k8eDeepSeek Harness plugin

k8e.sh — Open Source Agentic AI Sandbox Matrix. A single binary under 100MB that turns any Linux host into a secure, isolated execution platform for AI agents — gVisor, Kata, or Firecracker isolation, warm-pool fast starts, and an E2B-compatible API. Up and running in 60 seconds.

bash
curl -sfL https://k8e.sh/install.sh | sh -

That's it. Your agentic sandbox matrix is ready. 🤖

📖 Table of Contents

🤖 What is K8E?

K8E is the Open Source Agentic AI Sandbox Matrix — a self-hosted sandbox platform for running secure, isolated AI agent workloads at scale, packaged as a single binary under 100MB.

As autonomous AI agents increasingly generate and execute untrusted code, robust sandboxing infrastructure is no longer optional. K8E ships everything needed to spin up a production-grade cluster in under 60 seconds, with first-class primitives for agent isolation, resource governance, and ephemeral execution environments — purpose-built for the AI era.

🔒 One cluster. Many agents. Zero trust between them.

Sandbox Capabilities

🏗️ Architecture

 AI Agents (Claude Code / Codex / Pi / dsh)
        │  k8e-sandbox-cli / plugin tools    (gRPC over mTLS)
        ▼
┌──────────────────────────────────────────────┐
│              SANDBOX GATEWAY                 │
│  sessions · exec · files · PTY terminals     │
│  expose · allow-hosts · snapshots            │
│  warm pool · metrics · event stream          │
└──────────────┬───────────────────────────────┘
               │ claims ready pods from the warm pool
   ┌───────────▼───────────┐   ┌────────────────┐
   │   SANDBOX POD         │   │   SANDBOX POD  │
   │   gVisor / Kata / FC  │ … │   (isolated)   │
   │   agent's code + fs   │   │                │
   └───────────────────────┘   └────────────────┘
        eBPF per-session network policy between all of them

One gateway fronts every operation — session lifecycle, streaming exec, filesystem, PTY terminals, service exposure (expose), live egress policy (allow-hosts) and content-addressed snapshots — so agents get one audited door instead of raw infrastructure access.

⚙️ Components

🚀 Quick Start

Step 1 — Install a Sandbox Runtime (recommended: before K8E)

Install the runtime shim before K8E so it is auto-detected on first startup. gVisor is recommended — no KVM required.

bash
1# Download runsc + containerd-shim-runsc-v1 directly from the gVisor release bucket (requires wget)
2ARCH=$(uname -m)   # x86_64 on most servers, aarch64 on ARM
3URL=https://storage.googleapis.com/gvisor/releases/release/latest/${ARCH}
4
5wget ${URL}/runsc ${URL}/runsc.sha512 \
6     ${URL}/containerd-shim-runsc-v1 ${URL}/containerd-shim-runsc-v1.sha512
7
8sha512sum -c runsc.sha512 -c containerd-shim-runsc-v1.sha512   # both must print OK
9chmod +x runsc containerd-shim-runsc-v1
10sudo mv runsc containerd-shim-runsc-v1 /usr/local/bin/
11ls -l /usr/local/bin/runsc /usr/local/bin/containerd-shim-runsc-v1   # verify both installed

K8E detects runsc at startup and automatically injects the gVisor stanza into its containerd config (/var/lib/k8e/agent/etc/containerd/config.toml). Do not run runsc install — K8E manages its own containerd configuration.

Need stronger isolation? See Sandbox Runtime Setup for Kata Containers and Firecracker.

Step 2 — Install K8E

bash
curl -sfL https://k8e.sh/install.sh | sh -

Step 3 — Verify the Sandbox

bash
k8e-sandbox-cli status        # -> {"available": true, ...}
k8e-sandbox-cli run 'echo hello from the sandbox'

(Optionally, with KUBECONFIG=/etc/k8e/k8e.yaml: kubectl -n sandbox-matrix get pods shows the warm-pool pods.)

