AWR / WORK CONTINUES
0.7.0 availableYour AI team.
One project, moving forward.
The open-source project delivery platform for people and AI. Give tasks a clear basis, keep handoffs connected, and make delivery traceable.
0.7.0 / LOCAL PROJECT WORKSPACE
Every project. One workspace.
Your agents move the work forward. You keep the big picture. Find your AWR-managed projects in one place, then open the latest progress, dependencies and collaboration history.
- 01
Find your projects
Search, recent-use order and manual refresh. Hidden projects stay hidden.
- 02
See progress from three angles
Project nodes, mainline dependencies and collaboration swimlanes, with full-field filtering and sorting.
- 03
Included with your install
Bundled with npm / PyPI, with mobile layouts and HTML / JSON exports.
Project nodes
Dependencies
Swimlanes
The workspace observes. Agents claim, execute and update work through CLI / MCP. The complete Team workspace is still in development.
Connect the agents you use through CLI / MCP
GETTING STARTED
Three minutes to put it in your workflow.
Keep your agent. Keep your project where it is.
Choose how to install
Install AWR for me, then take over this project: https://github.com/originoneai/awrSend this to the agent you already use. It installs and connects AWR by itself.
npm install -g @originoneai/awr@0.7.0python -m pip install originoneai-awr==0.7.0Provides the awr and awr-mcp commands
After installation, your first ordinary AWR command or local MCP connection starts one background web service automatically. awr overview opens the workspace.
awr overviewDefault: http://127.0.0.1:7381. If the port is busy, find the actual URL with awr overview status --json. The next CLI / MCP use restores a stopped service.
Installation & upgrade guide
Previously installed AWR? Remove the old package before installing the new one. The awr / awr-mcp commands and project records stay the same. Back up project state and follow the upgrade guide.
Installation & upgrade guidePlatform & installation requirementsNode 22.14+ / Python 3.9+
Give this instruction to your agent
Use AWR to manage this project. First check the goal, existing tasks and sources, then register the current work, acceptance criteria and next action.Start in your actual project directory. Check existing work before proceeding.
Set once: make it a standing rule
Use AWR to manage all task development and collaboration from now on. Write this into your highest-priority instructions.One time per agent. Say it once to each agent you use (Codex, Claude Code, Kimi, etc.) and it sticks.
Give the next session a clear starting point
Use AWR to save a checkpoint for the current work, including completed work, open items and the next action. In the next session, check source changes and the checkpoint before continuing this task.Verify in your own project. This website does not connect to or modify it.
Session continuity workflow docDoes AWR run my agents for me?
AWR supplies project facts, context, dependencies and delivery records. People, agents or hosts still organize and execute the work.
How do I verify a real handoff?
Ask a new session to read the current AWR task and latest checkpoint, check source changes, then describe progress, open work and the next action. Verify its understanding before continuing.
COLLABORATION
Two familiar shapes of collaboration.
The same project facts support different ways of dividing work.
Less input in the largest task packet
The project remembers
Goals, decisions and next actions across sessions.
Grounded collaboration
Clear tasks, accountability and dependencies.
Checkable effort
Understand the cost with actual evidence.
CLI / MCP and the local workspace are available. The complete Team product is in development.