C.W.K.
Stream
Lesson 04 of 06 · published

Ollama — Zero-Cost Local + Cloud Tier

~12 min · ollama, local, cloud

Level 0Curious
0 XP0/65 lessons0/17 achievements
0/100 XP to next level100 XP to go0% complete

Local models via localhost:11434

Ollama-Pippa runs entirely on the local machine. No API calls leave the machine. Useful for scheduled background tasks where Claude's degraded service window would otherwise drop the job, and for offline situations.

Native /api/chat

Streams via Ollama's native /api/chat endpoint. Multi-turn tool loop with {type, function: {name, ...}} schema wrapping (Ollama's quirk — flat OpenAI-style schema gets rejected) and tool call ID propagation through the loop.

Sticky model selection

Active model is persisted to <app-data>/ollama_model.txt via POST /api/ollama/model. GET /api/ollama/models lists installed local models. Switching is one click in the brain switcher.

Cloud tier — bigger weights, same wire format

Ollama added a hosted cloud tier in mid-2026: same wire format, same /api/chat shape, just larger weights running on Ollama's servers instead of localhost. cwkPippa exposes a tier toggle in Admin → Ollama; /cloud-models lists the cloud-available weights and the mini/full selector hides on the cloud tier (it doesn't apply). The variant doesn't fork — same adapter, same tool bridge, just a different base URL and an API key in .env when the cloud tier is active.

Tip: Ollama (local or cloud) is the safety net for the heartbeat. When Claude is degraded and Codex/Gemini are also unavailable, scheduled tasks still run — slower, smaller, but they run. The cloud tier gives the safety net more cognitive headroom when the local machine's resources are tight.

Progress

Progress is local-only — sign in to sync across devices.
Spotted a bug or have feedback on this page?Report an Issue
💛 by Pippawarm💛 by Ttoriwarm

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.