Step 4 — Download Sandbox CLI & Connect Your AI Agent

Download the standalone sandbox CLI, authenticate, and install the skill into your agent:

bash
1# Download sandbox CLI (~44MB) — pick your platform suffix
2#   k8e-sandbox-cli-linux-amd64 / linux-arm64 / darwin-amd64 / darwin-arm64 / windows-amd64.exe
3curl -sLO https://github.com/xiaods/k8e/releases/latest/download/k8e-sandbox-cli-linux-amd64
4chmod +x k8e-sandbox-cli-linux-amd64
5
6# Symlink the plain command name to the downloaded file (do not rename)
7ln -s k8e-sandbox-cli-linux-amd64 k8e-sandbox-cli
8
9# Create an API key on the server (default TTL 30 days; use --ttl never for non-expiring)
10k8e sandbox-apikey create my-agent
11# → {"name":"my-agent","key":"k8e-abc123...","ttl_days":30,"expires_at":"..."}
12
13# Connect: authenticate (mTLS) + install /k8e-sandbox skill into agent harnesses
14./k8e-sandbox-cli --endpoint <server-ip>:50051 --apikey k8e-abc123... connect
15
16# Optional multi-cluster profiles (~/.k8e/sandbox/profiles.yaml — not server /etc/k8e/config.yaml)
17# See docs/kip-17-sandbox-cli-profiles-and-apikey-ttl.md
18# ./k8e-sandbox-cli --profile prod connect --apikey k8e-...

Local usage: If you're on the same machine as the K8E server, the CLI auto-discovers TLS certs — just run k8e-sandbox-cli connect.

Platform binaries: k8e-sandbox-cli-{darwin,linux,windows}-{amd64,arm64} (Windows: k8e-sandbox-cli-windows-amd64.exe, symlink via mklink k8e-sandbox-cli.exe k8e-sandbox-cli-windows-amd64.exe)

One binary, two names: the downloaded k8e-sandbox-cli-linux-amd64 file is the k8e-sandbox-cli command the skill uses. connect symlinks it to ~/.local/bin/k8e-sandbox-cli (on PATH) and installs the /k8e-sandbox skill into your agent harnesses, so every skill example (k8e-sandbox-cli run ...) is the same file you just downloaded.

Then ask your agent naturally:

"Run this Python snippet in a sandbox"

The agent executes k8e-sandbox-cli run automatically — no session management needed.

Supported agents: claude code, codex, pi.

🔒 Sandbox Runtime Setup

K8E auto-detects installed runtimes and registers the corresponding RuntimeClass. Choose based on your isolation requirements:

gVisor — Recommended Default

bash
1# Download runsc + containerd-shim-runsc-v1 directly from the gVisor release bucket (requires wget)
2ARCH=$(uname -m)   # x86_64 on most servers, aarch64 on ARM
3URL=https://storage.googleapis.com/gvisor/releases/release/latest/${ARCH}
4
5wget ${URL}/runsc ${URL}/runsc.sha512 \
6     ${URL}/containerd-shim-runsc-v1 ${URL}/containerd-shim-runsc-v1.sha512
7
8sha512sum -c runsc.sha512 -c containerd-shim-runsc-v1.sha512   # both must print OK
9chmod +x runsc containerd-shim-runsc-v1
10sudo mv runsc containerd-shim-runsc-v1 /usr/local/bin/
11ls -l /usr/local/bin/runsc /usr/local/bin/containerd-shim-runsc-v1   # verify both installed

Do not run runsc install — K8E manages its own containerd config at /var/lib/k8e/agent/etc/containerd/config.toml and auto-injects the gVisor stanza on startup.

