dev-changes
Turn described changes into reviewed pull requests: propose, triage, review, dependency audits.
Commands
All commands →feature-dev
Guided feature development with codebase understanding and architecture focus
32.8K stars
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests
32.8K stars
modernize-extract-rules
Mine business logic from legacy code into testable, human-readable rule specifications
32.8K stars
Subagents
All subagents →architecture-critic
Reviews proposed target architectures and transformed code against modern best practice. Adversarial — looks for over-engineering, missed requirements, and simpler alternatives.
32.8K stars
code-architect
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences
32.8K stars
legacy-analyst
Deep-reads legacy codebases (COBOL, Java, .NET, Node, anything) to build structural and behavioral understanding. Use for discovery, dependency mapping, dead-code detection, and "what does this system actually do" questions.
32.8K stars