An Elixir framework for defining and running AI agents. https://condukt.tuist.dev/blog/ 2026-05-19T00:00:00.000Z Tuist https://tuist.dev https://condukt.tuist.dev/blog/microsandbox/ 2026-05-19T00:00:00.000Z 2026-05-19T00:00:00.000Z

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

The Tuist team https://condukt.tuist.dev/blog/the-network-is-the-open-side-of-the-sandbox/ 2026-05-15T00:00:00.000Z 2026-05-15T00:00:00.000Z

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.

The Tuist team https://condukt.tuist.dev/blog/coding-agents-as-runtimes/ 2026-05-13T00:00:00.000Z 2026-05-13T00:00:00.000Z

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

The Tuist team https://condukt.tuist.dev/blog/kubernetes-sandbox/ 2026-05-11T00:00:00.000Z 2026-05-11T00:00:00.000Z

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

The Tuist team https://condukt.tuist.dev/blog/sandboxes-for-tool-calls/ 2026-05-03T00:00:00.000Z 2026-05-03T00:00:00.000Z

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

The Tuist team https://condukt.tuist.dev/blog/agent-session-secrets/ 2026-05-03T00:00:00.000Z 2026-05-03T00:00:00.000Z

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.

The Tuist team