Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.
Source
GitHub
Langage
Python
Dernière activité
17 oct. 2026
Étoiles0Mesuré · 19 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative
Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.
Source
GitHub
Langage
Python
Dernière activité
18 oct. 2026
Étoiles0Mesuré · 19 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative
50 règles .mdc testées en production pour le mode agent Cursor, couvrant React, TypeScript, Python, Go, Rust, Vue.js, Swift, Ruby on Rails, Kubernetes, Docker, Deno et autres.
Source
GitHub
Dernière activité
31 mai 2026
Étoiles0Mesuré · 18 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative
🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.
Outil permettant de mentionner des agents de codage ACP depuis Slack, GitHub, GitLab, Linear ou Lark, qui exécute le code localement et retourne les résultats vérifiés.
Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine fan-out, councils, session handoff, spend caps, MCP server, ACP agent.