Aevonix / FlashAlign
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
Why this job: topics: llama-cpp, vllm, inference
What it does
Apply alignment profiles per request. Use abliteration for approved users and channels, or keep a profile active across every routed request.
Get started
git clone https://github.com/Aevonix/FlashAlign.git
cd FlashAlign
bash ./install.sh --auto - Maintenance
- Active
- Last commit 3 days ago
- Stars
- 125
- +6 this week
- Licence
- AGPL-3.0
- Share-alike, even hosted
- Downloads for
- Linux
- From the latest release
- Latest version
- v1.2.0
- Released 3 days ago
- Built with
- Python
- 98% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 7 merged
- 0 waiting
- Releases
- 4
- 4 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 |
|---|---|---|---|---|
| heterodoxin / AbliteratedOutTheBox | 170 | 18 days ago | MIT | No downloads |
| xorbitsai / inference | 9,647 | yesterday | Apache-2.0 | No downloads |
| kvcache-ai / Mooncake | 7,006 | today | Apache-2.0 | Linux |
More: download files, languages, topics and project record
Languages
- Python 98%
- JavaScript 2%
- Shell <1%
Topics
- abliteration
- hermes
- inference
- llama-cpp
- llm
- model-alignment
- openclaw
- sglang
- tensorfold
- vllm
Project record
- JobLocal LLMs
- StatusNew to our list
- Commits8
- Forks15
- Watching0
- CreatedOct 31, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026