Wirken: Secure AI agent gateway. Encrypted vault. Single static binary
Wirken is a secure AI agent gateway that supports multiple messaging platforms and runs as a single static Rust binary. It provides encrypted credential storage, per-agent permissions, and a hash-chained audit log for transparency and security. The tool integrates with various AI providers and supports installation via a verified script or from source.
- ▪Wirken supports messaging platforms including Telegram, Discord, Slack, and WhatsApp, with each channel running in an isolated adapter process.
- ▪Credentials are stored in an encrypted XChaCha20-Poly1305 vault tied to the OS keychain, and all agent actions are logged in a per-session SHA-256 hash-chained audit log.
- ▪The installer verifies binary integrity using signed checksums, and installation fails securely if any verification step fails unless overridden.
- ▪Wirken supports AI providers such as OpenAI, Anthropic, Ollama, and Gemini, and can forward logs to SIEM tools like Datadog and Splunk.
- ▪It is MIT licensed, available for Linux, macOS, and Windows, and can be installed via a script or built from source with Rust 1.85+.
Opening excerpt (first ~120 words) tap to expand
Wirken Wirken is the switchboard for the agent era. Message it on Telegram, Discord, Slack, Microsoft Teams, Matrix, WhatsApp, Signal, Google Chat, or iMessage, and the agent on the other end reads files, calls APIs, and runs tools on your behalf. Each channel gets its own line. Every call is logged before it connects. Wirken ships as a single static Rust binary and works with Ollama, Anthropic, OpenAI, Gemini, Bedrock, Tinfoil, Privatemode, or any OpenAI-compatible endpoint. MIT licensed. Each channel runs in its own adapter process with a distinct Ed25519 IPC identity and its own vault-scoped token set. Credentials sit in an XChaCha20-Poly1305 vault keyed from the OS keychain, with per-credential expiry and manual rotation tracked in the store.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.