nex-code 0.4.22 → 0.4.24

package/README.md

@@ -38,7 +38,9 @@
 
 ## Demo
 
-https://github.com/user-attachments/assets/6a70525c-a1a4-4c6f-9784-176cb1becc15
+
+
+https://github.com/user-attachments/assets/68a6c134-2d13-4d66-bc5e-befea3acb794
 
 ---
 
@@ -907,18 +909,20 @@ This enables non-linear conversations: try an approach, and if it doesn't work,
 
 ### Autoresearch
 
-Autonomous optimization loops inspired by Karpathy's autoresearch pattern. The agent edits code, runs experiments, logs results, and automatically keeps improvements or reverts failures:
+Autonomous optimization loops inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch). The agent creates a dedicated experiment branch, edits code, runs experiments, and automatically keeps improvements or reverts failures:
 
 ```
 /autoresearch reduce test runtime while maintaining correctness
 /autoresearch optimize bundle size under 500kb
 ```
 
-The agent follows a repeating cycle: **checkpoint** (git) -> **edit** -> **run experiment** -> **log result** -> **keep or revert**. All experiments are logged to `.nex/autoresearch/experiments.json` with metrics and trend tracking.
+The agent follows a repeating cycle on a dedicated `autoresearch/<tag>` branch: **setup branch** -> **checkpoint** -> **edit** -> **run experiment** -> **log result** -> **keep or revert (git reset)**. Runs indefinitely until you interrupt. Experiments are logged to `.nex/autoresearch/experiments.json` with metrics, resource usage, and complexity tracking. Output can be redirected to log files with metric extraction via grep patterns to protect context.
 
 ```
-/ar-status    # show experiment history with trends
-/ar-clear     # reset experiment history
+/ar-self-improve          # self-improvement loop using nex-code's benchmark as metric
+/ar-self-improve sysadmin # focus on a specific weak category
+/ar-status                # show experiment history with trends
+/ar-clear                 # reset experiment history
 ```
 
 ### Memory