Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Ollama local setup gets stuck after startup screen #239

Unanswered
0xdanieltran asked this question in Q&A
Discussion options

image
I've cloned the openclaude and installed environment.
I am running local model - ollama 3.1:8b
But can't go forward after above image...
Please give me any idea how to do..
You must be logged in to vote

Replies: 7 comments 10 replies

Comment options

Moved this into Q&A so it is easier to track and answer.

For a local Ollama setup, the quickest checks are:

  • make sure Ollama is running and the model exists: ollama list
  • from the repo root, try bun run dev:ollama
  • if you are launching the built CLI directly, make sure your provider is configured either through /provider or the relevant OLLAMA_* env vars

If it is still getting stuck after the screen in your screenshot, please paste:

  • your OS
  • the exact terminal output after that point
  • whether this is on latest main or the latest release

That should make it much easier to pinpoint what is blocking startup.

You must be logged in to vote
3 replies
Comment options

image

This is what I am getting after bun run dev:ollama
Not sure what's wrong.

Comment options

What is your Bun version? Because I have this same issue with the Bun version, so can you check and tell ?

Comment options

1.3.11
I think this is latest one.

Comment options

Thanks. Bun 1.3.11 is the version we use in CI too, so that alone is probably not the blocker here.

bun run dev:ollama is the right source-build path, and current main routes Ollama through the OpenAI-compatible provider path.

Please paste text output for:

  • your OS + terminal (PowerShell, CMD, WSL, etc.)
  • bun run doctor:runtime
  • ollama list
  • the full output from bun run dev:ollama

For a working local Ollama launch, the key values should be:

  • CLAUDE_CODE_USE_OPENAI=1
  • OPENAI_BASE_URL=http://localhost:11434/v1
  • OPENAI_MODEL=<your pulled model>

Once we have that text output, we can tell whether this is an Ollama reachability/config problem or a startup/render bug.

You must be logged in to vote
2 replies
Comment options

OS: Windows 11
Terminal: CMD

`bun run doctor:runtime`
$ bun run scripts/system-check.ts
[PASS] Node.js version - 24.3.0
[PASS] Bun runtime - 1.3.11
[PASS] Build artifacts - D:\openclaude\dist\cli.mjs
[PASS] Provider mode - OpenAI-compatible provider enabled.
[PASS] OPENAI_MODEL - llama3.1:8b
[PASS] OPENAI_BASE_URL - http://localhost:11434/v1
[PASS] OPENAI_API_KEY - Configured.
[PASS] Provider reachability - Reached http://localhost:11434/v1/models (status 200).
[PASS] Ollama processor mode - No loaded model found (run a prompt first).
Runtime checks completed successfully.
`ollama list`
NAME ID SIZE MODIFIED 
qwen2.5-coder:7b dae161e27b0e 4.7 GB 3 days ago 
llama3.1:8b 46e0c10c039e 4.9 GB 3 days ago 
llama3.2:3b a80c4f17acd5 2.0 GB 3 days ago
`bun run dev:ollama`
$ bun run scripts/provider-launch.ts ollama
Launching profile: ollama
OPENAI_BASE_URL=http://localhost:11434/v1
OPENAI_MODEL=qwen2.5-coder:7b
OPENAI_API_KEY_SET=false
Runtime doctor failed. Fix configuration before launching.
error: script "dev:ollama" exited with code 1

I am always getting this runtime doctor failed issue for bun run dev:ollama

Comment options

Curl to ollama endpoint is working as well http://localhost:11434/v1

Comment options

new version released! Please try v0.1.8 if this its good.

You must be logged in to vote
0 replies
Comment options

I used this tutorial for local setup : https://www.youtube.com/watch?v=jS54xZUXVDs

I tried :
qwen2.5-coder:14b
gemma4:e4b

I get answers but no tool get called or anything to write to a file or make an hello world. Am I missing something?

You must be logged in to vote
4 replies
Comment options

will look into this? what OpenClaude version are you using?

Comment options

me too.. i'm using v0.18

Comment options

$env:CLAUDE_CODE_USE_OPENAI="1"
$env:OPENAI_BASE_URL="http://192.168.14.245:11434/v1"
$env:OPENAI_API_KEY=""
$env:OPENAI_MODEL="qwen2.5-coder:14b"
openclaude

❯ hi ──────────────────────────────────────────────────────

くろまる { ──────────────────────────────────────────────────────
"name": "Write", /buddy
"arguments": {
"file_path": "/home/user/greeting.txt",
"content": "Hello, user!"
}
}

not work !

Comment options

$env:CLAUDE_CODE_USE_OPENAI="1" $env:OPENAI_BASE_URL="http://192.168.14.245:11434/v1" $env:OPENAI_API_KEY="" $env:OPENAI_MODEL="qwen2.5-coder:14b" openclaude

❯ hi ──────────────────────────────────────────────────────

くろまる { ────────────────────────────────────────────────────── "name": "Write", /buddy "arguments": { "file_path": "/home/user/greeting.txt", "content": "Hello, user!" } }

not work !

hello, I met this same problem. Did you fix this problem? Plz let me know, I have not fixed it for 2 days

Comment options

hello @speccy88 can you try a fresh build from main branch if this issue still persists?

You must be logged in to vote
0 replies
Comment options

Is this still working for others machine?

You must be logged in to vote
1 reply
Comment options

Hey I'm facing this same issue. Did you managed to make this work?

Comment options

Okay, here is a working setup. I'm impressed so far
install this on your machine : https://github.com/ggml-org/llama.cpp
Get this model : https://huggingface.co/ggml-org/gemma-4-E4B-it-GGUF
to get it use this command : llama-server -hf ggml-org/gemma-4-E4B-it-GGUF
use these env :
export CLAUDE_CODE_USE_OPENAI=1
export OPENAI_BASE_URL="http://127.0.0.1:8080/v1"
export OPENAI_MODEL="gemma-4-E4B-it-GGUF"
run it : node openclaude/dist/cli.mjs

If you have a better model, let me know. I only have a MacBook M2 16GB

You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

AltStyle によって変換されたページ (->オリジナル) /