AI LLM for Coding

Opencode

brew install anomalyco/tap/opencode

# add context7 MCP
npx ctx7 setup --opencode

# initialize Opencode and create/update/improve/compress AGENTS.md file
/init
 
# update
brew update
brew upgrade anomalyco/tap/opencode

For saving of tokens, add Caveman speech to AGENTS.md

Mistral Devstral

Obtain API key from [1]

uv tool install mistral-vibe
# run via
vibe

Claude

Web

https://claude.ai
Pros: Daily reset free quota
Cons: Need to manually upload single files

Console

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

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

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

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].

Context7

https://context7.com offers an MCP server of latest spec to many languages, enabling the LLM to support latest versions and best practice.

npx ctx7 setup

In prompt write:

use context7. do xxx