Assign the outcome
Choose an Agent context and describe the result in New Work. XpressClaw creates a durable task for the selected harness.
Your project’s decisions, files, and task history stay in one workspace. Return to Codex, Claude Code, or another agent and pick up where you left off.
$ xpressclaw up
YOUR WORKSPACE
The current interface is built around Agents, durable tasks, work history, schedules, and workflows—not a terminal stream hidden inside a browser.
THE FIRST AHA MOMENT
XpressClaw wraps the native harnesses developers already trust with durable execution state and a control plane that can keep moving after you step away.
Choose an Agent context and describe the result in New Work. XpressClaw creates a durable task for the selected harness.
Codex—or another harness—works in its configured project container while attempts, progress, and results remain visible.
A reusable workflow can pass the draft PR to a separate reviewer context, such as Claude Code, and loop actionable feedback.
Inspect the record, add context, cancel work, schedule a follow-up, or let a durable wait resume after external activity.
XpressClaw includes an implementation + review template: one Agent context owns a draft pull request, another reviews it independently, and rejected changes return to implementation before the PR is marked ready.
DURABILITY AROUND THE LOOP
The harness keeps its reasoning loop. XpressClaw supplies the environment, execution state, automation, and history around it.
Across ordinary turns, an Agent keeps one Docker or Podman container and ACP process instead of rebuilding a disposable sandbox for every prompt.
A request becomes a task with attempts, messages, artifacts, dependencies, results, and provenance stored by the local control plane.
Queue work now, run it on a cron schedule, arm a one-shot wakeup, or move it through a reusable multi-harness procedure.
BRING YOUR HARNESS
XpressClaw is an ACP client and control plane. It does not replace the selected product’s reasoning, tools, permissions, or subagents.
Use the native product, not an imitation of it.
The harness owns planning, tool use, permissions, and subagents. XpressClaw owns durable work and presentation.
After discovery, supported commands, modes, models, reasoning levels, and MCP choices appear where work is composed.
Trusted runners can reuse standard logins, settings, skills, plugins, hooks, and custom agents from the host.
Keep project context stable while execution products evolve.
An Agent ties together a name, workspace, task history, runtime configuration, and the currently selected harness.
Provide a container image and command for another coding harness that speaks ACP over standard input and output.
Bind workflow roles to different Agent contexts so implementation, review, and follow-up can use different harnesses.
Power is visible and opt-in.
Worker environments run through Docker or Podman and receive only configured workspaces, volumes, and environment values.
Optional Docker, Compose, and Buildx access gives the runner control of the host engine and is clearly treated as privileged.
Control-plane data stays on your machine. Choose the harness and model that receive your prompts and code.
THE XPRESS AI ECOSYSTEM
Run native coding harnesses in XpressClaw. Use Xpress AI for persistent coworkers with shared context, memory, goals, and collaboration, built on the Xaibo framework.
Codex, Claude Code, OpenCode, and other ACP products bring focused execution loops that are already excellent at software work.
Longer-lived coworkers can combine reasoning, memory, review, perception, tools, procedures, knowledge, objectives, and identity through explicit modules.
XpressClaw combines native ACP harnesses with persistent Agent contexts, tasks, schedules, workflows, task history, and retained project environments.
COORDINATION MODEL
Assign work, track progress, and coordinate reviews and follow-ups in one workspace.
New Work or an Agent workspace accepts an outcome and creates a task for the selected Agent and harness.
Attempts, tool activity, questions, follow-ups, artifacts, and results persist. Schedules and workflows put work onto the same substrate.
Pass work between agents through reusable workflows, schedule the next task, and keep progress and results in the task conversation.
BUILT IN PUBLIC
Run XpressClaw on your machine. The public repository contains the runtime, UI, runner definitions, workflow examples, and docs. Explore the code, extend a runner, join Discord, or send a pull request.
YOU CONTROL THE WORKSPACE
Configuration, task state, and timelines stay on your machine. Your chosen cloud harness or model receives the context you send it. You choose which trusted runners receive host credentials.
XPRESSCLAW + XPRESS AI
XpressClaw is the open-source foundation for running agents on your machine. Xpress AI is the managed platform for organizations that want persistent coworkers with managed infrastructure.
For developers who want to own the control plane, bring native harnesses, inspect the runtime, and build durable agent work on their own machine.
For organizations that want hosted persistent AI coworkers with managed collaboration, infrastructure, integrations, and governance.
START LOCAL. KEEP CONTROL.
Download XpressClaw, choose a project folder and supported harness, then send the first outcome from New Work.