# Entire: Ex-GitHub CEO's Git Forge for Agents, Explained

> Ex-GitHub CEO Thomas Dohmke's Entire replaces the pull request with agent-scored Trails, adds regional Git hosting and repo memory. What it costs.

- Author: Nitish Garg, Founder & CEO, CellCog
- Published: 2026-10-27
- Canonical (HTML): https://cellcog.ai/blog/entire-git-forge-for-agents/
- Section: Guides / Choosing a platform
- Publisher: CellCog (https://cellcog.ai), the AI employee platform. Blog index for agents: https://cellcog.ai/blog/llms.txt

## Key points

- Entire, the startup led by former GitHub CEO Thomas Dohmke, launched its full Git forge on October 26, 2026, built for teams where agents write most of the code.
- Trails replace the pull request: review agents score every push on evals such as security, slop and risk, and a merge waits until the scores are green and the findings are closed.
- Entire hosts or mirrors repositories in the US, EU, Australia and India, and its own open-source benchmark puts pushes at up to 89 times faster than GitHub.
- Continuous Memory stores agent sessions in the repository; the open-source entire-graph and entire-brain plugins turn them into context the next agent can search.
- The platform is free at launch with a $100 starter credit for review-agent tokens, then market model rates; public repositories and self-hosted nodes are still on the roadmap.

## At a glance

- **What is Entire?** A Git-compatible forge from former GitHub CEO Thomas Dohmke, built on three parts: Trails for agent-scored review, distributed Git hosting across regions, and Continuous Memory that keeps agent sessions in the repo.
- **What replaces the pull request?** A Trail. Review agents score each push on evals and return findings; merge gates wait for green scores, human approvals and passing CI.
- **What does it cost?** The platform is free at launch. Review agents use model tokens: Entire gives a $100 starter credit, then charges market rates for the model you choose.

**Entire, the startup led by former GitHub CEO Thomas Dohmke, launched "the first Git forge built specifically for agent-human collaboration" on October 26, 2026.** It hosts code like GitHub, but the review page, the CI and the memory are designed for teams where agents write most of the changes and humans decide what merges.

Dohmke's thread went up at 17:00 UTC and passed 73,000 views within eight hours. The New Stack noted the timing: two days before GitHub Universe.

## What Entire shipped

Entire's launch post names three primitives, plus CI partners:

- **Trails.** A replacement for the pull request. Review agents score every push on evals and return findings, and the page shows those scores first.
- **Distributed Git hosting.** A new Git-compatible server with a distributed object store. You pick a primary region and replicate to others: the US, EU, Australia and India today.
- **Continuous Memory.** Agent sessions and prompts are synced into the repository and made searchable for the next agent.
- **CI through partners.** Buildkite and Depot at launch, each able to convert existing GitHub Actions workflows (`bk pipeline convert`, `depot ci migrate`).

## How a Trail works

Dohmke's diagnosis of the pull request is blunt: "The pull request has become an audit log that only the agent reads." Coding agents and review agents trade long comments in a linear timeline, and the human at the bottom still cannot tell whether the change is safe to merge.

A Trail turns that loop into numbers at the top of the page:

1. **Start.** A Trail opens from a bug report, a feature request or straight from your agent, and can span several repositories.
2. **Score.** On each push, review agents run independently in cloud sandboxes (Daytona and E2B, using Claude Code and Codex) and each returns a score and a rationale. The page shows the current run and the last five, so you can see whether scores have settled.
3. **Close and merge.** Findings carry severities and suggested fixes; agents or humans address or dismiss them. Per-repo Gates can require green evals, human approvals and passing CI before the merge.

![Animated scene: an agent pushes, Security, Slop and Risk gauges score it, Slop shows one finding, the agent pushes again, all gauges turn green and the merge gate opens](https://cellcog.ai/blog/media/entire-git-forge-for-agents/trail.svg)
*Review is a loop: agents push, evals score, the gate opens when all are green*

Each project ships with preset agents for code quality, security and slop, and teams can define their own in the UI or in a `.json` file in the repo.

*Table: Pull request vs Trail, as Entire describes them*

| | Pull request | Trail |
|---|---|---|
| What you read first | A comment timeline | Eval scores on every push |
| Who reviews | People, plus an AI reviewer if added | Review agents in sandboxes, plus people |
| Merge signal | CI status and approvals | Gates: evals, approvals and CI |
| Scope | One repository | One or several repositories |
| Context kept | The diff and comments | The request, agent sessions and code |

## How fast, and where

Entire says its forge is the fastest in production. Its own open-source benchmark, ForgeMark, measures pushes per second:

*Table: Pushes per second in Entire's benchmark (launch post, October 26, 2026)*

| Forge | Pushes per second |
|---|---|
| Entire | 418 |
| Cursor Origin | 65 |
| Pierre | 15 |
| GitLab | 10 |
| GitHub | 4.7 |

That is where "up to 89x faster than GitHub and 6x faster than Cursor Origin" comes from. It is a vendor benchmark; push throughput matters most when many agents push at once, less for a small team.

Leaving GitHub is optional. As Dohmke put it in a reply: "You don't need to leave, you can have both, we even offer GitHub mirroring." A mirrored repository keeps GitHub as the source of truth and can still run Trails on its pull requests; if GitHub goes down, Entire keeps serving clones from the regional mirror and agents can push to branches prefixed `entire/unmirrored/`. Moving for good uses the `entire-migrate` plugin, or a Detach button for mirrors hosted in the US.

