AMD-AGI / GEAK
Generating Efficient AI-Centric Kernels
Why this job: works in the areas we cover, but does not say which job it does
What it does
GEAK targets AMD Instinct MI GPUs (CDNA, e.g. gfx942 / gfx950; the on-box card is auto-detected), and also runs on RDNA3.5 client parts (gfx1151 / Radeon 8060S) and the validated RDNA4 product Radeon AI PRO R9700 (gfx1201). gfx1201 is an ISA shared by other products; it does not by itself select R9700 images, calibrated peaks, or serving policy. It is driven by Claude Code and orchestrated by deterministic JS Workflows. It ships two workflows, each for a different scenario:
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit today
- Stars
- 204
- +6 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v4.2.0
- Released 24 days ago
- Built with
- Python
- 76% of the code
Is it looked after?
- Contributors
- 10
- Last 90 days
- Issues
- 79% closed
- 34 still open
- Pull requests
- 274 merged
- 58 waiting
- Releases
- 10
- 10 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| hyperai / triton-cn | 129 | 11 months ago | MIT | No downloads |
| tensorpool / tensorpool | 438 | 7 months ago | MIT | No downloads |
| BobMcDear / attorch | 607 | 3 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 76%
- JavaScript 17%
- Shell 7%
- C++ <1%
Topics
- gpu
- hip
- kernel-optimization
- triton
- brain
- llm
- python
Project record
- JobOther AI tools
- StatusListed
- Commits1,003
- Forks71
- Watching4
- Stars in 28 days+19
- CreatedJul 30, 2025
- First seen by usNov 7, 2026
- CheckedNov 12, 2026