From f3793935bb4e782ecc09dd77567d20ef21d657a5 Mon Sep 17 00:00:00 2001 From: Abdelrahman Abdallah Date: Wed, 1 Apr 2026 22:45:37 +0200 Subject: [PATCH] update readme to include ollama --- README.md | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index f43b399..1e36067 100644 --- a/README.md +++ b/README.md @@ -118,7 +118,7 @@ claw-code/ | Requirement | Details | |-------------|---------| | ๐Ÿ Python | `3.10` or higher | -| ๐Ÿ–ฅ๏ธ Model Server | `vLLM` with tool calling enabled | +| ๐Ÿ–ฅ๏ธ Model Server | `vLLM` or `Ollama`, with tool calling support | | ๐Ÿง  Model | [`Qwen/Qwen3-Coder-30B-A3B-Instruct`](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) (recommended) | --- @@ -146,6 +146,33 @@ curl http://127.0.0.1:8000/v1/models > ๐Ÿ“š **References:** [vLLM Tool Calling Docs](https://docs.vllm.ai/en/v0.13.0/features/tool_calling/) ยท [OpenAI-Compatible Server](https://docs.vllm.ai/en/v0.13.0/serving/openai_compatible_server.html) +### Optional: Use Ollama Instead of vLLM + +`claw-code-agent` can also work with Ollama because the runtime targets an OpenAI-compatible API. Use a model that supports tool calling well. + +Example: + +```bash +ollama serve +ollama pull qwen3 +``` + +Then configure: + +```bash +export OPENAI_BASE_URL=http://127.0.0.1:11434/v1 +export OPENAI_API_KEY=ollama +export OPENAI_MODEL=qwen3 +``` + +Notes: + +- prefer tool-capable models such as `qwen3` +- plain chat-only models are not enough for full agent behavior +- Ollama does not use the `vLLM` parser flags shown above + +> ๐Ÿ“š **References:** [Ollama OpenAI Compatibility](https://docs.ollama.com/api/openai-compatibility) ยท [Ollama Tool Calling](https://docs.ollama.com/capabilities/tool-calling) + ### 2. Configure Environment ```bash