benchmark
01kayba-ai/agentic-context-engine
Command Claude Code
Run a TAU-bench evaluation end-to-end and present results.
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
kayba-ai/agentic-context-engine
Command Claude Code
Run a TAU-bench evaluation end-to-end and present results.
kayba-ai/agentic-context-engine
Command Claude Code
Switch to an existing branch by checking out its worktree, or creating one if needed.
kayba-ai/agentic-context-engine
Command Claude Code
Create a new git branch with an associated worktree following the project naming convention.
kayba-ai/agentic-context-engine
Command Claude Code
Create a pull request for the current branch against main.
kayba-ai/agentic-context-engine
Command Claude Code
Finalize the current work: format, test, fix, commit, and push.
kayba-ai/agentic-context-engine
Command Claude Code
List project branches with their worktree status.
kayba-ai/agentic-context-engine
Command Claude Code
Release a new version: bump version, update changelog, tag, push, and create a GitHub release.
kayba-ai/agentic-context-engine
Command Claude Code
Remove a branch and its associated worktree.
kayba-ai/agentic-context-engine
Command
The kayba CLI interacts with the Kayba hosted API (https://use.kayba.ai). Auth: set KAYBAAPIKEY env var or pass --api-key to every command.