agent-substrate/substrate
Can I trust it?
No red flags in our checks.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A Kubernetes-based zero-trust runtime for sandboxed agents, written in Go. It maps many stateful actors onto a smaller pool of worker pods, snapshotting idle actors out of memory and restoring them on request. Sandboxes use gVisor or Cloud Hypervisor microVMs, with per-actor…
Who it's for
Platform engineers running large numbers of untrusted, mostly idle AI agents on Kubernetes
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up agent-substrate/substrate in my project. Follow its README: https://github.com/agent-substrate/substrate. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/agent-substrate/substrate?ref=badge)Similar repos
- comp-work/gke-sandboxes
A self-hosted TypeScript client and deployment for running isolated Linux sandboxes on Google Kubernetes Engine with gVisor. Sandboxes run commands, keep files, sleep to Cloud Storage snapshots when i
- opensandbox-group/OpenSandbox
Runtime and API for running AI agent workloads in isolated sandboxes on your own infrastructure. Sandboxes support command execution, file management, code execution, and browser or desktop automation
- guregodevo/memdoor
A headless coding and automation agent distributed as a single Go CLI binary, with no Docker or Python required. It runs locally or on a remote machine over SSH, and includes a multi-agent harness, YA
- ai-openshell/openshell
A runtime that runs autonomous AI agents in isolated sandboxes. Kernel-level controls limit the files, system calls and network connections each agent can use, enforced by a declared policy. Credentia
- smhanov/agentloop
A Go library that implements the LLM tool-calling loop: it sends prompts to a model, executes requested tool calls, feeds results back, and repeats until a final answer. It adds budgets, hooks, skills
- vicotrbb/cubebot
A Kubernetes-native runtime for persistent AI agents with shared rooms, memories and skills. It is a minimal text-chat MVP with sign-in, agent management, an encrypted OpenAI connection and one perman