## Continuous Memory

Dohmke's thread makes the claim plainly: "Session logs are now the second most important artifact in software development, and they belong in the repo."

Two open-source, local-first plugins for the Entire CLI do the work:

- **entire-graph** parses the repository locally with tree-sitter into a map of definitions, callers, types and routes. Entire says it makes no network requests or model calls, and saved up to 71% on tokens in its testing.
- **entire-brain** indexes recorded agent sessions against that map, so the next agent can recall why the code looks the way it does, which fixes already shipped, and which tests broke last time. Connected to Entire's backend, those memories are shared across a team and shown on each Trail.

This builds on Checkpoints, the session-capture CLI Entire launched with in February. The CLI already integrates with Claude Code, Codex, Gemini CLI and, since October 16, Grok Build.

## What it costs, and what is missing

- **Price.** The New Stack reports the platform is free and customers pay only for the tokens the review agents use: a $100 starter credit, then market rates for the model you pick. Entire publishes no plan page yet.
- **Repositories.** Native hosting covers private repositories at launch; public repositories and self-hosted Git nodes are on the roadmap, per The New Stack.
- **Open source.** The CLI, entire-graph and entire-brain are MIT-licensed. The launch post does not describe the hosted forge or Trails as open source.

## Who is behind it

Entire announced a $60 million seed round at a $300 million valuation on February 10, 2026, led by Felicis with Madrona, M12, Basis Set, 20VC, Cherry Ventures, Picus Capital and Global Founders Capital. Angels included Gergely Orosz and Theo Browne. Entire says it built Entire using Entire.

## Our conflict, and who this is for

Our conflict, declared: CellCog sells AI employees, including an AI software engineer that keeps its own memory of a codebase between tasks, so we have a view on where agent memory should live. Treat our read with that in mind.

Entire's bet is that review, not writing code, is now the bottleneck, and that the fix needs a new forge rather than an AI reviewer bolted onto a pull request. It fits engineering teams that already run several coding agents in parallel, want merge decisions backed by repeatable evals, and need code kept in a specific region. A team pushing a few human-written pull requests a day will feel less of the difference.

## What we are watching

- **Pricing beyond the credit.** Whether Entire publishes plans, and what review-agent runs cost per push at market rates.
- **Public repositories.** When open-source projects can host on Entire, and whether Dohmke's hinted help for maintainers arrives.
- **GitHub's answer at Universe.** What GitHub ships for agent review two days after this launch.
- **Outside benchmarks.** Independent push and clone numbers against ForgeMark's.

## Sources

- Entire, [The Git Forge for Agent-Human Collaboration](https://entire.com/blog/the-git-forge-for-agent-human-collaboration), Thomas Dohmke, October 26, 2026.
- Thomas Dohmke, [launch thread on X](https://x.com/ashtom/status/2114763996691562540), October 26, 2026, 17:00 UTC, and [reply on mirroring](https://x.com/ashtom/status/2114878025674440707).
- The New Stack, [Ex-GitHub CEO launches a GitHub rival that reinvents the pull request](https://thenewstack.io/entire-trails-agentic-code-review/), Frederic Lardinois, October 26, 2026.
- Entire, [seed round announcement](https://entire.io/news/former-github-ceo-thomas-dohmke-raises-60-million-seed-round), February 10, 2026.
- Entire, [Entire CLI on GitHub](https://github.com/entireio/cli).

## FAQ

**Who founded Entire?**

Thomas Dohmke, the former CEO of GitHub, who is Entire's co-founder and CEO. The company announced a $60 million seed round at a $300 million valuation, led by Felicis, on February 10, 2026.

**Do I have to leave GitHub to use Entire?**

No. You can mirror a GitHub repository, keep GitHub as the source of truth and still run Trails on your pull requests, or migrate the repository to Entire later.

**Which coding agents work with Entire?**

Dohmke names Claude Code, Codex, Cursor, pi, GitHub Copilot and Kiro. Entire's own review agents run on Claude Code and Codex in cloud sandboxes from Daytona and E2B.

**Is Entire open source?**

Parts of it. The Entire CLI and the entire-graph and entire-brain memory plugins are open source and MIT-licensed; the hosted forge and Trails are not described as open source.

**How does Entire handle CI?**

Through partners. Buildkite and Depot connect at the project level, convert existing GitHub Actions workflows, and report each build as a check on the Trail.

## Related

- [Cursor Origin Pricing: What It Actually Costs in 2026](https://cellcog.ai/blog/cursor-origin-pricing/index.md)
- [Cursor Agent SDK: Agents as Code, Evals, Self-Hosting](https://cellcog.ai/blog/cursor-agent-sdk/index.md)
- [Claude Writes 90% of Claude Code: How Review Keeps Up](https://cellcog.ai/blog/claude-code-90-percent-code-review/index.md)
- [Best AI Agent Harnesses: October 2026 Rankings](https://cellcog.ai/blog/best-ai-agent-harnesses/index.md)

## The AI employee for this read

[AI Software Engineer](https://cellcog.ai/ai-employees/ai-software-engineer): I built this page. For what it covers, hire an engineer: it works in your repo behind an approval gate, so nothing reaches your world unclassified.

---

Markdown alternate of https://cellcog.ai/blog/entire-git-forge-for-agents/. Try CellCog free, no credit card needed: https://cellcog.ai/signup