Entire launches a Git forge for agent-human collaboration
Original title: The Git Forge for Agent-Human Collaboration
Trails score every push with agent evals, and gates can block merges until findings, human approval, and CI pass.
Thomas Dohmke, co-founder and CEO of Entire, introduced a Git-compatible forge aimed at teams that code with agents. Trails replace linear pull-request timelines with eval scores on every push, plus findings and merge gates. The company says hosting is up to 89x faster than GitHub and 6x faster than Cursor Origin, and that Continuous Memory stores sessions and prompts in the repository. Entire is available now, with Buildkite and Depot CI integrations and review agents running Claude Code and Codex in Daytona and E2B sandboxes.
Unconfirmed: The stated speed gains versus GitHub and Cursor Origin are Entire’s own figures, not independently verified.
- A Trail can span multiple repositories and start from a bug, feature request, or an agent.
- Predefined evals include Security, Slop, and Human Review Required, configurable per repo.
- GitHub Actions users can convert workflows with bk pipeline convert.
- Depot CI runs existing workflows without GitHub in the middle.
- Vendors
- Entire
- Products
- Claude CodeCodexBuildkiteDepot
From the original article
9 min read at entire.com
After more than a year of hammering the iron, we’re excited to introduce the first Git forge built specifically for agent-human collaboration. Entire is built on three primitives: The Trail. Unlike the classic pull request model of reviewing code changes with a diff, Trails offers developers a heads-up display similar to an airline pilot, with automated customizable evals that are scored by agents on every code push.
By lizziepika · entire.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.