This has been insanely fun to work on for the past couple weeks!
This rewrite tested the limits of all our products: thousands of subagents via Prime Agent, billions of tokens via Prime Inference, and hundreds of sandboxes via Prime Sandboxes!
It's incredibly rewarding to see our full stack come together, and Prime Agent is now faster than ever :)
prime agent v0.9.6 is out:
◆ Support for GPT-6 Sol, Opus 5.5, and Grok 4.7
◆ /mcp plugin catalog with one-click connections to Linear, Notion, Posthog, Stripe, and 60+ more services
◆ Huge perf and reliability pass 🫡
Lots more coming soon :)
We’re hiring a full-time engineer to help build Prime Agent :)
Own features end to end across agent harnesses, cloud agents, and self-improving loops -- integrated with our sandboxes, evals, and hosted training stack.
Full-time, in person in SF:
Working on this with the team has been an absolute pleasure!
Prime Agent combines RLM-native tool calling, programmable context, and multi-agent orchestration to create a general-purpose coding harness that can improve itself. It also happens to score 95.5% on ARC-AGI-3.