Update README.md

README.md

@@ -27,7 +27,6 @@ Sensitive prompts and outputs remain isolated inside hardware-attested environme
 
 It separates reasoning from action, keeps credentials outside the model context, isolates tools, scopes permissions, and records an auditable history of agent activity. The goal is to let agents safely work across applications, services, and financial systems on behalf of users and organizations.
 
-[Explore IronClaw](https://github.com/nearai/ironclaw)
 
 ## User-owned data with Trace Commons
 
@@ -35,7 +34,6 @@ It separates reasoning from action, keeps credentials outside the model context,
 
 Instead of disappearing into proprietary platforms, these traces can remain private, be selectively shared, improve future models, or create value for the people and organizations that produced them.
 
-[Explore Trace Commons](https://github.com/zmanian/tracedao-server)
 
 ## The full stack
 
@@ -55,13 +53,9 @@ A framework for proving that decentralized systems and agents produced a specifi
 
 A technical vision for training and running AI across distributed infrastructure while preserving confidentiality and verifiability.
 
-## Benchmarks
+## Benchmarks (https://nearai.github.io/benchmarks/)
 
-NEAR AI publishes reproducible evaluations of models and agents across practical tasks including coding, tool use, document workflows, and multi-step execution.
-
-### [Explore NEAR AI Benchmark Results](https://nearai.github.io/benchmarks/)
-
-Compare model and agent performance across public benchmarks, inspect individual runs, and see how different implementations perform on real-world tasks.
+NEAR AI publishes reproducible evaluations of models and agents across practical tasks including coding, tool use, document workflows, and multi-step execution. Compare model and agent performance across public benchmarks, inspect individual runs, and see how different implementations perform on real-world tasks.
 
 ### [Explore NEAR AI on GitHub](https://github.com/nearai)