AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Cybersecurity › Wirken
✦ Free & open sourceCybersecurity

Wirken

Enterprise gateway for autonomous AI agents with isolation and audit logs.

Enterprise Gateway for Autonomous Agents

Isolate messaging channels, vault credentials, and audit agent actions securely.

Free forever · open source · MIT
✓ Light setup✓ Browser-based✓ Real-time collaboration
7.1
ZEKAI
Secure agent gateway
Free & open source · Cybersecurity
Ease of setup6
Usefulness8
Maintenance9.5
Community5
★ 190
GITHUB
Oct 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

Wirken is an enterprise gateway that acts as a secure switchboard between team messaging channels and autonomous AI agents. It is designed for security teams needing to contain compromised agents, enforce least privilege, and maintain tamper-evident audit trails.

Runs on
Cross-platform
Hosting
Self-host
Languages
Rust
License
MIT

What it is

It receives inbound messages from channels like Telegram, Slack, or Matrix, wakes up an ephemeral agent, and routes actions through permission checks and Docker-based sandboxes. Every tool call and file read is signed and written to a hash-chained audit log before execution.

Who it's for

Suits security and IT infrastructure professionals deploying autonomous AI agents in production environments. It does not suit teams wanting unconstrained agent execution or those unwilling to run Docker and configure isolated channels.

Key features

Encrypted Credential Vault

Tokens and API keys stay in a local vault, supplied only at the edge so models never see them.

Signed Audit Chains

Every agent action is written to a typed, hash-chained log before it executes.

Ephemeral Sandboxing

Shell commands run inside temporary containers with no network access by default.

Provider-Agnostic Routing

Connects to frontier APIs, local Ollama instances, or TEEs with per-agent spend limits.

How to start

Up and running in 3 steps

1
Run the installation script to download the binary for your supported OS
2
Execute wirken setup to initialize configuration and local storage
3
Start the gateway with wirken run to accept authenticated connections and launch WebChat
Real talk

Our honest verdict

What's great

  • Ships as a single static Rust binary with no complex dependencies
  • Per-channel isolation ensures compromised endpoints stay contained
  • Three-tier permission model and budget gates restrict runaway costs
  • Tamper-evident audit logs capture actions for SIEM integration

Where it falls short

  • Requires Docker installed and running for proper shell command sandboxing
  • Egress is not fully contained by default and requires additional firewall rules
  • Audit tamper-evidence relies on an out-of-band key anchor to remain secure
  • Turning off the sandbox exposes the host to direct command execution
Cost

Pricing & license

Free under its license, with the only cost being the hardware and LLM API usage required to run it yourself.

Paid work

Open remote AI-training roles

873 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: Wirken for Cybersecurity
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure Wirken for you — and train your team.
Get it done for you ↗
Questions

FAQ

Can agents execute shell commands without Docker?

Without Docker, the agent simply cannot run shell commands, while all other functionalities remain operational.

How does Wirken handle agent spend limits?

Each agent is capped by a defined per-agent spend budget enforced by a budget gate.

Where are credentials stored?

Credentials reside in an encrypted vault managed via an age-file backend or OS keychain.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Cybersecurity — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google