Sploom releases an AI code provenance tool
Understand this story
Sploom has released a code provenance tool that runs in parallel with git and can record which agent and which model wrote each line of code, and based on what prompt and intent. The tool runs locally: the first use requires downloading an embedding model of about 130 MB, after which it can work offline; installation requires Rust and git. When connecting to different agents, hooks must first be authorized: Codex requires one-time approval with /hooks, Grok Build uses /hooks-trust, Gemini CLI asks whether to trust, and Cline requires enabling "Enable Hooks" in VS Code settings.
AI overview based on source reports · Updated 3 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: Trace AI written code back to the agent and prompt
Sploom is a tool that lives alongside git and records which agent and model wrote each line of code, along with the intent, prompts, decisions and checks behind it, working with Claude Code, Codex, Cursor, Gemini CLI, Copilot CLI, Devin CLI, Grok Build, Goose, Cline and any MCP-capable agent. After a one-time `sploom init`, it installs git hooks so provenance travels with commits via git notes, and offers commands like `sploom why`, `sploom rewind --green` and `sploom context`. Prompts are encrypted to the team's SSH keys listed in a committed `.sploomkeys` file, and it runs locally with an initial ~130 MB embedding model download.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 12 01:00
- Change in the past 24 hours
- -51%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.