LearnNewsExamplesServices
Frontmatter
id9639
titleLocal LLM Provider Adapter (Ollama + Gemma-4)
stateClosed
labels
epicaiarchitecture
assigneestobiu
createdAtApr 3, 2026, 12:44 PM
updatedAtApr 3, 2026, 1:02 PM
githubUrlhttps://github.com/neomjs/neo/issues/9639
authortobiu
commentsCount0
parentIssue9638
subIssues
9644 Add Neo.ai.provider.Ollama base adapter
9645 Configure Agent.mjs to orchestrate mixed providers
subIssuesCompleted2
subIssuesTotal2
blockedBy[]
blocking[]
closedAtApr 3, 2026, 1:02 PM

Local LLM Provider Adapter (Ollama + Gemma-4)

Closedepicaiarchitecture
tobiu
tobiu commented on Apr 3, 2026, 12:44 PM

Parent Epic: #9638

Problem

Currently, Neo.ai.Agent only supports the Gemini API cloud provider. To support local execution (Dream Mode / Swarm) with consumer hardware, we need a local adapter.

Solution

Create Neo.ai.provider.Ollama to conform to the provider interface, targeting the Gemma-4 model.

  • Implement standard /api/generate and /api/chat interaction APIs.
  • Ensure prompt parameter structure aligns with existing agent infrastructure.
tobiu added the ai label on Apr 3, 2026, 12:44 PM
tobiu added the architecture label on Apr 3, 2026, 12:44 PM
tobiu added the feature label on Apr 3, 2026, 12:44 PM
tobiu added parent issue #9638 on Apr 3, 2026, 12:44 PM
tobiu removed the feature label on Apr 3, 2026, 12:46 PM
tobiu added the epic label on Apr 3, 2026, 12:46 PM
tobiu cross-referenced by #9644 on Apr 3, 2026, 12:47 PM
tobiu cross-referenced by #9645 on Apr 3, 2026, 12:47 PM
tobiu added sub-issue #9644 on Apr 3, 2026, 12:47 PM
tobiu added sub-issue #9645 on Apr 3, 2026, 12:47 PM
tobiu assigned to @tobiu on Apr 3, 2026, 1:00 PM
tobiu closed this issue on Apr 3, 2026, 1:02 PM