Srinivas Karre retweeted
I don’t recommend this approach.
Many of the elite engineers I’ve ever met put everything into their daily work cuz they on purpose chose a role/company/challenge they are truly passionate about & put a lot of extra effort into the company
This is a lazy way to judge autonomy.
Your agent needs connections and scoped permissions to act on your behalf. Scalekit is building that layer, starting with 600+ connectors and 30,000+ tools.
try it out for free scalekit.com
We're live on @ProductHunt with AgentKit - an MCP gateway for agents that act on behalf of your users! 🚀
Connecting an agent to an app is easy. Getting it to pick the right tool, act with the right permissions, and handle everything underneath? Not so much.
Nobody starts building agents because they're excited about managing OAuth, token refresh, or audit logs. That's what we been building at @scalekitinc
AgentKit handles the auth and integrations behind agent actions, across 600+ connectors and 30,000+ tools. User-delegated authentication, scoped tools, custom connectors for your own APIs, event-driven triggers, and per-action audit logs.
Already in production with 100+ customers. Would love your feedback: producthunt.com/products/sca…
1
23
This is for normies.
Legends need to direct us how to move to higher levels of abstraction working with claude and teaching on how to use the powerful models >= opus/fable/sonnet 5.5
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5:
hackertube.org/
- Excellent recs without any logins (state is kept in local browser session)
- Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads
- Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version
- HackerTube Longs ✊
A bit more on the process:
I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing.
Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.
44
Your agent needs connections and scoped permissions to act on your behalf. Scalekit is building that layer, starting with 500+ connectors and 20,000+ tools.
try it out for free scalekit.com/
Connecting an agent to an app is just the beginning. Here's what we've been building for the last six months 📷
AgentKit by @scalekitinc is the MCP gateway for agents that act on behalf of your customers, connecting 600+ apps and 30,000+ tools. It brings together:
→ User-delegated auth
→ Virtual MCP servers
→ Custom connectors for internal APIs
→ Event-driven triggers
→ Per-action audit logs
The infrastructure agents need to work across real applications, for real users.
We've spent six months going deeper on the infrastructure developers need after their first agent demo.
Now we'd love to see what you build with it.
Free tier: 10,000 tool calls/month. Try for free: scalekit.com
1
30
Srinivas Karre retweeted
this was @scalekitinc's 5th hackathon for the year, and i think we're getting better at figuring out how much people can actually build in less than 4 hours!
a little late, but here's a recap from our SF @Techweek_ hackathon with @cognee_ and @RespanAI!
the challenge: build a company brain that could pull context from different tools, remember things, and actually take action with the right access.
we had 8 solid submissions by the end of the evening, and some really fun demos. thanks to everyone who showed up and built with us. and to @tricalt and @HendrixLiu29208 for putting this together with us!
Srinivas Karre retweeted
Every conversation lately is about which agent to build next.
Over coffee with Adam Frankl, the OG dev marketer, we went back to first principles instead: how buyers make decisions. Agents haven’t changed that.
A few things that stuck 🧵
Srinivas Karre retweeted
SFTW 2/4 - Build a company brain with @scalekitinc @cognee_ @RespanAI 🧠
Live from primitive.space
@Techweek_ @filgran_ - me again :)
The most important skill a dev should develop in 2026 is structured thinking (input, output, and control & data flow)
22
Srinivas Karre retweeted
🚀 I'm excited to share that we've launched the 𝗔𝘂𝘁𝗵 𝗦𝘁𝗮𝗰𝗸 𝗳𝗼𝗿 𝗔𝗜 𝗔𝗽𝗽𝘀 and are announcing $𝟱.𝟱𝗠 in seed, led by @z47_vc and @scaletogether.
We are cooking Authentication for AI apps at Scalekit
Signup at: scalekit.com
check it out: lnkd.in/g7gfpNFQ
#auth #ai
1
23
Srinivas Karre retweeted
Live Now : Drop in Authentication for MCP Servers.
youtube.com/live/e6X-JWIMY-s
Srinivas Karre retweeted
We mapped out the emerging infrastructure layer that’s powering AI-agent interfaces.
Think of it like the early API economy — but rebuilt for tool calls, not REST.
MCP Server as Resource Server, This provides the flixibility for the MCP servers to offload auth to Authorization server with scopes, permissions and groups.
As per the new MCP spec (June 18, 2025), your remote MCP server no longer needs to act as an OAuth Authorization Server.
It’s just a Resource Server now — nothing more.
1
50
Srinivas Karre retweeted
Scalekit is already compliant with new MCP spec . @scalekitinc can be added as an authentication server for any MCP server you are building right now.


















