Archestra Apps HackathonJoin now

#general

Jul 4July 6, 2026Jul 7Latest
A
Hi team , I was confused about this , while reading the limits implementation, I noticed the frontend computes 75%/90% usage warnings but the backend only enforces the hard limit
was this intentionally kept as a UI-only signal, or was there ever discussion about exposing it as a backend event or alert?
5 replies
RM
Rohan Mishra2:29 PMOpen in Slack
what about the open bounties
M
mohd.fadel10:31 PMOpen in Slack
Hey, Mohamad here, Exploring this space for 17 years now. Hey @user
R
Hi , Reda ...
MK
Matvey Kukuy (archestra team)4:48 PMOpen in Slack
Release 1.3 will be out in a few minutes 🎉
M(
Margaret (archestra team)5:45 PMOpen in Slack
🚀 Hey Community, we’ve just shipped a major release: Archestra 1.3.0, which we’re calling Lyra.
The full release is available now, and over the next few days we’ll highlight one of its new features each day.
We’re starting with Skills and Sandboxes.
Agents can now load SKILL.md-based Skills and run their code in secure Sandboxes governed by the environment and access policies you choose.
Give it a try - we’d love to hear what you build with them!
AM
Alexander Mosharov12:55 PMOpen in Slack
hey Team!👋
I'm planning to submit a PR with this commit (github.com/archestra-ai/archestra/commit/4b153a675484…) to support tools that run longer than the standard 60-second timeout. I aimed for a minimal implementation.
However, judging by the issues in modelcontextprotocol/typescript-sdk, using resetTimeoutOnProgress=true with an onprogress callback seems like a cleaner way to handle this.
Would you recommend sticking with my minimal hotfix for now, or should we implement proper configuration parameters for the MCP client from the start?
3 replies
M(
Margaret (archestra team)4:22 PMOpen in Slack
Happy Tuesday!
Today’s Lyra feature: one-step connection for your coding agents :archestra-love:
Engineers working in Claude Code want to stay in Claude Code. Platform teams still need model calls and tool access to run through the right controls.
Now you can connect your favourite coding agents to Archestra’s LLM Proxy and MCP Gateway with one command. The same flow also works with Codex, GitHub Copilot CLI, and Cursor.
:stopwatch: We timed it: setup takes just 45 seconds.
Pull the latest release and check it out.
🚀1:archestra-banana-dance:1:archestra-sign:1:archestra-party-blob:1:archestra-rave:1
BJ
Benjamin Janis9:21 PMOpen in Slack
👋 Hey everyone, great to meet you all!
I’m Benjamin, a Senior Software Developer exploring new opportunities.
I recently came across Archestra’s job postings, which led me here. I’m really interested in AI‑powered development tools, and I use assistants like Claude heavily in my workflow. Archestra.AI immediately caught my attention, so I joined to learn more, try things out, and connect with others building in this space.
Excited to be here and looking forward to meeting everyone!
❤️3

Read-only live mirror of Archestra.AI Slack

👋Join the discussion withAI enthusiasts!