AI agents
Rookery
An orchestrator for coding agents that runs your GitHub issues without merging them
- 0community votes
- 0DR by Ahrefs no change since last check
Ahrefs Domain Rating signal 18 Nov 2026, signal shifted 1 Nov 2026.
Rookery watches GitHub repositories for a label, creates a plan for approval, executes tasks one at a time, and opens a draft pull request for review.
What it is

Rookery is an orchestrator for coding agents that automates work on your GitHub issue queue while keeping humans in control. Label an issue, and Rookery reads it, writes a plan for your approval, then executes the tasks one at a time. Each task runs in its own session, preventing context from snowballing across long issues. The output is always a draft pull request—Rookery never merges.
The system uses GitHub labels as its state machine, so you can see where any run stands from the issue alone. Every step is visible and auditable. When something fails, Rookery reports it as a comment on the issue. You can approve the plan before work starts and review the result after, with the plan, tasks, and decisions committed to the branch for full transparency.
Rookery runs each repository's queue independently and one job per repository to avoid race conditions. It handles multiple repositories in parallel, and the cost is predictable: every task costs the same regardless of its position in the queue. Installation is straightforward—add the GitHub App to your repositories and configure each with a .rookery/workflow.json file.
Systems
- Plan approval workflow before execution
- Each task runs in isolated session to prevent context snowball
- GitHub labels as state machine for visibility
- Predictable per-task pricing
- Never merges—always opens draft pull request
- Daily repository limits to control costs
- Error reporting as issue comments
Want to see what Rookery does next? Follow them for milestones, new products and stories by email.
Rookery metrics
Signal readout for rookery.run: Ahrefs Domain Rating and Majestic link signals, arrows for the change since the last scan.
- 0 Domain Rating no change since last check
- 0 Trust Flow no change since last check
- 0 Citation Flow no change since last check
- 0 Referring domains no change since last check
- 0 External backlinks no change since last check
Ahrefs Domain Rating signal 18 Nov 2026, signal shifted 1 Nov 2026. Majestic signal 1 Nov 2026, signal shifted 1 Nov 2026. Link signals from Majestic. Trust Flow, Citation Flow and Topical Trust Flow are trademarks of Majestic-12 Ltd.
Rookery domain signal
Show the signal details
Public RDAP record, last read 16 Nov 2026, 21:36 UTC.
- Domain age 1 month
- Registered
- Expires
- Registrar GoDaddy.com, LLC
- DNSSEC Not signed
Rookery post-launch signal
The record for Rookery after its launch on Nexora Launch (1 November 2026), from the readings we keep.
- 0 Domain Rating (Ahrefs) no change since launch
at launch: 0 (1 Nov 2026); latest: 17 Nov 2026 - 0 Trust Flow (Majestic)
first measured 1 Nov 2026 - 0 Referring domains (Majestic)
first measured 1 Nov 2026
Day 16 since launch. Next receipt: day 30, 1 Dec 2026. A change here is a reading, not a claim about its cause; lots of things move these figures. Anything we do not measure is not shown.
Got a launch coming up?
Plan your launch with our free playbook, from preparing your listing to choosing more launch directories.
Quick answers
- How do I get started with Rookery?
- Install the GitHub App on the repositories you want covered, then steer each one with a .rookery/workflow.json configuration file. Watch every run from the portal.
- What happens if a task fails?
- Rookery labels the issue with rookery:error and posts the error as a comment. You can approve again to resume at the first unticked task.
Rookery has a free listing. The owner can unlock the full profile with a paid launch for $5:
- Founder story (locked)
- Milestones (locked)
- Demo video (locked)
- Dofollow website link: not on this free listing (its website link is nofollow)
Also on the frontier
-
Rank 1: AITasker
AI agent marketplace where agents compete with real prototypes
AI agentsAustraliaVerified
DR 10 no change since last check DA 12 no change since last check 7 votes. Log in to send AITasker a vote -
Rank 2: Ejentum
Inference-time reasoning harness for AI agents that cuts inference costs by 60% to 85%
AI agentsStartupUnited StatesVerified
DR 20 no change since last check 6 votes. Log in to send Ejentum a vote -
DR 28 no change since last check 5 votes. Log in to send Denker a vote
-
Rank 4: NoInfra
Managed AI agents for personal tasks and business workflows with no infrastructure to manage
AI agentsStartupUnited States
DR 34 no change since last check 1 votes. Log in to send NoInfra a vote