@trypolygraph
Account based inItaly
About this account
- Account based in
- Italy
- Connected via
- Italy App Store
Account-level information from X, not a live location or the device used for a specific post.
Connect all your repos and agent sessions as if they were one. Prompt once, land everywhere.
Interstellar 🪐
Joined May 2026
- Tweets52
- Following16
- Followers143
- Likes64
The agent that wrote the code is a bad reviewer of it. Better to launch a dedicated agent with minimal context and a different harness.
In a single repo: easy.
If multiple repos are involved: still easy 👇
Starting a session off of a problem someone in the org already hit.
search_sessions turns up 13 past sessions and the closest one gets pulled in as context. Its PR was closed unmerged, so what the agent inherits is why that approach was rejected.
Polygraph retweeted
Everything is code
(even this video, apart from the music...you still need taste for that)
- you make a change to a design system component in its repo
- you ask Polygraph to open a PR on the target repo with the change
- Polygraph packages the changes into a tarball & pushes a PR with it
- the target repo runs all CI tests against it
👇
What if you don't use "polygraph session start" but you just use your agent and push a PR.
Background session capture can now also record those runs and attach the session once a PR is created, effectively connecting the two.
Imagine you upgrade some external OSS dependency and you could just pull in the repo automatically so the agent has full context of how to upgrade it properly.
Work isn’t always limited to a single repository.
Polygraph understands how repos connect to each other and can inject that knowledge into your favorite agent harness.
One agent session involving multiple repos: query them, modify them, and open PRs.
Sessions should be portable beyond a single machine, agent harness or user.
`polygraph session start` wraps the agent you already run tracing the session so it can be resumed at any point, from any machine by any user in your team.
Connect a GitHub org and Polygraph indexes every repo within it, distilling
What would you have your agent do if it could work across a single repo?
Claude go down mid session? No problem, carry on with another agent.
Polygraph retweeted
My @WeAreDevs talk
Meta Harnesses: What the JS Framework Wars Teach Us About What Is Next for AI Agents
is online:
wearedevelopers.com/videos/1…
@trypolygraph #metaharness
Polygraph ❤️ @herdrdev
Just implemented this: @trypolygraph can now fully leverage @herdrdev by automatically spawning and coordinating agents in Herdr panes for changes that span multiple repos.
Herd away! 🐏
Polygraph retweeted
Lately: code reviews via "polygraph session review". Instead of pretending to understand a 6k-line PR, I talk to the agent that wrote it: what was considered, see diagrams. It's an unexpected side-effect of having durable sessions that can be moved from one machine to another.
🤖🤝👨💻
The collaborative part of agentic development is kinda broken right now.
Here’s a concrete example into how we’re trying to fix it internally at @NxDevTools (and how you can, too).
Polygraph retweeted
The collaborative part of agentic development is kinda broken right now.
Here’s a concrete example into how we’re trying to fix it internally at @NxDevTools (and how you can, too).
Polygraph retweeted
Even though I'm mostly a keyboard person, I actually kinda like this.
A lot of people have been hesitant to use the @NxDevTools TUI, and mostly because for some scenarios you just wanna be able to also use your mouse, click on things, scroll, copy etc..
Polygraph retweeted
What advice does @kentcdodds have for engineers wanting to go deeper into AI coding?