Coding

Show HN: Git for AI Agents

A Version Control System for AI Agents Emerges, Bringing Transparency to Agent Decision-Making. A new open-source tool, inspired by Git's version control capabilities, aims to provide a similar framework for tracking and auditing AI agent actions, enabling users to query and analyze agent decisions, and even "rewind" or "bisect" previous sessions to identify changes. This innovation could fundamentally shift the way developers interact with AI agents.

Oscar V (AI-assisted) May 8, 2026 1 min read EN

Based on reporting from Source.

Version control for AI agent activity is now available through an open-source tool called re_gent. This tool allows users to track what their AI agents did, which prompt wrote each line, and rewind when things break.

Overview

re_gent stores agent activity in a .regent/ directory, similar to how Git stores version control information in a .git/ directory. Every tool call creates a Step, which includes information such as the parent step, workspace snapshot, conversation delta, tool name, arguments, and result. Steps form a directed acyclic graph (DAG), and each session has its own branch.

What it does

re_gent provides several commands for users to interact with their AI agent activity. These commands include:

rgt init: Initialize .regent/ in the current directory
rgt log: Show step history (supports --session, -n, --since)
rgt sessions: List all active sessions
rgt status: Show current repository state
rgt show : Display full context for a step (tool call + conversation)
rgt blame [:]: Show per-line provenance for a file
rgt cat : Inspect any object by hash (debug)
rgt version: Print version information
rgt completion: Generate shell completion scripts

Coming soon are commands for non-destructive time-travel (rgt rewind), garbage collection (rgt gc), and creating a new session from a step (rgt fork).

Tradeoffs

re_gent is designed to complement Git, not replace it. It provides features such as content-addressed storage, fast queries, per-session DAG, conversation tracking, and hook-driven integration with Claude Code. re_gent is built in public, and contributions are welcome.

In conclusion, re_gent provides a much-needed solution for tracking and auditing AI agent activity. Its features and commands make it a useful tool for developers working with AI agents. By using re_gent, developers can gain more insight into their AI agents' actions and decisions, making it easier to debug and improve their systems.

More articles like this

Coding 1 min

Open Source Resistance: keep OSS alive on company time

As companies increasingly adopt "open-source everything" policies, a grassroots movement is emerging to ensure that employees can contribute to open-source projects on company time without sacrificing their intellectual property or compromising sensitive data. This pushback is centered around the concept of "open-source-compatible" enterprise software licenses, which would allow developers to contribute to OSS projects without risking corporate liability. The movement's advocates argue that such licenses are essential for preserving the integrity of open-source ecosystems.

Coding 2 min

The limits of Rust, or why you should probably not follow Amazon and Cloudflare

Rust's promise of memory safety is being put to the test as Amazon and Cloudflare's high-profile migrations to the language reveal a disturbing trend: the more complex the system, the more it exposes the limitations of Rust's borrow checker. Specifically, the language's inability to handle cyclic references and its reliance on manual memory management are causing headaches for developers. As a result, some are questioning whether Rust is truly ready for prime-time.

Coding 1 min

The AI Backlash Could Get Ugly

As the AI industry's carbon footprint and data storage needs continue to balloon, a growing coalition of environmental activists and community organizers is linking the expansion of data centers to rising rates of political violence and displacement, sparking a contentious debate over the true costs of AI's accelerating growth. The movement's focus on data center siting and energy consumption has already led to high-profile protests and municipal ordinances restricting new facility development.

Coding 1 min

Software Developers Say AI Is Rotting Their Brains

As AI-driven development tools increasingly rely on opaque, black-box models, software engineers are reporting a surge in cognitive dissonance, with many citing the inability to understand or debug complex neural networks as a major contributor to mental fatigue and decreased job satisfaction. This phenomenon is particularly pronounced in the use of large language models, which often employ transformer architectures and billions of parameters. The resulting "explainability gap" threatens to undermine the productivity gains promised by AI-assisted coding.

Coding 2 min

My graduation cap runs Rust

A DIY robotics project showcases the potential of Rust for real-time, low-latency systems, leveraging the language's memory safety guarantees and concurrency features to control a graduation cap's LED display and motorized movement. The project's use of the Tokio runtime and async-std library highlights Rust's growing adoption in the embedded systems and robotics communities. By pushing the language's capabilities in these domains, developers may unlock new applications for Rust in the IoT and automation spaces.

Coding 1 min

When "idle" isn't idle: how a Linux kernel optimization became a QUIC bug

A latent Linux kernel power-saving quirk—collapsing CPU idle states too aggressively—has triggered catastrophic QUIC packet loss on Cloudflare’s edge, forcing a custom kernel patch that trades microjoules for microseconds. The fix exposes how energy governors, tuned for bare-metal efficiency, clash with latency-sensitive transport stacks when milliseconds decide user churn.