#general

Jun 1June 2, 2026Jun 3Latest
EK
Here need guidance from the team - what's the best solution here, cuz changing the model's characteristic leads to undefined behaviour
3 replies
EB
Hello, I'm Eloy, and I'd like to contribute in the project 👀
Y
Hello everyone ! I'm Yanis. I've been working as a Software Engineer (AI focused) for nearly a year now, I've been dealing with MCPs for the major part of it. I found this gem of a software and it's clear to me just by reading the docs that you guys understand the problems you're solving very well.
I like what you guys are doing, i'd love to contribute despite my relative lack of experience. This project uses a tech stack I am not familiar with, so I will probably spend more time learning than implementing. If you think I could pick up a non-urgent issue to sink my teeth into, i'd love to contribute.
Thanks.
EK
Just a quick question:
what's the typical ETA on review to understand if any code fixes are required or it's good to go? These 3 are pending. Feel free to close them if you decide that issues are not worth fixing, thx
NC
Nikola Couture1:30 PMOpen in Slack
Congrats on raising with 20VC - I used to listen to his pod casts on BART in the mornings 13 years ago. Wow time flies.
2 replies
JC
Junyi Chen3:15 PMOpen in Slack
Hey everyone! I'm Junyi, based in London. :gb:
I've spent the past 2.5 years as a founding commercial hire at an AI startup, deploying workflows into heavy industries like building materials, chemicals, and healthcare.
I’ve lived the problem Archestra is solving from the other side: watching enterprises become dependent on external vendors to maintain workflows, while the real context and intelligence sits with their own teams the whole time. The second I saw what you’re building with MCP, it clicked — this is what is going to unlock enterprise AI at scale.
Excited to follow along, share an operator’s perspective, and contribute where I can. Huge congrats on the funding news!
1 reply
EB
Is there a simple issue to start with?
CT
Chris Turner10:39 AMOpen in Slack
Hey everyone, my name is Chris in :gb:, and I am the founder of Proof, creating the GitHub of Agriculture. (almost, not quite.. maybe not)
Looking forward to using Archestra, as I have huge anxieties about data, and think that implementing this at the very start, will act as the core foundation of our business.
Also, if anyone has tons of spare cash that you would like to invest in a 10% chance of becoming disgustingly rich, hit me up.
Jokes aside, thrilled to be part of this community.
A
Congrats to the whole team on the raise! Shared a post about my experience contributing to Archestra. Thanks for building something worth contributing to 🙌
1 reply
AA
Archestra App5:58 PMOpen in Slack
New release! 🚀🚀🚀
1.2.55 (2026-06-03)
Features
  • add environment network policies (#5207) (aac23b0)
  • add instance PostHog analytics events (#5231) (aee3be9)
  • environments (#5134) (937be7b)
  • *mcp-catalog:* clone catalog items, with tools + guardrails inheritance (#5203) (572f618)
  • *mcp-registry:* retire Presets field scope option and sidebar section (#5245) (7d9126c)
  • *mcp-registry:* shareable catalog edit deep-link + environment label (#5237) (9e88cec)
  • *skills:* add generated skill index search (#5242) (b1208ae)
  • *skills:* convert an agent into a skill (#5205) (5971f40)
  • *skills:* ship built-in Archestra skills with reset-to-default (#5223) (5a64ed2)
  • *skills:* templated skills + AI-generated descriptions (#5234) (a0888e5)
  • tie PostHog events to instance analytics (#5244) (3e59ace)
Bug Fixes
  • *chat:* auto-retry empty model responses, surface as structured error (#5240) (30c98ff)
  • *chat:* dedupe unavailable tool stream errors (#5170) (0609a85)
  • *chat:* drop empty assistant messages after normalization (#5219) (2359a3c)
  • *chat:* drop empty assistant turns from persist, read, and model prep (#5255) (6460b31)
  • *chat:* share and browser pane (#5228) (7fdc5d9)
  • *chat:* stop reconnect render loop; fixme duplicate-assistant e2e (#5261) (9560992)
  • *dev:* use --webpack for int-tests frontend to avoid turbopack idle CPU (#5241) (ae35c37)
  • *docker:* cache cargo/turbo/next artifacts in builder pnpm build (#5230) (541a27c)
  • *frontend:* derive chat MCP App canvases from messages; independent sidebar scroll (#5185) (aeb55a8)
  • *k8s:* pre-load deployments before single-tenant env relocation (#5236) (cb8057d)
  • *k8s:* tear down old namespace explicitly on env relocation (#5266) (e3bbda6)
  • *mcp-gateway:* promote validateExternalIdpToken catch debug->warn (#5193) (b85d913)
  • *mcp-gateway:* upstream Bearer forwarding (#5215) (d72da5e)
  • reduce Next dev cold compile overhead (#5180) (f152a4c)
  • *sandbox:* recover stale dagger sessions (#5209) (af9db49)
  • usage limits and cleanup windows (#5238) (49ce84f)
Performance Improvements
  • *backend-tests:* snapshot migrated PGlite schema instead of replaying per file (#5259) (08f6d5c)
Documentation
Code Refactoring
  • clean up dead sandbox and compaction TS (#5158) (a132de6)
  • genericize sandbox runtime wrapper (no behavior change) (#5181) (da9ba55)
  • introduce backend seam in sandbox-core (#5186) (f60c307)
  • *rbac:* collapse environment permissions to admin + deploy-to-restricted (#5243) (2e2164c)
Miscellaneous Chores

Read-only live mirror of Archestra.AI Slack

👋Join the discussion withAI enthusiasts!