Frontmatter
| id | 9644 |
| title | Add Neo.ai.provider.Ollama base adapter |
| state | Closed |
| labels | aiarchitecturefeature |
| assignees | tobiu |
| createdAt | Apr 3, 2026, 12:47 PM |
| updatedAt | Apr 3, 2026, 12:53 PM |
| githubUrl | https://github.com/neomjs/neo/issues/9644 |
| author | tobiu |
| commentsCount | 1 |
| parentIssue | 9639 |
| subIssues | [] |
| subIssuesCompleted | 0 |
| subIssuesTotal | 0 |
| blockedBy | [] |
| blocking | [] |
| closedAt | Apr 3, 2026, 12:53 PM |
Add Neo.ai.provider.Ollama base adapter
Closedaiarchitecturefeature

Parent Epic: #9639
Problem
The framework needs to interface directly with a local
ollama run gemma-4daemon to handle the "Night Shift" REM mode tasks.Solution
Create
src/ai/provider/Ollama.mjs(or equivalent location) extending a base provider.generateContentmapped to the Ollama/api/generateendpoint.chat/sendMessagemapped to Ollama/api/chat.