Skip to content
aicoolies logo
Checkpoints by Entire logo

Checkpoints by Entire

Git-native AI agent session capture and reasoning traceability

Checkpoints by Entire captures the full reasoning context behind AI-generated code directly in Git. Entire records transcripts, prompts, files touched, token usage, and tool calls alongside every commit. Session metadata lives on a separate branch keeping your history clean, with rewind capabilities to restore any previous agent checkpoint when things go sideways.

About Checkpoints by Entire

Checkpoints introduces a new Git primitive that treats AI reasoning as first-class versioned data. When an agent like Claude Code or Gemini CLI generates a commit, Checkpoints automatically captures the full session context including the transcript, original prompts, files modified, token consumption, and tool invocations. This metadata is stored on a dedicated branch called entire/checkpoints/v1, keeping the primary branch history clean while creating an append-only audit log of the reasoning behind every AI-assisted change.

The rewind capability allows developers to restore their codebase to any previous checkpoint when an agent goes sideways, then resume the session from that known-good state with full context preserved. Each session is identified by a date-UUID format and linked to commits through a 12-character hex trailer in the commit message. Nested session support captures sub-agent hierarchies when a primary agent spawns child agents, preserving the complete multi-agent workflow context. Git worktree compatibility enables independent session tracking across parallel workspaces.

Founded by Thomas Dohmke, who scaled GitHub Copilot during his tenure as GitHub CEO, Entire positions Checkpoints as the first open-source CLI in a broader AI-native developer platform. Launch and funding posts describe company backing from Felicis, Madrona, M12, Garry Tan, and Olivier Pomel, including a $60M seed round and $300M valuation; because Entire's current site and docs emphasize product workflow rather than financing, this page treats those numbers as company-context signals instead of capability proof. The tool supports Claude Code, Gemini CLI, OpenCode, Cursor, Factory AI Droid, and GitHub Copilot CLI with a two-step setup process, while the MIT-licensed CLI underpins a broader Git-compatible database and semantic reasoning roadmap.

Pricing & Platform Specs

Pricing Summary

Free and open source under the MIT license ($0 software cost). Checkpoints by Entire provides a 100% free, Git-native local CLI with no seat licenses, subscription paywalls, or mandatory cloud lock-in for tracking and rolling back AI agent coding sessions.

full pricing breakdown →

Supported Platforms

CLI on macOS, Linux, Windows

Explore categories, tags & use cases

Virtual engineering team as Claude Code skills by YC CEO Garry Tan

GStack transforms Claude Code into a structured virtual engineering team through 23 opinionated slash command skills created by Y Combinator CEO Garry Tan. It assigns specialist roles including CEO product review, engineering manager architecture oversight, designer visual audit, QA lead with real browser testing, and release engineer deployment. Each skill enforces focused workflows with clear decision principles for running parallel coding sessions.

Open Source

Agent harness performance system with 30+ agents and 136 skills

Everything Claude Code is a comprehensive agent harness performance optimization system providing 30 specialized agents, 136 skills, 60 commands, and automated hook workflows for AI-assisted development. Born from an Anthropic hackathon winner and evolved over 10+ months of intensive daily use, it works across Claude Code, Codex, Cursor, and OpenCode with built-in security scanning via AgentShield, continuous learning, and research-first development patterns.

Open Source

Kanban board with isolated workspaces for AI coding agents

Vibe Kanban bridges project management and AI coding agents by providing kanban-style issue tracking with dedicated workspaces where agents like Claude Code, Codex, and Gemini CLI execute tasks. Each workspace gets its own Git branch, terminal, dev server, and preview environment through Git Worktrees isolation. Developers can review diffs, leave inline comments, and manage 10+ parallel coding sessions from a single Rust-powered interface with a local-first SQLite architecture.

Open Source

Community experience

Sources & verification

Sources checked
Content verified

Verification dates are editorial checks. Routine CMS saves and automatic updatedAt timestamps do not advance them.

FAQ

What is Checkpoints by Entire?

Checkpoints by Entire captures the full reasoning context behind AI-generated code directly in Git. Entire records transcripts, prompts, files touched, token usage, and tool calls alongside every commit. Session metadata lives on a separate branch keeping your history clean, with rewind capabilities to restore any previous agent checkpoint when things go sideways.

Is Checkpoints by Entire free?

Yes — Checkpoints by Entire is open source and free to use. Free and open source under the MIT license ($0 software cost). Checkpoints by Entire provides a 100% free, Git-native local CLI with no seat licenses, subscription paywalls, or mandatory cloud lock-in for tracking and rolling back AI agent coding sessions.

Is Checkpoints by Entire open source?

Yes — Checkpoints by Entire is open source.

Is Checkpoints by Entire still maintained?

Yes — Checkpoints by Entire is active. Its listing was last verified on September 6, 2026.

What are the best Checkpoints by Entire alternatives?

The first editor-selected Checkpoints by Entire alternatives are GStack, Everything Claude Code, Vibe Kanban.

How does Checkpoints by Entire score in our review?

The published editorial review lists Checkpoints by Entire at 83/100 overall across speed, privacy, and developer experience. Check the review's evidence status and test metadata for its verification level.