openclaw-control-center

TianyiDataScience/openclaw-control-center is ranked 7,725 among these 8 peers; sourcebot-dev/sourcebot is ranked 7,729.

Built for non-technical operators who need observability and certainty, not raw backend payloads. Safe first-run defaults: read-only by default local token auth by default mutation routes disabled by default What you get : health, current state, decisions waiting, and operator-facing summaries : usage, spend, subscription windows, and connector status : who is really working now versus only queued : a hall-first multi-agent work chat with live discussion, execution order, handoff, review, and evidence threads : current work, approvals, execution

chains, and runtime evidence and : source-backed workbenches scoped to active OpenClaw agents What this release adds : a new hall-first collaboration page so you can post work in one shared timeline, see real agent roster names reply live, and watch discussion collapse into one execution owner before review. : hall discussion, assign, and handoff can now dispatch through the real runtime, so the live draft stream reflects real session execution instead of only synthetic orchestrator text. : hall runtime streaming now

prefers direct CLI/stdout passthrough when OpenClaw emits live output, and gracefully falls back to session-history deltas when the runtime only exposes persisted session updates. : can now trigger a short automatic real execution chain, so one owner can continue through several runtime turns before the task pauses in or . : the hall now uses your current OpenClaw roster directly; existing agent ids do not need to be renamed to any control-center-specific defaults before they can discuss, execute, and

hand off work. : linked task rooms now act as detail and evidence threads with live room streaming, assignment, review, and optional outbound Discord or Telegram mirroring without moving source-of-truth storage out of . : a new card that tells you what is already wired, what is still partial, and where to finish setup. : a new that translates current risk, impact, and next-step guidance into plain operator-facing language. : a new card for current version, latest version, update channel, and

install method. : a new card so you can see which sessions are closer to context limits and where things may get slower or more expensive. : a new card so you can see whether each visible agent's memory is usable, searchable, or worth checking. Who it is for OpenClaw users who want one local control center for observability, usage, tasks, approvals, replay, documents, and memory teams running OpenClaw on one machine or a reachable local environment maintainers who want a public

-ready, safety-first OpenClaw dashboard instead of a generic agent platform Screenshots Example UI from a local OpenClaw environment: Hall integration with your existing agents The hall reads the current OpenClaw roster from the runtime environment and uses the live agent ids and display names it finds there. Existing users do not need to rename agents to , , , or any other control-center-specific name before using hall collaboration. If the roster has clear names such as , , , or , the hall will

use them; otherwise it falls back gracefully without blocking the workflow. Hall runtime turns now carry structured transport context such