lumen
v0.0.42by ory · author: Ory Corp
Precise local semantic code search for coding agents, powered by local embedding models.
What lumen does, in the publisher's words
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.
The payoff is measurable and reproducible: across 9 benchmark runs on 9 languages and real GitHub bug-fix tasks, Lumen cuts cost in every single language, up to 39%. Output tokens drop by up to 66%, sessions complete up to 53% faster, and patch quality is maintained in every task. All verified with a transparent, open-source benchmark framework that you can run yourself.
- Demo
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 2
- MCP servers
- 1
- Stars
- 317
- License
- Apache-2.0
- Repo created
- 2026-02-27
- Last pushed
- 2026-10-11
- Publisher type
- Organization
- Version
- 0.0.42
Links
Skills · 2
- 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.
- 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.
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
MCP servers · 1
- lumenstdio
- ./scripts/run stdio
Read from the plugin's own mcp.json. We list environment variable names, never values.
Category
Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
semantic-search · code-index · mcp · embeddings · ollama · rag
Related by publisher and keywords
Multimodal local search over documents and media, pdf, office files, notes, images, audio and subtitles, from any MCP-capable agent.
Turn any file, PDF, spreadsheet, scan, email, 60+ formats, into clean, agent-ready structured data (Markdown or JSON) without leaving your editor.
Semantic long-term memory and context engine for coding agents. Recall prior knowledge with the find/search/read MCP tools and persist durable facts with remember/write, backed by an OpenViking server.
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production hardening.
Qdrant stores semantic memories and finds related memories with vector search
Universal LLM API client for 174 providers, chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP server.
[](https://agentpluginsdirectory.com/plugins/lumen)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.