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.
Sternverlauf
7 Snapshots
| 2026-10-20 | 448 |
| 2026-10-21 | 450 |
| 2026-10-23 | 461 |
| 2026-10-24 | 465 |
| 2026-10-25 | 468 |
| 2026-10-26 | 475 |
- Letzte 7 Tage
- +27 in 5,4 Tagen
- Letzte 30 Tage
- Zu wenig Verlauf (7 Snapshots)
- Methode
- Differenzen zwischen gespeicherten Snapshots. So funktionieren Trends
Schnellstart
cargo build --release -p strands-box -p strands-box-containmentAus der README des Projekts übernommen. Happylancing Directory führt keinen Repository-Code aus und testet ihn nicht; prüfe Befehle, bevor du sie ausführst.
Warum es im Katalog ist
GitHub search: LLM projects created recently.
Mehr in KI-Tools und Agenten
- JuliusBrussee/caveman115.107
🪨 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-agent257.141
The agent that grows with you
- earendil-works/pi117.676
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
- heygen-com/hyperframes72.420
Write HTML. Render video. Built for agents.
- ggml-org/llama.cpp132.382
LLM inference in C/C++
- DietrichGebert/ponytail175.745
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.