Hi team! I'd like to discuss one idea, I don't know how much it is relevant for you now at all, but to me it looks like a pretty natural continuation of what you already have in guardrails.

It is about something like policy dry run / what-if for tool policies: so it would be possible to run tool call scenarios through current or proposed policies and see what would happen with them and for what reason.

I see two modes here:

1. synthetic scenarios - more for new clients, I don't know how your sales are organized, but potentially it could be useful there.

2. running on historical cases - for already existing clients, so before changing a policy they could see how it would affect their real scenarios.

It seems to me that in a light version this should fit pretty well into the current architecture.

If it's interesting, I'd be glad to discuss it more and take implementation on myself.

Hey, my name is Anmol-I'd love to work on issue https://github.com/archestra-ai/archestra/issues/3406 (Claude models failing through the Bedrock proxy with body/system/1 Invalid input). Mind if I pick it up?

New release! 🚀🚀🚀

Features

Bug Fixes

Miscellaneous Chores

Hey team!

I've had a few feature ideas that I think could really improve the experience for users. Wanted to check if they align with the current roadmap. If they look good, I'd be happy to open issues and take them on!

1. Agent Cloning (One-click duplication): Right now, if you want to fork an agent to test a new prompt or slightly different toolset, you have to recreate the whole config (tools, KBs, sub-agents, labels) from scratch. I’ve seen this in a few other products and it's a huge time-saver. It would be a pretty self-contained backend addition using the existing model associations.

2. Knowledge Base Search Feedback Loop: Right now, we can see sync stats and query volume, but we have no way to know if cited documents actually helped the user. Adding small 👍/👎 buttons to citations in chat would give us a direct signal on which docs are authoritative vs. which ones are just noise. This helps admins find content gaps (frequent 👎) and identify outdated docs without manually auditing thousands of files. In the long run, we can feed this data back into rrf.ts to automatically boost documents that users find consistently helpful. I think it adds a lot of value for anyone managing enterprise knowledge at scale.

What do you all think?

New release! 🚀🚀🚀

Features

Bug Fixes

Hey team 👋. I'm Sasha)

I’m interested in contributing to this issue: https://github.com/archestra-ai/archestra/issues/3838

Before I jump in, I wanted to ask - is there already a defined vision or some expectations for how this should be approached? Or is this more of an open-ended task where contributors are encouraged to propose their own direction/implementation?

Happy to align with any existing ideas, or draft a proposal if it’s still exploratory.

Can't we attempt the the issue with the tag Reserved for SE Interview?

Hi Team, I am Palak

I am interested in contributing to Archestra, but I found that commenting on issues is currently blocked. Could anyone please guide on how can we claim an issue? Should I work on reproducing and provide a video of working fix first?

Ps: I’m about to graduate and have prior experience through internship at MNC as well as open source contributions. I’d also like to know if I’m eligible to participate in the interviews.

Hi everyone! I'm Phil, have been working in software engineering for 15 years, will try and contribute to Archestra in the next few days, then we'll see how it works out

Hi, is the A2A API supposed to work right now, specifically with API keys managed on the Settings page? API keys in Settings are handled via ApiKeyModel, and it looks like that model is not used anywhere. For the A2A API, I only see UserTokenModel and TeamTokenModel.

Hey all,

I’ve been poking at upgrading the repo from TypeScript 5.9 to 6.0, and it looks like a pretty smooth change.

I only ran into two things:

• a tsconfig deprecation warning, already addressed in this PR

• a small TS bug that the stricter compiler checks caught, already fixed in my TS 6 PR

So it feels like we're in a good spot to move to 6.0 without much churn. It also seems like a good prep step for eventually switching to the faster TypeScript 7 toolchain.

TypeScript 6 PR is here https://github.com/archestra-ai/archestra/pull/4035

New release! 🚀🚀🚀

Features

Bug Fixes

Documentation

Miscellaneous Chores

While working on error processing in web chat I noticed we started showing duplicate error cards – it wasn't like this a few days ago. Traced it to the AI SDK invoking onError twice after we added persistence inside that callback. Proposed fix here: https://github.com/archestra-ai/archestra/pull/4047

Hi Kyle looking to be more involved with open source. Experience in building LLM, environments and various programs. I noticed most of the new bounties appear to be for in house members. If there is anything i can jump on let me know!