Troubleshooting

What to do when OpenClaw doesn't find its model, loses a turn or keeps starting outside Link (OpenClaw).

"OpenClaw runs local models through Ollama"

The model is in LM Studio, llama.cpp, vLLM or Jan. Pull it in Ollama, or use Hermes.

No local model offered

Ollama isn't installed or isn't running. Install it, then start it:

lnk up models
ollama serve

It answers "Auto-compaction could not recover this turn"

The model's context window was too small. lnk agent start again sets 32,768 tokens. A model that can't hold that much needs more memory, or a hosted model.

Something else on your Mac uses port 18789

Or the ports after it. Stop it, because main's ports are fixed. Another agent's are in its own block (lnk agent list --json).

Its own service, from before Link ran it, is still installed outside its home. See Clean up an old OpenClaw install.