Kata Containers

bash
bash -c "$(curl -fsSL https://raw.githubusercontent.com/kata-containers/kata-containers/main/utils/kata-manager.sh) install-packages"
kata-runtime check

Firecracker (requires /dev/kvm)

bash
ls /dev/kvm   # verify KVM is available

# Install firecracker-containerd shim + devmapper snapshotter
# See: https://github.com/firecracker-microvm/firecracker-containerd
mkdir -p /var/lib/firecracker-containerd/runtime
# Place hello-vmlinux.bin and default-rootfs.img here

Apply Changes

Install runtimes before starting K8E for zero-restart setup. If K8E is already running, restart it after installing a new runtime shim:

bash
systemctl restart k8e
kubectl get runtimeclass
# NAME          HANDLER       AGE
# gvisor        runsc         10s
# kata          kata-qemu     10s
# firecracker   firecracker   10s   ← only if /dev/kvm present

🤖 Sandbox CLI

k8e-sandbox-cli is a standalone binary (~44MB) that gives AI agents direct access to K8E sandbox infrastructure — no server install needed.

AI Agent (claude code / codex / pi)
    │  shell command
    ▼
k8e-sandbox-cli run "print('hello')" --lang python
    │  gRPC (TLS)
    ▼
sandbox-grpc-gateway:50051
    │
    ▼
Isolated Pod (gVisor / Kata / Firecracker)

Install the Skill

On the server, create an API key for secure remote access:

bash
k8e sandbox-apikey create my-agent
# → {"name":"my-agent","key":"k8e-abc123..."}

On the client, download the standalone CLI, log in, and install the skill:

bash
1# 1. Download the platform-specific binary (~44MB)
2#    k8e-sandbox-cli-linux-amd64 / linux-arm64 / darwin-amd64 / darwin-arm64 / windows-amd64.exe
3curl -sLO https://github.com/xiaods/k8e/releases/latest/download/k8e-sandbox-cli-linux-amd64
4chmod +x k8e-sandbox-cli-linux-amd64
5
6# 2. Symlink the plain command name to the downloaded file (do not rename)
7ln -s k8e-sandbox-cli-linux-amd64 k8e-sandbox-cli
8
9# 3. Connect: mTLS auth + install /k8e-sandbox skill into Claude/Codex/Pi
10#    Note: --endpoint and --apikey are global flags, placed before the subcommand
11./k8e-sandbox-cli --endpoint <server-ip>:50051 --apikey k8e-abc123... connect

Platform binaries: k8e-sandbox-cli-{darwin,linux,windows}-{amd64,arm64} (Windows: k8e-sandbox-cli-windows-amd64.exe, symlink via mklink k8e-sandbox-cli.exe k8e-sandbox-cli-windows-amd64.exe)

One binary, two names: the downloaded k8e-sandbox-cli-linux-amd64 file is the k8e-sandbox-cli command the skill uses — the symlink is just a plain-name alias to the same file. connect installs the /k8e-sandbox skill, so every skill example (k8e-sandbox-cli run ...) is the same file you just downloaded.

Then in your agent harness:

/k8e-sandbox <goal>

Or ask naturally: "Run this Python snippet in a sandbox" — the skill drives k8e-sandbox-cli run.

Available Commands

See pkg/sandboxcli/skills/k8e-sandbox/SKILL.md and docs/kip-17-sandbox-cli-profiles-and-apikey-ttl.md.

