AI LLM for Coding: Difference between revisions
mNo edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
==Opencode== | ==Opencode== | ||
https://opencode.ai | [https://opencode.ai] | ||
brew install anomalyco/tap/opencode | brew install anomalyco/tap/opencode | ||
| Line 7: | Line 7: | ||
# initialize Opencode and create/update/improve/compress AGENTS.md file | # initialize Opencode and create/update/improve/compress AGENTS.md file | ||
/init | |||
# update | # update | ||
| Line 24: | Line 24: | ||
==Claude== | ==Claude== | ||
===Web=== | ===Web=== | ||
https://claude.ai | [https://claude.ai] | ||
Pros: Daily reset free quota | * Pros: Daily reset free quota | ||
Cons: Need to manually upload single files | * Cons: Need to manually upload single files | ||
===Console=== | ===Console=== | ||
Claude Console via API and VISA Pre-Paid: https://console.anthropic.com | Claude Console via API and VISA Pre-Paid: [https://console.anthropic.com] | ||
Pros: | * Pros: Fully integrated in codebase | ||
Cons: | * Cons: Costs money (e.g., 5€ are easily spent) | ||
npm install -g @anthropic-ai/claude-code | npm install -g @anthropic-ai/claude-code | ||
cd myProject | cd myProject | ||
claude | claude | ||
==Google Gemini== | ==Google Gemini== | ||
Pros: Free to use with | * Pros: Free to use with Google account | ||
Create your API key at [https://aistudio.google.com/app/api-keys] | |||
Install | Install | ||
| Line 44: | Line 45: | ||
# or just run | # or just run | ||
npx https://github.com/google-gemini/gemini-cli | npx https://github.com/google-gemini/gemini-cli | ||
Usage | Usage | ||
cd /tmp | cd /tmp | ||
| Line 58: | Line 60: | ||
==Google Antigravity== | ==Google Antigravity== | ||
https://antigravity.google/download | [https://antigravity.google/download] | ||
==Tips== | ==Tips== | ||
| Line 64: | Line 66: | ||
* Use tools for code formatting, linting, type-hints | * Use tools for code formatting, linting, type-hints | ||
* Configure these tools to produce minimum output to reduce token consumption. e.g. for | * Configure these tools to produce minimum output to reduce token consumption. e.g. for | ||
** Prettier: | ** Prettier: --log-level silent | ||
** Cypress: cypress run --e2e --quiet | ** Cypress: cypress run --e2e --quiet | ||
* For Refactoring/renaming: better do it manually, via VSCode, that is a lot faster | * For Refactoring/renaming: better do it manually, via VSCode, that is a lot faster | ||
===Cavemen style=== | ===Cavemen style=== | ||
https://github.com/JuliusBrussee/caveman | [https://github.com/JuliusBrussee/caveman] | ||
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 | 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: | It can be replaced by 6 hard coded lines in AGENTS.md: | ||
Respond like smart caveman. Cut all filler, keep technical substance. | Respond like smart caveman. Cut all filler, keep technical substance. | ||
| Line 84: | Line 85: | ||
===Context7=== | ===Context7=== | ||
https://context7.com offers an MCP server of latest spec to many languages, enabling the LLM to support latest versions and best practice. | [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 | npx ctx7 setup | ||
In prompt write: | In prompt write: | ||
use context7. do xxx | use context7. do xxx | ||
Revision as of 07:10, 9 June 2026
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 [2]
uv tool install mistral-vibe # run via vibe
Claude
Web
- Pros: Daily reset free quota
- Cons: Need to manually upload single files
Console
Claude Console via API and VISA Pre-Paid: [4]
- Pros: Fully integrated in codebase
- Cons: Costs money (e.g., 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 [5]
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
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
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 [8] 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
[9] 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