Side-by-side comparison · apps and saas, skills
AutoGen vs self-customize
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Apps and SaaS
AutoGen
A programming framework for agentic AI
Skills
self-customize
A lightweight alternative to OpenClaw that runs in containers for security.
Checked facts
Line by line
| Measure | AutoGen | self-customize |
|---|---|---|
| Latest version | python-v0.7.5 (for 30 Sept 2025) | Not checked yet |
| Security check (static checks) | Not checked yet | 100 out of 100 |
| Days since the last commit | 9 | 0 |
| GitHub forks | 9,380 | 12,669 |
| GitHub stars | 61,737 | 31,090 |
| Days to a first reply on issues | 24.7 | 18.3 |
| Open issues | 566 | 294 |
| Releases in the last 90 days | 0 | 8 |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.