Quick Examples

bash
1# Run Python code (auto-creates session)
2k8e-sandbox-cli run "print('hello')" --lang python
3
4# Shell command (default lang=bash)
5k8e-sandbox-cli run "ls -la /workspace"
6
7# TypeScript — type annotations run via tsx
8k8e-sandbox-cli run "const nums: number[] = [1, 2, 3]; console.log(nums.reduce((a, b) => a + b, 0))" --lang ts
9
10# Multi-line TypeScript via stdin (interfaces, async/await)
11k8e-sandbox-cli run --lang ts <<'EOF'
12interface User { name: string; age: number }
13
14async function oldest(users: User[]): Promise<User> {
15  return users.reduce((a, b) => (a.age > b.age ? a : b));
16}
17
18const users: User[] = [{ name: "Ada", age: 36 }, { name: "Linus", age: 54 }];
19oldest(users).then((u) => console.log(`Oldest: ${u.name} (${u.age})`));
20EOF
21
22# Multi-line via stdin
23k8e-sandbox-cli run --lang python <<'EOF'
24for i in range(10):
25    print(i)
26EOF
27
28# Default egress: pypi.org, files.pythonhosted.org, registry.npmjs.org,
29#   objects.githubusercontent.com, github.com, raw.githubusercontent.com
30SID=$(k8e-sandbox-cli create | jq -r .session_id)
31k8e-sandbox-cli write $SID /workspace/script.py <<'PYEOF'
32import pandas as pd
33print(pd.__version__)
34PYEOF
35k8e-sandbox-cli run "pip install pandas" --session-id $SID
36k8e-sandbox-cli run "python3 /workspace/script.py" --session-id $SID
37
38# Create session with custom runtime and egress
39SID=$(k8e-sandbox-cli create --runtime firecracker --allowed-hosts pypi.org,github.com | jq -r .session_id)
40
41# Clone git repo at session creation
42SID=$(k8e-sandbox-cli create --git-repo https://github.com/user/repo.git --git-ref main | jq -r .session_id)
43
44# Stream long-running output
45k8e-sandbox-cli run "python3 train.py" --session-id $SID --raw
46
47# Tenant-based cross-process session reuse
48k8e-sandbox-cli run "echo hello" --tenant my-project

Configuration Overrides

The CLI auto-discovers the local cluster via TLS. For remote clusters, use k8e-sandbox-cli login once to set up mTLS credentials. Override when needed:

bash
1# Remote cluster: log in once (creates ~/.k8e/sandbox/{client.crt,client.key,ca.crt})
2k8e-sandbox-cli --endpoint 10.0.0.1:50051 --apikey k8e-abc123... login
3
4# After login, subsequent commands work without --apikey:
5k8e-sandbox-cli run "echo hello"
6
7# Or via environment variables:
8K8E_SANDBOX_ENDPOINT=10.0.0.1:50051 K8E_SANDBOX_APIKEY=k8e-abc123... k8e-sandbox-cli login
9
10# Override endpoint per-command:
11K8E_SANDBOX_ENDPOINT=10.0.0.2:50051 k8e-sandbox-cli run "echo hello"

🖥️ Advanced Installation

Add a Worker Node

bash
# Get token from server node
cat /var/lib/k8e/server/node-token

# On worker machine
curl -sfL https://k8e.sh/install.sh | \
  K8E_TOKEN=<token> \
  K8E_URL=https://<server-ip>:6443 \
  INSTALL_K8E_EXEC="agent" \
  sh -

Disable Sandbox Matrix

bash
curl -sfL https://k8e.sh/install.sh | INSTALL_K8E_EXEC="server --disable-sandbox-matrix" sh -

Key Environment Variables

bash
K8E_TOKEN=<secret>              # cluster join token
K8E_URL=https://<server>:6443   # server URL (agent nodes)
K8E_KUBECONFIG_OUTPUT=<path>    # kubeconfig output path

🆚 K8E vs Other Sandbox Platforms

How K8E compares to mainstream sandboxes for AI agents:

When to choose K8E

• You want E2B-style sandboxes but self-hosted — same official SDKs, your infrastructure, no per-seat pricing.
• Your agents need a rich tool surface beyond "run code": PTY terminals, snapshots, service exposure, and live egress policy — all through one audited gateway.
• You want pluggable isolation (swap gVisor ↔ Kata ↔ Firecracker per session) instead of being locked to one microVM stack.

🤝 Contributing

bash
git clone https://github.com/<your-username>/k8e.git && cd k8e
git checkout -b feat/my-feature
make && make test
git push origin feat/my-feature

• 🐛 Bug Reports
• 💡 Feature Requests
• 🔍 Open PRs

🛡️ Security

Report vulnerabilities via GitHub Security Advisories. Do not open public issues for security bugs.

📄 License

Apache License 2.0 — see LICENSE.

🙏 Acknowledgments

k8e.sh — Open Source Agentic AI Sandbox Matrix

If K8E powers your agents, give us a ⭐ — it means the world to us!