Former GitHub CEO's Entire Redefines Git for the Agent Era
Can you explain why an AI agent wrote code a certain way three months from now?
Git records what changed, but not why those decisions were made. Entire, co-founded by former GitHub CEO Nat Friedman, tackles this problem head-on.
Key Features
Entire Checkpoints is a layer on top of existing Git. It stores not just code changes but the AI agent's decision-making context—prompts, intermediate reasoning, and alternative comparisons.
- Context Checkpoints: Bundle code diffs with decision records
- Agent Replay: Reproduce an agent's thought process at any point
- Branch Comparison: Visually compare alternatives the agent considered
Why It Matters
In 2026, 30-50% of codebases are written by AI agents. Git commit messages alone can't track an agent's decision rationale. Entire provides the infrastructure to record the "why."
Implications
Entire's approach goes beyond version control. In an era where agents write code, it builds the foundation for human developers to understand and verify AI decisions.
Related Stories
Stay ahead of AI
Top stories, curated daily. No spam, no noise. Unsubscribe anytime.