T-Crypt / berth
Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how that access is handed off.
Why this job: topics: llama-cpp, ollama, vllm, inference, local-ai
What it does
Berth makes the programs on your PC take turns with the GPU's memory, so they stop crashing each other, and tells you who is holding it.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 291
- +5 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- 2 systems
- Windows, Linux
- Latest version
- v0.5.0
- Released 2 days ago
- Built with
- Go
- 85% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 74% closed
- 11 still open
- Pull requests
- 256 merged
- 2 waiting
- Releases
- 22
- 22 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| varunvasudeva1 / llm-server-docs | 849 | 4 months ago | MIT | No downloads |
| SemiAnalysisAI / InferenceX | 2,016 | today | Apache-2.0 | No downloads |
| thushan / olla | 337 | 9 days ago | Apache-2.0 | Mac, Windows, Linux |
More: download files, languages, topics and project record
Download files, v0.5.0
- Windows1 file, 5 downloads
- Linux2 files, 5 downloads
Languages
- Go 85%
- JavaScript 7%
- Python 3%
- CSS 3%
Topics
- comfyui
- golang
- gpu
- inference
- llama-cpp
- llama-swap
- llm
- local-ai
- nvidia
- ollama
- self-hosted
- vllm
Project record
- JobLocal LLMs
- StatusListed
- Commits860
- Forks30
- Watching2
- Stars in 28 days+290
- CreatedOct 11, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026