mavdol/capsule
A secure, durable runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.
This is for developers building AI agent systems that need to run custom code from users or third-parties. It helps ensure that each AI agent task runs securely and reliably, preventing misbehaving code from affecting the main system. Developers define tasks in Python or TypeScript, which are then executed in isolated environments with set limits on CPU, memory, and runtime.
225 stars.
Use this if you are a developer building AI agent platforms and need to execute potentially untrusted code safely, reliably, and at scale.
Not ideal if you are looking for a ready-to-use AI agent solution and not a developer tool for building one.
Stars
225
Forks
12
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/mavdol/capsule"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
e2b-dev/E2B
Open-source, secure environment with real-world tools for enterprise-grade agents.
alibaba/OpenSandbox
OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language...
e2b-dev/infra
Infrastructure that's powering E2B Cloud.
always-further/nono
Secure, kernel-enforced sandbox CLI and SDKs for AI agents. Capability-based isolation with...
boxlite-ai/boxlite
Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.