/wa·keel/ — Arabic for agent, representative
Orchestrate AI Agents at Scale
A self-hosted platform to configure, trigger, and orchestrate AI agents across our delivery pipeline — from code reviews to deployments, all through the tools our team already uses.
Wakeel wraps AI capabilities in predictable, reliable operations. Minimize AI unpredictability to only where you need it.
DETERMINISTIC
NON-DETERMINISTIC
DETERMINISTIC
AI unpredictability is sandwiched between reliable, deterministic operations. The blast radius is minimized to only the part where you actually need AI.
@wakeel on GitHub
issue
wakeel-qa Jira
label
@wakeel in Slack
wakeel@almosafer.com
Self-hosted on our K8s cluster
No new tools to learn. Wakeel lives where our team already works.
Every concern is addressed at the architecture level — not as an afterthought.
Self-hosted on our K8s cluster. Code context is sent only to the configured model API.
Hard ceiling on concurrent runners. Queue absorbs bursts. We control the spend.
Every run is observable, recoverable, and graded by the people who use it.
Every external dependency is behind an adapter. Swap providers without touching core logic.
The same engine powers every agent — only the config changes.
Same engine, new config — developer, DevOps, security, documentation, or anything your team needs.
Two agents, two repos, full end-to-end visibility — expanding from results.
Live — running on staging
Triggers
In Code Review
with label
wakeel-review
What happens
reviewed_by_wakeel
Auto-abort
Up next — planned for next sprint
Triggers
Ready for QA
with label
wakeel-qa
What will happen
Human gate
A walkthrough of what's been built so far — the dashboard, agent configuration, and a live agent run.
Wakeel — وكيل — Our AI Representative