On Oct 26, Entire co-founder and CEO Thomas Dohmke announced on X and the company blog that Entire is live as "the Git forge for agent-human collaboration." It has three parts: Trails, which replace diff-based review with eval scores computed on every push; Git-compatible distributed hosting that can replicate across regions or mirror from GitHub; and Continuous Memory, which stores agent sessions in the repo. Buildkite and Depot are the first CI integrations, and it is open to any developer today.
Key Takeaways
- ✓Push speed (vendor-reported, open-source benchmark): Entire 418 pushes/s vs Cursor Origin 65, Pierre 15, GitLab 10, GitHub 4.7, i.e. up to 89x faster than GitHub and 6x faster than Cursor Origin
- ✓Trails: on every push, several review agents score the change independently in cloud sandboxes (defaults include Security, Slop and Human Review Required), showing the last 5 runs plus the current one; per-repo Gates can require human approval and passing CI before merge
- ✓Continuous Memory: two open-source, local-first plugins, entire-graph and entire-brain; entire-graph saved up to 71% of tokens in Entire's testing
- ✓Regions at launch: US, EU, Australia and India; repos can be mirrored from GitHub with GitHub kept as the source of truth
- ✓Pricing: not stated in the launch post
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Core Background & Industry Pain Points
Agents now write code faster than humans can review it. In the launch post, Entire co-founder and CEO Thomas Dohmke (former GitHub CEO) argues that the linear pull request timeline is flooded by coding-agent and review-agent comments and has become "an audit log that only the agent reads," leaving developers unsure whether they can merge with confidence. Entire rebuilds hosting, review and context memory around agents.
Architecture Highlights & Internals
First, Trails: every push triggers several review agents that run Claude Code and Codex in isolated sandboxes from Daytona and E2B, each returning a score and a rationale. Evals can be configured in the UI or as .json in the repo, and one Trail can span several repositories. Second, a new Git-compatible source control server built on a distributed object store and a transactional ref database, with multi-region replication and data residency. Third, Continuous Memory: entire-graph builds a local code map with tree-sitter, and entire-brain indexes agent sessions recorded in Git history into retrievable memories.
Authoritative Benchmarks & Measured Scores
Vendor-reported: in Entire's open-source benchmark, pushes per second were Entire 418, Cursor Origin 65, Pierre 15, GitLab 10 and GitHub 4.7. entire-graph saved up to 71% of tokens in Entire's testing. No independent third-party measurements yet.
Developer Hands-on Guide
Create a repo from the web UI or the Entire CLI, or mirror an existing repo via the GitHub App, keep GitHub as the source of truth and layer Trails on top of PRs; during a GitHub outage, agents can push to entire/unmirrored/ branches. The entire-migrate plugin handles full migration. CI connects to Buildkite or Depot, which can convert GitHub Actions with depot ci migrate. Pricing was not announced.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.