Multi-Agent Code Review
Hey HN! We’re Oliver Gilan & Ben Warren and today we’re launching Mesa (https://mesa.dev) into public beta to help large engineering teams review code more effectively. There are plenty of code review agents that exist but we found that they fall short in a number of ways. They don’t… - Let you tailor the reviews with enough fidelity - Give you control over the models used. If a new foundation model is released I might want to try it! - Align the costs effectively Mesa solves these problems with a multi-agent architecture where you define custom review agents that specialize in…
What it does
In the maker’s words, at launch
Hey HN! We’re Oliver Gilan & Ben Warren and today we’re launching Mesa (https://mesa.dev) into public beta to help large engineering teams review code more effectively. There are plenty of code review agents that exist but we found that they fall short in a number of ways. They don’t… - Let you tailor the reviews with enough fidelity - Give you control over the models used. If a new foundation model is released I might want to try it! - Align the costs effectively Mesa solves these problems with a multi-agent architecture where you define custom review agents that specialize in reviewing certain dimensions of your codebase. This allows you to finely control the review quality and receive reviews that are aware of specific dependencies, business logic, a specific domain in your codebase, or anything else you care about. You can control the model a specialist uses which is great for trying newly released models but also for controlling costs. When a change is made to our database schema, we have a specialist agent that reviews it and uses the most expensive, smartest, model it can while our frontend agent uses a faster, cheaper agent. Control over models and the fact that we only charge you for the tokens you use, at cost, aligns our cost structure and gives teams control that they do not get with other agents. We’ve found code review to be a subtly big problem for teams trying to improve development velocity. It’s the primary point of contact for managing the changes to the living system of your codebase and mistakes are costly. Missed bugs that make it to production can cause downtime, lost revenue, loss of trust, security breaches, compliance breaches, etc. Engineers spend hundreds of expensive man-hours that they do not enjoy reviewing code and still there’s too many mistakes being made. We do not believe you can remove humans from the loop of reviews entirely but we can dramatically shift the amount of work done on an average code review and eliminate the need for human reviews altogether on a large subset of PRs. This sort of automation will lead to faster teams and more reliable codebases over time. We are now in public beta and there’s a generous free tier (~100k lines reviewed free per month) available to all. Give it a spin and let us know what you think! Oliver & Ben
Does the same job
all alternatives →- CACoding Agents swarming your codebaseSep 2025 · infrastructureas.ai · ▲9
I built this because I was tired of creating pull requests in 20 repositories just to change a single line of workflow job version. With Infra as AI, just mention the change. Agents work on all repos in parallel, read the docs, make a bunch of PRs and fill in the description. You can see the demo of the actual dashboard in the landing. Let me know your thoughts :) It means a lot to me!
- IBi built an AI code reviewer for github (used it on itself during dev)2025 · codii.dev · ▲6
I’ve spent the last 2.5 months building a product that runs LLM-powered code reviews on my pull requests — and I just launched it. The tool is built specifically for solo developers. You install it on your repo, trigger a scan by creating a pull request, and it leaves structured review comments using OpenAI under the hood. Funnily enough, I used the dev version of this app to review its own pull requests while building it. It helped me spot bugs, simplify structure, and keep quality high — all with minimal need for another human in the loop. Things I want to try out in the next months : -…
- IBI built new type of dev environment for agentic coding2025 · github.com · ▲6
The main goal of this was to be able to not just run multiple Claude Code sessions at once, but actually manage them and keep track of what I was doing. Sometimes this is multiple attempts on the same task, sometimes I work several tasks at once. Really I was just sick of twiddling my thumbs waiting for the coding agent to finish, and I wanted it to be easy to work on/review/test another change while I waited.
- SRShikigami, run AI coding agents in parallel, each in a Git worktreeJul 2026 · shikigami.dev · ▲7
Hello all, I'm a software developer. Over the last few months more and more of my work has turned into using coding agents instead of typing the whole code myself. Usually a few claude sessions at once, sometimes codex, one per feature or per revealed bug. I ran them in a split terminal for a few weeks, and quickly spotted two main problems. The first is that I couldn't easily tell which agent was stuck waiting on me and which was still working, so I'd cycle through sessions and checking on them. The second one: agents sharing a single branch step on each other. Two of them could be editing…
- ARAgents, run any coding agent on your subscription not API costsMay 2026 · agents-cli.sh · ▲6
Hi HN. I'm the founder of Phoenix Labs (ex TikTok, Applied AI) and we're open sourcing our internal tooling today which is like a toolchain / meta-harness for CLI agents useful for really scaling eng and creative work. We are a very small team who's building a very ambitious product so we had to find ways to squeeze every ounce of efficiency that we could get our hands on. Harness strengths of different models (Claude, GPTs) and CLI-harnesses (Claude Code, Codex), safe/robust browser integration to speed up UX/QA testing, teams cli to speed up security reviews and parallelize…
- OAOpenRig – a control plane for multi-agent coding topologiesMay 2026 · openrig.dev · ▲6
Hi HN, I’m Mike, the founder of OpenRig. I built this because my Claude Code + Codex setup kept forming little "topologies" of long-lived agents that worked well together, but the terminal sprawl was intense. So I built a primitive the agents could intuitively reach for to save and recreate these setups on the fly. This then led to more agent-first primitives like coordination, declarative workflow patterns, workspaces, etc. Several months in and these "rigs" I manage with openrig require a lot less babysitting and I can manage more projects at once without getting overwhelmed. The short…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology