You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+1-20Lines changed: 1 addition & 20 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,11 +20,7 @@
20
20
21
21
LLMs excel at writing code but struggle with tool calls. Instead of exposing hundreds of tools directly, give them ONE tool that executes TypeScript code with access to your entire toolkit.
22
22
23
-
**Research from [Apple](https://machinelearning.apple.com/research/codeact), [Cloudflare](https://blog.cloudflare.com/code-mode/) and [Anthropic](https://www.anthropic.com/engineering/code-execution-with-mcp) proves:**
24
-
-**60% faster execution** than traditional tool calling
25
-
-**68% fewer tokens** consumed
26
-
-**88% fewer API round trips**
27
-
-**98.7% reduction in context overhead** for complex workflows
23
+
[Apple](https://machinelearning.apple.com/research/codeact), [Cloudflare](https://blog.cloudflare.com/code-mode/), and [Anthropic](https://www.anthropic.com/engineering/code-execution-with-mcp) say that Code-Mode is a more efficient way to approach tool calling compared to the traditional dump function information and then extract a JSON for function calling.
0 commit comments