strands-agents/box
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon, with Linux support planned.
Historique des étoiles
7 relevés
| 2026-10-20 | 448 |
| 2026-10-21 | 450 |
| 2026-10-23 | 461 |
| 2026-10-24 | 465 |
| 2026-10-25 | 468 |
| 2026-10-26 | 475 |
- 7 derniers jours
- +27 sur 5,4 jours
- 30 derniers jours
- Historique insuffisant (7 relevés)
- Méthode
- Différences entre les relevés enregistrés. Fonctionnement des tendances
Démarrage rapide
cargo build --release -p strands-box -p strands-box-containmentTiré du README du projet. Happylancing Directory n'exécute ni ne teste le code des dépôts ; vérifiez les commandes avant de les lancer.
Pourquoi il figure au catalogue
GitHub search: LLM projects created recently.
Plus dans Outils et agents d'IA
- JuliusBrussee/caveman115,1 k
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
- NousResearch/hermes-agent257,1 k
The agent that grows with you
- earendil-works/pi117,7 k
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
- heygen-com/hyperframes72,4 k
Write HTML. Render video. Built for agents.
- ggml-org/llama.cpp132,4 k
LLM inference in C/C++
- DietrichGebert/ponytail175,7 k
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.