I built something I wanted for some time, big fan of claude code but I don't use Anthropic's models anymore.
Also all the other gateways are super-buggy/bloated.
I built something I wanted for some time, big fan of claude code but I don't use Anthropic's models anymore.
Also all the other gateways are super-buggy/bloated.
Adversaries hack trusted members of your team weeks/months before orchestrating attacks. One trusted maintainer account can turn your entire software supply chain into an attack surface overnight.
That's why we built Security ToDo's. We audit your codebases security posture as
Seen an acceleration in hacker activity on Github the last 2 weeks. A new form of attack where hackers pwn popular contributors and use their accounts to plant backdoors into code.
We use an origin based credit score system to identify these hackers and automatically flag/block
Seen an acceleration in hacker activity on Github the last 2 weeks. A new form of attack where hackers pwn popular contributors and use their accounts to plant backdoors into code.
We use an origin based credit score system to identify these hackers and automatically flag/block
One thing I hear consistently: Superagent PR scans finds vulnerabilities no other scanners surface.
We call it "daily freshness", feeding the harness with thousands of new attack surfaces every week to keep it up to date with the state-of-the-art.
He misses the main point of open weights models, which is Dario can cut your access...
Some people (including me) would gladly give up 5 units on Terminal Bench 2 in order to not get banned from Anthropic, a government or some other third party.
"open source is kind of a distraction you still can’t really see what’s happening inside the model, so it’s not truly "free."
After watching the clip, I’m even more convinced of open source than I was before.
3 days ago @superagent_ai was installed on 500 code bases. Yesterday we crossed 1000. Some of the biggest repos in the supply chain.
Love getting feedback from these folks who are truly domain experts in their respective fields.
If you want more flexibility in your open-source project you need to add CLAs.
The past couple of months many large repos have gone closed source due to valid security concerns (even though I personally think its worse for security).
@superagent_ai offers this for free.
Excited to release Security Todos in Superagent ✅
Contributors get phished. Maintainers get pwned. Tokens leak.
Security Todos help teams find and fix those weak points before an attacker uses them.