Memory issues while trying to set up Openclaw locally with Ollama.
Hi there! Managed to get openclaw running and tied together with ollama,
The agent responds via dashboard, but not TUI. Shows "(no output)". It responds to the latest message via dashboard but has no recollection of the previous messages. Trying to also set up local embeddings with ollama. Will use glm-4.7-flash:latest for local embeddings via Ollama. Can you please help? Thank you!
Here is the openclaw.json contents:
{
"meta": {
"lastTouchedVersion": "2026.1.29",
"lastTouchedAt": "2026-01-31T00:21:15.834Z"
},
"wizard": {
"lastRunAt": "2026-01-26T02:17:41.790Z",
"lastRunVersion": "2026.1.24-3",
"lastRunCommand": "onboard",
"lastRunMode": "local"
},
"models": {
"providers": {
"ollama": {
"baseUrl": "http://127.0.0.1:11434/v1",
"apiKey": "ollama-local",
"api": "openai-responses",
"models": [
{
"id": "glm-4.7-flash:latest",
"name": "GLM-4.7 Flash",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "ollama/glm-4.7-flash:latest"
},
"workspace": "/home/local/.openclaw/workspace",
"compaction": {
"mode": "safeguard"
},
"maxConcurrent": 4,
"subagents": {
"maxConcurrent": 8
}
}
},
"messages": {
"ackReactionScope": "group-mentions"
},
"commands": {
"native": "auto",
"nativeSkills": "auto"
},
"gateway": {
"port": 18789,
"mode": "local",
"bind": "loopback",
"auth": {
"mode": "token",
"token": "redacted"
},
"tailscale": {
"mode": "off",
"resetOnExit": false
}
}
}
The agent responds via dashboard, but not TUI. Shows "(no output)". It responds to the latest message via dashboard but has no recollection of the previous messages. Trying to also set up local embeddings with ollama. Will use glm-4.7-flash:latest for local embeddings via Ollama. Can you please help? Thank you!
Here is the openclaw.json contents:
{
"meta": {
"lastTouchedVersion": "2026.1.29",
"lastTouchedAt": "2026-01-31T00:21:15.834Z"
},
"wizard": {
"lastRunAt": "2026-01-26T02:17:41.790Z",
"lastRunVersion": "2026.1.24-3",
"lastRunCommand": "onboard",
"lastRunMode": "local"
},
"models": {
"providers": {
"ollama": {
"baseUrl": "http://127.0.0.1:11434/v1",
"apiKey": "ollama-local",
"api": "openai-responses",
"models": [
{
"id": "glm-4.7-flash:latest",
"name": "GLM-4.7 Flash",
"reasoning": true,
"input": [
"text"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 128000,
"maxTokens": 8192
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "ollama/glm-4.7-flash:latest"
},
"workspace": "/home/local/.openclaw/workspace",
"compaction": {
"mode": "safeguard"
},
"maxConcurrent": 4,
"subagents": {
"maxConcurrent": 8
}
}
},
"messages": {
"ackReactionScope": "group-mentions"
},
"commands": {
"native": "auto",
"nativeSkills": "auto"
},
"gateway": {
"port": 18789,
"mode": "local",
"bind": "loopback",
"auth": {
"mode": "token",
"token": "redacted"
},
"tailscale": {
"mode": "off",
"resetOnExit": false
}
}
}
The AI that actually does things. Emails, calendar, home automation - all from your favorite chat app. New shell, ready to help. The lobster way.
83,815Members
Resources
Similar Threads
Was this page helpful?
