canivel / dynolab
Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.
Why this job: says: local inference; topics: apple-silicon, mlx
What it does
Start with a model on your Mac: MLX, or GGUF with llama.cpp. For larger GGUF models, an experimental local GPU pool can connect your Mac and a Windows NVIDIA worker. You do not need a pool to start learning.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 5 days ago
- Stars
- 153
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- Mac
- From the latest release
- Latest version
- v0.6.18
- Released 5 days ago
- Built with
- Python
- 50% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 0% closed
- 12 still open
- Pull requests
- 84 merged
- 7 waiting
- Releases
- 24
- 24 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 |
|---|---|---|---|---|
| jundot / omlx | 23,491 | 5 days ago | Apache-2.0 | Mac |
| Neywa-Labs / nativ | 1,582 | yesterday | MIT | Mac |
| vllm-project / vllm-metal | 1,979 | yesterday | Apache-2.0 | Mac |
More: download files, languages, topics and project record
Languages
- Python 50%
- Swift 49%
- PowerShell 1%
- Shell <1%
Topics
- ai
- ai-interpretability
- ai-safety
- aisafety
- mechanistic-interpretability
- probes
- sae
- alignment
- apple-silicon
- llm
- mcp
- mlx
Project record
- JobLocal LLMs
- StatusListed
- Commits115
- Forks152
- Watching1
- Stars in 28 days0
- CreatedSep 4, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026