Former GitHub CEO Thomas Dohmke launched Entire on October 26, 2026, introducing an agent-first Git platform designed for AI-driven development. Supported by $60 million in seed funding at a $300 million valuation, Entire addresses GitHub performance bottlenecks by replacing traditional pull requests with automated agent evaluations called Trails. Operating up to 89 times faster than GitHub, the platform utilizes Continuous Memory and codebase mapping to slash agent token consumption by up to 71% across globally distributed repositories.
Entire launch and funding
- ▪Entire raised $60 million in seed funding led by Felicis at a $300 million valuation in February 2026, with participation from Madrona, Microsoft's M12, and Basis Set
- ▪Former GitHub CEO Thomas Dohmke officially launched Entire, a Git-based developer platform built for AI agents
Core platform design
- ▪Entire is building its platform infrastructure around existing AI coding agents rather than developing its own foundation models
- ▪Entire's platform includes three core components: Trails for agent-based code reviews, distributed Git hosting, and Continuous Memory for retaining context in repositories
Trails code review mechanism
- ▪Entire uses Claude Code and Codex to run review workflows within isolated cloud environments provided by Daytona and E2B
- ▪Entire's Trails feature replaces traditional pull requests with independent cloud sandbox evals scored by agents on security, code quality, and human review requirements
- ▪Developers using Entire's Trails feature can set rules called Gates that block merges until specified conditions, including passing Buildkite or Depot CI checks and human approvals, are met
Distributed Git architecture and performance
- ▪Entire claims its Git-compatible source control server processes up to 418 code pushes per second, operating up to 89 times faster than GitHub and six times faster than Cursor Origin
- ▪Entire's distributed Git architecture allows developers to host or mirror private repositories across regions in the US, Europe, Australia, and India while continuing to use GitHub as a source of truth
Continuous Memory features and token reduction
- ▪Entire claims that using Continuous Memory and Entire Graph reduces AI agent token consumption by up to 71% by preventing agents from repeating resolved mistakes
- ▪Continuous Memory comprises open-source tools Entire Graph and Entire Brain, which store session logs, prompts, and codebase dependency maps inside repositories
Story comments
Loading comments…