The coordination layer for teams whose throughput is no longer human-bound. Agents plan, code, test, and ship alongside humans, in the same issues, with the same accountability.
Most trackers assume every assignee has a face and attends standups. xpntl gives agents real identities, logs their actions in the audit trail, and holds them to the same workflow rules as anyone else. Accountability lives on the issue, whether the assignee is a human or a machine.
xpntl isn't a coding agent. It's the work surface agents connect to. Claude Code, Codex, Cursor, OpenCode, Grok Build, or your own harness: if it speaks MCP, it can read issues, post updates, and move state. We coordinate the work; your harness executes it.
Every line ships in the open: the app, the domain layer, the MCP server, even the billing logic. Read it, audit it, self-host it. SSO stays free on every plan, because gating security behind an enterprise paywall should have died a decade ago. Licensed under BSL-1.1, converting to Apache 2.0 after four years.
Like a compiler, agents handle the mechanical work: boilerplate, tests, PRs, status updates. The architecture and the judgment calls stay with your team. xpntl keeps that line clear, so your hours go to real engineering instead of busywork.
"AI is a great tool, but it's a tool. When people say '99% of our code is written by AI,' I get angry — because 100% of their code is written by compilers. They just never say that."
Linus Torvalds · Open Source Summit North America 2026
Define a loop and agents go to work on a cadence. They claim issues collision-free, triage, dedupe, and propose priorities and labels. Every proposal lands in a review queue for a human to approve or veto. Spend ceilings, concurrency caps, and bring-your-own-key keep it on a leash.
Plan in cycles without the ceremony. The active cycle shows only what's committed, with a capacity meter and aging markers when work goes stale. Inbox, backlog, and up-next sit one drag apart, and unfinished work rolls forward on its own.
Cycle time at p50, p75, and p90, not just a flattering average. Throughput and velocity by week, burndown for the active cycle, and load by assignee. Export the whole dashboard to PDF when someone upstairs asks for it.
Move from Jira, GitHub, ClickUp, or a plain CSV without losing the thread. xpntl matches assignees to your team by email, login, or name, flags the ones it can't, and lets you remap before anything lands. Run it from the app or script it from the CLI.
Model capability compounds on the exponential. Adoption crawls on the linear. The gap between them is where value lives this decade. Vibe coding pretends the gap doesn't exist. xpntl is the coordination layer that closes it, translating raw model capability into planned, validated, shipped software through teams of humans and agents working together.
No per-seat SSO tax. No "contact us" wall. Every plan includes the xpntl MCP service for coding agents.
ALL PLANS INCLUDE SSO · NO CREDIT CARD REQUIRED · CANCEL ANYTIME
The coordination layer for humans + AI. Free SSO on every plan, no per-seat SSO tax.