Comments URL: https://news.ycombinator.com/item?id=48504325

Points: 4

# Comments: 0

The thing that makes this work is where in the loop the review happens. CodeRabbit, Greptile, etc review at the PR level after the agent is done. The findings go to a human who has to interpret them. The agent that wrote the code never sees the critique. We find that most people just spin up a new agent and ask "Are these review findings correct?" anyways.

Saguaro reviews during the agent's session and sends findings back to the same agent. Because the agent still has its full context window, it knows why it made each decision, it can evaluate the findings intelligently. "I made this choice for X reason, but this review shows a gap in my thinking, let me fix that." Or "This finding isn't relevant because of Y." The agent has the context to make that judgment call. That's why false positives are lower.

The daemon is completely invisible to the user. It self-spawns from the Claude Code stop hook, runs a SQLite-backed job queue on localhost, and auto-shuts down after 30 minutes idle. The review happens in the background while the user keeps working. We feed context from the original programming session into the review process. The findings surface on the next stop hook, your agent just starts fixing things.

For teams that want more precision, there's a rules engine: markdown files with YAML frontmatter that enforce specific patterns (architectural boundaries, security invariants, etc). But the daemon works with zero rules out of the box. The rules engine works great for teams with well-defined rules.

Some technical decisions: - SQLite (via better-sqlite3) as job queue, right amount of infrastructure for a local dev tool. - The daemon reviewer gets the original agent's summary ("the developer described their work as...") for context - Agent gets read-only tools (Read, Glob, Grep) with up to 15 tool calls per review, it can inspect the full codebase for context but can't edit.

Limitations: - The daemon review is async. Findings arrive on the next stop hook, not the current one. Fast iterations may miss a cycle. - Review quality depends on the model. We default to your configured model but you can override for daemon specifically. - Cost is your normal AI provider usage. `sag stats` tracks it.

Happy to answer technical questions about the architecture.

Saguaro is a background daemon that reviews AI-generated code and feeds findings back to the same agent that wrote it. The agent evaluates the critique, it knows why it made those decisions in the first place, and self-corrects what's actually wrong.

The flow: you tell Claude Code to build something. Claude writes code. Saguaro's stop hook triggers a background review (the user sees nothing). On the next turn, findings come back to Claude. Claude says "I see some issues with my approach, fixing now" and corrects itself. No human typed anything. No blocking.

It uses your existing Claude Code / Codex / Gemini subscription. No API key needed. No external account. Everything runs locally. The daemon self-spawns on demand and auto-shuts down after 30 minutes of inactivity.

There's also a rules engine for teams that want more deterministic enforcement. You write rules as markdown files with YAML frontmatter, scoped to specific file globs. But the daemon works out of the box with zero rules. It reviews like a senior staff engineer: bugs, security, regressions, dead code. The rules engine adds more precision for teams/individuals that need it.

Setup is "sag init" + restart CC + go back to coding. That's it.

Apache-2.0. TypeScript.

Comments URL: https://news.ycombinator.com/item?id=47340583

Points: 3

# Comments: 3

Comments URL: https://news.ycombinator.com/item?id=47183524

Points: 4

# Comments: 0

We designed our integration with Claude code to reject edits before it's written if it violates a rule via an exit 2 code. Also don't think any system will be 100% on rule enforcement, senior reviewers included. We can't be perfect but we can raise the floor.

Actually our approach is the opposite. Writing rules forces teams to articulate what their standards are. Mesa makes you write them down, version control them, and review them as code, similar to a linter. This specificity is why this system works much better than a standard AI code reviewer that checks for general issues.

We aren't trying to replace tests or humans. The goal is to make them more effective by filtering out the noise before it reaches them.

Comments URL: https://news.ycombinator.com/item?id=47172228

Points: 5

# Comments: 3

Those problems are real independent of Mesa. I do shoutout an open source project we have called AgentBlame but don't talk about anything related to proprietary software or why Mesa is the end-all-be-all.

Thanks for your feedback, definitely did not mean for this to come across as an ad.

Comments URL: https://news.ycombinator.com/item?id=47066213

Points: 11

# Comments: 5