| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| atomic-agent-win32-x64.zip.sha256 | 2026-08-05 | 93 Bytes | |
| atomic-agent-win32-x64.zip | 2026-08-05 | 43.7 MB | |
| atomic-agent-linux-x64.tar.gz.sha256 | 2026-08-05 | 96 Bytes | |
| atomic-agent-linux-x64.tar.gz | 2026-08-05 | 51.0 MB | |
| atomic-agent-linux-arm64.tar.gz.sha256 | 2026-08-05 | 98 Bytes | |
| atomic-agent-linux-arm64.tar.gz | 2026-08-05 | 50.8 MB | |
| atomic-agent-darwin-arm64.tar.gz.sha256 | 2026-08-05 | 99 Bytes | |
| atomic-agent-darwin-arm64.tar.gz | 2026-08-05 | 49.8 MB | |
| README.md | 2026-08-05 | 1.1 kB | |
| v0.1.71 source code.tar.gz | 2026-08-05 | 5.7 MB | |
| v0.1.71 source code.zip | 2026-08-05 | 6.6 MB | |
| Totals: 11 Items | 207.6 MB | 0 | |
Fixed
- NVIDIA driver 610+ silently landed the managed backend on the wrong GPU. Driver 610 renamed the
nvidia-smiheader fields, the CUDA version parser stopped matching, and the backend selector fell back to the Vulkan build, which re-admits integrated GPUs into auto-selection. The parser now accepts both header generations (#55 by @sachin-detrax, fixes [#54]).
If your Windows install already picked the wrong backend: this fix cannot repair an existing wrong download (every backend zip ships the same llama-server.exe, so the installer sees it as already present). Delete the backend directory and run atomic-agent models update to force a clean re-download.
Updating
macOS / Linux
curl -fsSL https://atomicagent.io/install | sh
Windows (PowerShell)
irm https://atomicagent.io/install.ps1 | iex
Existing installs update in place; the TUI prompts for a restart afterwards.
Thanks @sachin-detrax for the report, the diagnosis and the fix.
Full Changelog: https://github.com/AtomicBot-ai/atomic-agent/compare/v0.1.69...v0.1.71