condukt
Features Install Blog Docs GitHub

Blog

Notes from the Tuist team.

Release notes, OTP patterns, and lessons we learn while building production AI agents on the BEAM.

Subscribe via RSS or Atom.

  1. May 19, 2026

    Microsandbox support in Condukt

    Condukt can now run agent tool calls inside a local microVM through Microsandbox, with the same tools and the same agent definition.

  2. May 15, 2026

    The network is the open side of the sandbox

    Sandboxing the filesystem and processes is the easy part. The network is the surface most stacks leave open, and the one that matters most as agents start touching real systems. Here is how we are closing it in Condukt, and the missing piece we are watching for.

  3. May 13, 2026

    Coding agents as runtimes

    Codex and Claude are already tuned coding harnesses. Condukt should meet them where they are and orchestrate them as runtimes.

  4. May 11, 2026

    Tool calls in a pod you already run

    We just shipped a Kubernetes sandbox for Condukt. One pod per session, the same agent definition, the same tools.

  5. May 3, 2026

    Where an agent's tools should run

    We just landed sandboxes in Condukt. Same agent, swap where the tool calls actually execute. Here is the thinking behind it.

  6. May 3, 2026

    Secrets belong in the session

    Agents need to act against real systems. We added session secrets to Condukt so credentials become part of the execution boundary, not part of the conversation.

An Elixir framework for defining and running AI agents. · MIT licensed · github.com/tuist/condukt · Made by the Tuist team.