Ollama
for LuumenAI

Query your own Ollama models from the terminal, alongside everything else

Point Luumen at your Ollama host and use the models you already run. Check what is loaded with OLLAMA_LIST_MODELS, inspect a model's parameters and template with OLLAMA_SHOW, then send prompts through OLLAMA_CHAT or OLLAMA_GENERATE. OpenAI-compatible endpoints are there too. Connect with an API key. Every tool here is read-only.

Book a DemoDownload Luumen

The Ollama toolbox

8 tools, all read-only. They answer instantly, and every call is logged.

  • ReadChat with Ollama modelSend a chat message with conversation history to Ollama.
  • ReadGenerate Text with OllamaGenerate text responses from Ollama models with optional raw mode.
  • ReadList ModelsList all available Ollama models and their details.
  • ReadOpenAI-Compatible Chat CompletionCreate OpenAI-compatible chat completions using Ollama models.
  • ReadOpenAI-Compatible Text CompletionCreate OpenAI-compatible text completions using Ollama models.
  • ReadList Models (OpenAI Compatible)List available models using OpenAI-compatible API format.
  • ReadShow Model InformationShow comprehensive information about an Ollama model.
  • ReadGet Ollama VersionGet the version of Ollama running locally.

Questions

How does LuumenAI connect to Ollama?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in Ollama on its own?

No. Every one of the 8 tools LuumenAI has for Ollama is read-only, so it can answer questions from Ollama but cannot change anything in it. Reads are not gated — they answer immediately, and each one is recorded on the audit trail with the actor and the result.

Who gets access to the integration?

You decide. Access is granted per agent, skill, and team, and per environment — production is not staging.

Is there an audit trail?

Every call to Ollama is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.

All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task statusAffindaRead parsed documents, collections, and annotations — change them with approvalAgent MailGive the agent its own mailbox for reading threads and sending updatesAI/ML APIInspect assistants, threads, and runs — and change them as approved steps

Put Ollama to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.

Book a DemoDownload Luumen