mngr has 12+ plugins that help developers
👉 pull files from stopped agents
👉 schedule nightly code reviews
👉 sync changes with a remote agent
👉 track everything from a CLI Kanban board
We broke down every plugin, what it does, and when you'd actually reach for it.
🔗 https://t.co/B1Fs02YkBE
Blueprint has become a daily tool. Why ever write a detailed, big agent prompt yourself?
I spend ~3 minutes upfront planning with Blueprint and I've yet to see an agent miss the mark I originally intended.
Great work @nayana_b_ and @nikos_plugachev!
Most agents rush to code or blindly guess on a plan. Blueprint does the opposite.
It reads your code, asks grounded questions that matter, and hands any agent a plan worth executing.
Claude is great at figuring things out. IFTTT MCP lets it act on them.
Connect @claudeai to 1000+ services and turn conversations into action: emails sent, workflows triggered, Applets created.
Here's how: https://t.co/DaPn1Zf9tm
We've been building connections between apps for over a decade. Now we're bringing that to AI. 🚀
Introducing IFTTT MCP. Your AI assistant will never be the same.
Learn more about it here: https://t.co/U8tFys1y1z
You should control your Twitter feed, not the other way around. That's why we built Bouncer.
For humans to live freely, open software must prevail over closed ecosystems and walled gardens. That’s why we’re working on new tools that are built for you, not against you.
Twitter’s algorithm is optimized for addiction, not for us. We deserve better.
We’re releasing Bouncer today so you can take back control of your feed. Describe what you don't want, and Bouncer removes it.
It’s free, doesn’t collect your data, and will be open source soon.
mngr: programmatically manage 100s of claude code sessions in parallel 🤖
open source today.
lets you do things like:
— for each open GitHub issue, create a PR
— for each flaky test in the past week, fix it
— for each rule in style guide, scan codebase & fix all instances
runs any agent: @claudeai, codex, @opencode, etc.
runs on any compute: locally, @modal, @Docker, or anything you can ssh into.
Saros takes Returnal's looper shooter action and twists it into a whole new cosmic horror bullet-fest that aims to eclipse its predecessor.
From playing three hours myself, I think it's doing just that.
Our preview: https://t.co/smGKHvbG86
We open sourced a tool for local agents to use any service you have authentication to — Notion, Slack, AWS, etc. — without needing to bother you about auth.
I use it for pulling messages from Slack to see what I need to respond to, pulling data from websites I'm logged into, etc.
With Offload, @imbue_ai saw a 6x drop in execution times by giving agents the ability to parallelize tasks.
Now open source, and backed by Modal Sandboxes 👇
Your parallel agents needed scalable test coverage yesterday
Introducing Offload: a Rust CLI that spreads your test suite across 200+ @Modal sandboxes, freeing your CPU to keep your agents shipping.
On our Playwright suite, it took a 12 min run to 2, at $0.08 a run