Claude Code

-

Install

curl -fsSL https://claude.ai/install.sh | bash

https://claude.com/product/claude-code

to setup then run command from command line "claude"

Ollama & Claude Code

below shows how to use local ollama with claude code

https://www.youtube.com/watch?v=FPUsn0ZK000

Can i use Claude Code with Other LLMs ?

The short answer is yes, but it requires a bit of a "workaround" because Claude Code is built specifically to talk to Anthropic's API.

While Anthropic doesn't officially support other models, you can use API proxies or local gateways to "trick" Claude Code into using GPT-4, Gemini, or even local models like Qwen or Llama.

How it Works: The "Base URL" Trick

Claude Code uses an environment variable called ANTHROPIC_BASE_URL to know where to send its requests. By default, this points to Anthropic. By changing this, you can route the traffic through a translator that converts Claude's requests into a format other models understand.
 
1. Using Local Models (Ollama)
This is the most popular way to run Claude Code for free using your own hardware.
  • The Setup: Ollama now provides an Anthropic-compatible endpoint specifically for this.
  • The Command: ```bash
    • export ANTHROPIC_BASE_URL="http://localhost:11434"
    • export ANTHROPIC_AUTH_TOKEN="ollama"
    • claude --model qwen3-coder:32b
  • Best Local Models: As of 2026, Qwen 3.5 Coder and GLM-4.7 are the top choices because they handle Claude Code’s complex "tool-calling" (reading files, running shell commands) better than most.

2. Using Other Cloud Models (LiteLLM or OpenRouter)
If you want to use GPT-4o or Gemini 2.0/3.0, you can use a proxy like LiteLLM or a service like OpenRouter.

  • LiteLLM: You run a small server on your machine that acts as a middleman.
  • OpenRouter: You simply point Claude Code to OpenRouter's API:
Bash 
export ANTHROPIC_BASE_URL="https://openrouter.ai/api"
export ANTHROPIC_AUTH_TOKEN="your-openrouter-key"
claude --model openai/gpt-4o

The Catch: Why Claude is still "Best"
Even though you can use other models, Claude Code was designed for Claude 3.5/3.7 Sonnet. You might run into these issues with other LLMs:
  • Diff Failures: Claude is exceptionally good at producing "diffs" (specific instructions on which lines of code to change). Other models often hallucinate line numbers or fail to provide the exact formatting Claude Code needs to apply the edit automatically. 
  • Tool-Calling Loops: Claude Code is an "agent"—it thinks, then reads a file, then thinks, then runs a test. Other models can get "confused" in these long loops and stop acting or start repeating themselves. 
  • Context Length: Claude Code sends a massive amount of context (it reads your whole repo). Local models need at least 64k context window to work effectively without "forgetting" the task halfway through

Plans
















different types









































Comments

Post a Comment

Popular posts from this blog

Agentic AI Course : Week 1

-
Image
8 weeks https://edwarddonner.com/2024/11/13/llm-engineering-resources/  6 week Agentic AI Course https://github.com/ed-donner/agents the file .env has all the keys select kernel https://github.com/ed-donner/agents/blob/main/1_foundations/1_lab1.ipynb import os openai_api_key = os.getenv( 'OPENAI_API_KEY' ) from openai import OpenAI openai = OpenAI() messages = [{ "role" : "user" , "content" : "What is 2+2?" }] response = openai.chat.completions.create(      model= "gpt-4.1-nano" ,      messages=messages      ) print (response.choices[ 0 ].message.content) Day 2 : what are AI Agents? 5 different patterns for agentic systems https://lavnish.blogspot.com/2025/05/essential-design-patterns-for-building.html In General Day 3 comparing different models  https://www.vellum.ai/llm-leaderboard syntax to call diff LLMs openAI , anthropic, gemini, deepseek, groq https://github.com/ed-donner/agents/blob/main/1_foundations/2_lab2.ipynb...
Read more

LLM Engineering course : Day 1

-
Image
 Anaconda Power Shell    this will open , way you know if it is a anaconda power shell by seeing "base" Then you can install the full environment    then to activate use command "conda activate llms"     Open Ques "what is environment.yml" Then activate the conda environment and open jupyter lab   you can start with virtualenv as well (all details in readme) Video 11 : Day 1 every AI has 2 types of plan 1) pro plan with UI monthly subscription 2) API pricing , pay per request, for OPEN API need to put in 5$ pre payment (can use gpt4-o-mini for less cost)  (all details in readme)  Video 11:  store keys in .env files (all details in readme)  Video 14 there are two types of prompt   Video 15 OpenAI came up with a standard way of interacting with LLMs which is now standard for many LLMs. It is a list of dictionaries. Use completions API https://platform.openai.com/docs/guides/completions   For websites that use Java...
Read more

LLM Engineering : Week 2

-
Day 2.1 setup  anthropic api key google api key (more complex) update .env file     What is Temperature ?  Pass value between 0 to 1. 1 is most creative , 0 is least There is a slight difference in Claude API and OpenAI  in claude API we pass system message and user message separately in claude we also give context  if you want to stream , in claude there is an extra method , in openAI there is a boolean attribute.    Day 2.2 : Gradio         Day 2.3         Day 2.4 Day 2.5          
Read more