Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.
- amd
- gfx1151
- gpu-inference
- hip
102,118 visible repositories in the index
1–4 of 4 · Most stars
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.
Autonomous software factory. Give it a GitHub issue, a spec or a one-line task; get back a pull request with a signed receipt anyone can re-check offline. Runs on your machine with your own keys: Claude, Codex, OpenCode.
Run Claude Code natively on Android via Termux or AVF (Android Virtualization Framework) -- no desktop, no SSH, no root required.
🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / Gemini. Eval-gated 100/100, you always merge.