10 GitHub repositories from the companies building these models.
DeepSeek, Anthropic, OpenAI, Google, Cursor, xAI. 1. DeepSeek Harness (123k⭐) - Agent runtime where everything is a plug-in: model adapters, tools, memory, all interchangeable. MIT License, went from 0 to 123k stars in just a few days. 2. Claude Skills (170k⭐)
DeepSeek published the models, the harness and the 88-page paper under it
Then kept every researcher off camera This one talked for 59 minutes, and he explains why your agent gets dumber the longer you run it 19:04 - agents already past the self-improvement line 20:11 - why an
How is this even allowed
I dropped my $200/mo claude plan for deepseek harness, it’s basically free the whole thing runs on one simple rule: everything is a plugin [setup takes 3 minutes, here’s the playbook] 1. clone/install the repo called deepseek-harness 2. skim the
Grok Bot is fixed to Grok.
Great model, I love it. But you're betting your automation stack on one company. Hermes Agent runs on 20+ providers. This morning I switched my entire setup to DeepSeek V4 Flash 0731 - better for agent workflows, and 35% cheaper than the version I was
You have reached the end of the archive
All of deepseek