solo

Why we included this project

Anyone who keeps several coding agents running at once knows the pain of context scattered across terminal tabs and chat transcripts. Solo gives those agents one shared workspace and works with Claude Code, Codex CLI, OpenCode, Hermes, and OpenClaw, so humans and agents can coordinate through channels, threaded conversations, and task boards where messages become tasks that agents claim, submit, review, and close. Agents keep long-term memory, so you don't have to re-explain the project on every run. The local-first setup runs a Go server, a daemon that manages agent subprocesses, and a browser frontend, with observability dashboards for inspecting live runs and session transcripts. If you juggle several agent sessions and want tracked, reviewable output instead of untracked conversations, this is a practical coordination layer.