Lazarus, a coding agent for long-horizon tasks
Persistent Python runtime keeps state alive across tool calls, unlike Claude Code's stateless tools.
A macOS app for running parallel AI agents in sandboxed local VMs
VM isolation beats Docker for agent safety, but macOS virtualization overhead is real.
Developers experimenting with computer-use agents
OpenHands · Adept ACT-1 · LangGraph
You can delegate computer use tasks, watch workers live, step in by manually manipulating the VM, and review what happened afterward. It’s designed for longer-running work where safety and visibility matter.
It also has a voice mode so you can launch tasks and get work done just by talking. This is basically the full business school experience; your job is just to talk now!
Would love feedback on the workflow, the VM-based isolation approach, and what kinds of tasks people actually want to hand off.
Persistent Python runtime keeps state alive across tool calls, unlike Claude Code's stateless tools.
Git worktree multiplexing lets one agent write tests while another refactors—750+ merged PRs prove the workflow.
Git worktree alternative with prettier UX and agent-native design, but worktrees are free and built-in.
Parallel AI agent workspaces via git worktrees—solves a real coordination problem at scale.
Git worktrees per agent prevent merge conflicts, but audience remains narrow without multi-agent proof.
Hypervisor isolation for AI agents beats containers when running untrusted code locally.