Jump to content

AI LLM for Coding: Difference between revisions

From Torben's Wiki
No edit summary
No edit summary
Line 9: Line 9:
https://opencode.ai
https://opencode.ai
  brew install anomalyco/tap/opencode
  brew install anomalyco/tap/opencode
npx ctx7 setup --opencode


==Context7==
==Context7==
https://context7.com
https://context7.com
npx ctx7 setup --opencode


==Google Gemini==
==Google Gemini==
Line 64: Line 66:
  npx skills add JuliusBrussee/caveman -a github-copilot
  npx skills add JuliusBrussee/caveman -a github-copilot
It has an option to install to local home dir instead of to project repo.
It has an option to install to local home dir instead of to project repo.
According to https://medium.com/@KubaGuzik/i-benchmarked-the-viral-caveman-prompt-to-save-llm-tokens-then-my-6-line-version-beat-it-d8e565f95e15
It can be replaced by 6 hard coded lines in AGENTS.md:
Respond like smart caveman. Cut all filler, keep technical substance.
- Drop articles (a, an, the), filler (just, really, basically, actually).
- Drop pleasantries (sure, certainly, happy to).
- No hedging. Fragments fine. Short synonyms.
- Technical terms stay exact. Code blocks unchanged.
- Pattern: [thing] [action] [reason]. [next step].

Revision as of 02:44, 9 June 2026

Mistral Devstral

uv tool install mistral-vibe
# run via
vibe

Obtain API key from [1]

Opencode

https://opencode.ai

brew install anomalyco/tap/opencode
npx ctx7 setup --opencode

Context7

https://context7.com

npx ctx7 setup --opencode

Google Gemini

pros: free to use with google account create your API key at https://aistudio.google.com/app/api-keys

Install

npm install -g @google/gemini-cli@latest
gemini
# or just run
npx https://github.com/google-gemini/gemini-cli

usage

cd /tmp
export GEMINI_API_KEY="xxx"
git clone https://github.com/entorb/meeting-meter
cd myProject
gemini

to switch model from pro to flash:

export GEMINI_MODEL="gemini-2.5-flash"

secret alternative: .env file

GEMINI_API_KEY=xxx

Google Antigravity

https://antigravity.google/download

Claude

Web

https://claude.ai
pro: Daily reset free quota
cons: need to manually upload single files

Console

Claude Console via API and VISA Pre-Paid: https://console.anthropic.com
pro: fully integrated in code base
cons: costs money, 5€ are easily spend

npm install -g @anthropic-ai/claude-code
cd myProject
claude

Tips

  • E2E tests (e.g. Cypress) are very important
  • Use tools for code formatting, linting, type-hints
  • Configure these tools to produce minimum output to reduce token consumption. e.g. for
    • Prettier: --log-level silent
    • Cypress: cypress run --e2e --quiet
  • For Refactoring/renaming: better do it manually, via vscode, that is a lot faster

Cavemen style

https://github.com/JuliusBrussee/caveman

npx skills add JuliusBrussee/caveman -a github-copilot

It has an option to install to local home dir instead of to project repo.

According to https://medium.com/@KubaGuzik/i-benchmarked-the-viral-caveman-prompt-to-save-llm-tokens-then-my-6-line-version-beat-it-d8e565f95e15

It can be replaced by 6 hard coded lines in AGENTS.md:

Respond like smart caveman. Cut all filler, keep technical substance.
- Drop articles (a, an, the), filler (just, really, basically, actually).
- Drop pleasantries (sure, certainly, happy to).
- No hedging. Fragments fine. Short synonyms.
- Technical terms stay exact. Code blocks unchanged.
- Pattern: [thing] [action] [reason]. [next step].