Map

re_gent

Toolbox toolboxgoagentic-codingvcswatchlistGoApache 2.0 ↳ show in map Markdown
title
re_gent
type
toolbox
summary
Git-shaped version control for AI agent activity, with log, blame and show per tool call
tags
go, agentic-coding, vcs, watchlist
repo
https://github.com/regent-vcs/re_gent
language
Go
license
Apache 2.0
created
2026-05-10
updated
2026-05-10

re_gent is a git-shaped version control system for AI agent activity. It tracks each tool call an agent (specifically Claude Code today) makes, captures the workspace snapshot, conversation transcript, and tool invocation, then exposes git-like commands (log, blame, show) over the resulting history. The idea is to make agent activity auditable per-prompt, not per-PR.

How it works

Storage lives in a .regent/ directory analogous to .git/. Each tool call creates a Step containing:

  • Parent step hash (chains form a DAG)
  • Workspace snapshot before/after
  • Conversation transcript at that point
  • Tool name, arguments, result
  • Session ID
  • Timestamp

Steps form a directed acyclic graph; each session is its own branch. Storage uses BLAKE3 content addressing for deduplication and SQLite for the index. Hooks capture Claude Code activity transparently — no separate driver, no manual rgt commit.

Critically, the conversation history is preserved across /compact operations. So rgt blame file.go:42 can return not just "step abc123 wrote this line" but "this prompt at this point in this conversation produced this line." That's the missing primitive for agent-driven engineering: a stable spec→code link that survives context compaction.

Usage

brew install regent
rgt init
rgt log              # view step history
rgt blame file.go:42 # which prompt wrote this line
rgt show <step>      # full step context

Status / limitations

  • 265 stars at time of ingest, Apache 2.0
  • Pre-v1.0; the README describes the codebase as "production-quality at POC-level feature completeness"
  • Currently focused on Claude Code; Cursor/Cline adapters planned for later phases
  • Planned but not implemented: rewind, fork, multi-tool support
  • Not yet integrated with PR workflows — the agent-VCS history is local to the developer, not shared across review

Conceptually adjacent to acceptance-criteria-ids (acai's spec-back-reference idea) and to forge (Nesbitt's unified git-host CLI; agents need both forge-level operations and an agent-history layer). Solves a real problem named in agent-principal-agent-problem — when the prompt is the contributor, you need provenance at the prompt grain.

Watchlist reason

On watchlist: pre-v1.0, single-author, narrow Claude Code coupling, planned-but-not-built core features. Re-check in 90 days for: v1.0 release, Cursor/Cline adapters, integration with PR review tooling, whether other coding-agent ecosystems have shipped similar primitives that obviate it.

Linked from