sandboxing repositories
Trending repositories tagged sandboxing, ranked by trending score. Updated daily.
-
1
agent-substrate/substrate
Agent Substrate: the core system
GitHub · Go · 8,035 stars · 881 forks · +427 stars in 24 hours · Trending score 4.98
-
2
pydantic/monty
A secure Python sandbox, written in Rust, for code written by AI.
GitHub · Rust · 8,975 stars · 508 forks · +13 stars in 24 hours · Trending score 2.55
-
3
NVIDIA/NemoClaw
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
GitHub · TypeScript · 23,058 stars · 3,226 forks · +8 stars in 24 hours · Trending score 2.26
-
4
lemonadesaltbagel/crab
CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.
GitHub · Python · 400 stars · 72 forks · +5 stars in 24 hours · Trending score 2.17
-
5
flatpak/xdg-desktop-portal
Desktop integration portal
GitHub · C · 845 stars · 295 forks · +11 stars in 24 hours · Trending score 2.14
-
6
landlock-lsm/rust-landlock
Safe Rust library for Linux Landlock sandboxing
GitHub · Rust · 348 stars · 30 forks · +10 stars in 24 hours · Trending score 1.76
-
7
ruvnet/metaharness
🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
GitHub · TypeScript · 758 stars · 96 forks · +9 stars in 24 hours · Trending score 1.75
-
8
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 and Linux.
GitHub · Rust · 560 stars · 60 forks · +3 stars in 24 hours · Trending score 1.66
-
9
multikernel/sandlock
The lightest sandbox. A process-based sandbox for Linux, no container, no VM, no privilege, no prompt injection
GitHub · Rust · 625 stars · 60 forks · +4 stars in 24 hours · Trending score 1.41
-
10
hartwork/sandwine
:wine_glass: Command-line tool to run Windows apps with Wine and bwrap/bubblewrap isolation on Linux
GitHub · Python · 171 stars · 17 forks · +4 stars in 24 hours · Trending score 1.11
-
11
JanPokorny/locki
Locki: AI sandboxing without the taste of sand
GitHub · Python · 72 stars · 6 forks · +3 stars in 24 hours · Trending score 0.95
-
12
Sanne/incus-spawn
Give your AI coding agents their own machines — not your credentials. Isolated Linux workstations with full autonomy, on Linux and macOS.
GitHub · Java · 57 stars · 31 forks · +1 stars in 24 hours · Trending score 0.92
-
13
inoio/agents-sandbox
Sandbox for AI coding agents (Claude Code, opencode, pi): runs each project in an isolated microVM with host-side secret injection. Linux/KVM & macOS.
GitHub · Go · 91 stars · 10 forks · +2 stars in 24 hours · Trending score 0.92
-
14
laurentftech/pi-outpost
A self-hosted web interface for the pi coding agent: chat, files, documents and an integrated terminal, with the agent's shell confined by OS sandboxes.
GitHub · TypeScript · 31 stars · 3 forks · +2 stars in 24 hours · Trending score 0.87
-
15
tinylabscom/mvm
Manage secure microVMs — one command from zero to secure sessions, locally and remotely.
GitHub · Rust · 49 stars · 8 forks · +2 stars in 24 hours · Trending score 0.82
-
16
getdruks/druks
An operating system for companies: AI agents build and run software tailored to your company. Own your software instead of paying for services you barely use. Agents work in sandboxes, a person approves the important steps, and every run is recorded.
GitHub · Python · 23 stars · 5 forks · +1 stars in 24 hours · Trending score 0.79
-
17
cleatdev/cleat
Give the agent a cage, not your keys. One-command Docker sandbox for AI coding agents: full autonomous permissions, per-project isolation, your host stays untouched.
GitHub · Shell · 19 stars · 0 forks · +2 stars in 24 hours · Trending score 0.72
-
18
Godcreatebugs/raytrace-cli
Sandbox to create a local isolation for agentic run. "Eye of Sauron" for agents, observe everything from file access to network calls with rayTrace sandbox
GitHub · JavaScript · 25 stars · 28 forks · 0 stars in 24 hours · Trending score 0.71
-
19
brekkylab/virtx
Disposable Linux VMs for your own code. Runs microVMs on Linux, macOS and Windows hosts with no Docker or daemon, GPU through Vulkan, and host folders mounted in. Python, Node.js and Rust.
GitHub · Rust · 10 stars · 5 forks · +1 stars in 24 hours · Trending score 0.69
-
20
fhiltscher/awesome-ai-coding-sandboxes
Security-posture-first list of sandboxes for running AI coding agents' code, ranked by isolation, egress control and secrets handling
GitHub · Python · 30 stars · 22 forks · 0 stars in 24 hours · Trending score 0.59
-
21
christopherkarani/rv
Fail-closed policy gate for AI coding agents. Blocks destructive shell commands and secret-file access before they run 95 rule packs, MCP gateway, secrets placeholders, tamper-evident audit. macOS & Linux.
GitHub · Swift · 8 stars · 0 forks · +1 stars in 24 hours · Trending score 0.56
-
22
octelium/cordium
Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials.
GitHub · Go · 88 stars · 11 forks · +1 stars in 24 hours · Trending score 0.54
-
23
brekkylab/ailoy
The open-source agent SDK that gives every agent its own VM. Each VM is a microVM sandbox where the agent installs software, runs code and uses the GPU. Python, Node.js and Rust.
GitHub · Rust · 158 stars · 12 forks · 0 stars in 24 hours · Trending score 0.54
-
24
ProjectRecon/awesome-ai-agents-security
A living map of the AI agent security ecosystem.
GitHub · 81 stars · 162 forks · 0 stars in 24 hours · Trending score 0.51