AMD-AGI/AgentKernelArena
View on GitHubAgentKernelArena provides an end-to-end siloed-benchmarking environment where different LLM-powered agents—such as Cursor Agent, Claude Code, Codex, SWE-agent, and GEAK—can be evaluated side-by-side on the same GPU kernel tasks, using objective and reproducible metrics.
- Stars
- 118
- Forks
- 14
- Open beginner issues
- 0
- Indexed issues
- 8
- Avg merge
- 3d 5h
- Merged PRs (30d)
- 8
- Dominant language
- Python
- License
- Apache-2.0
- Last GitHub push
- Sep 15, 2026
- Latest indexed
- Sep 20, 2026
- Contributing guide
- Contributing guide
- Code of conduct
- No code of conduct
- Beginner labels
- No beginner labels indexed
-
Difficulty 4/5 3-5 days Newbie friendliness 48/100
AMD-AGI/AgentKernelArena#108 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 42/100
AMD-AGI/AgentKernelArena#91 ·
-
Difficulty 5/5 Over a week Newbie friendliness 35/100
AMD-AGI/AgentKernelArena#88 · 1 reaction ·
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
AMD-AGI/AgentKernelArena#41 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 45/100
AMD-AGI/AgentKernelArena#30 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
AMD-AGI/AgentKernelArena#10 ·
-
AMD-AGI/AgentKernelArena#9 · 1 assignee ·
-
Difficulty 5/5 Over a week Newbie friendliness 25/100