Metadata-Version: 2.4
Name: rigma
Version: 0.3.0
Summary: Hardware-aware local LLM deployment: probe, resolve, run.
License-Expression: Apache-2.0
License-File: LICENSE
Requires-Python: >=3.11
Requires-Dist: fastapi>=0.111
Requires-Dist: httpx>=0.27
Requires-Dist: huggingface-hub>=0.23
Requires-Dist: psutil>=5.9
Requires-Dist: pydantic>=2.7
Requires-Dist: typer>=0.12
Requires-Dist: uvicorn>=0.30
Provides-Extra: dev
Requires-Dist: pytest>=8; extra == 'dev'
Requires-Dist: ruff>=0.4; extra == 'dev'
Provides-Extra: nvidia
Requires-Dist: pynvml>=11.5; extra == 'nvidia'
Description-Content-Type: text/markdown

# Rigma

Hardware-aware local LLM deployment for consumer machines: `rigma up` probes your GPU/RAM,
picks the community-verified best model + quant + flag combo for your exact hardware,
downloads a pinned llama.cpp build and the model, and serves an OpenAI-compatible endpoint —
no knob-mashing required.

Unlike generic runners, Rigma applies the tuning that actually matters per machine:
MoE expert offload (`--n-cpu-moe`) sized to your RAM, architecture-aware KV-cache policies
(e.g. `q8_0` K-cache floor on DeltaNet-family models), backend selection per GPU generation
(e.g. Vulkan over ROCm on RDNA4), flash attention, and session persistence
(`--slot-save-path`) on by default. Every decision is auditable: `rigma plan --explain`
shows the arithmetic and sources.

## Quickstart (pre-alpha)

```powershell
pip install rigma
rigma up            # probes your machine, downloads the best model, opens the chat UI
```

That's it — a browser tab opens with a chat connected to your tuned local model, and any
OpenAI-compatible tool can use `http://127.0.0.1:11500/v1`.

## Commands

| Command | What it does |
|---|---|
| `rigma up` | Start everything; opens the chat UI in your browser |
| `rigma chat` | Chat with the running model in the terminal |
| `rigma status` | What's running, where |
| `rigma stop` | Stop the model server and UI |
| `rigma models` | What fits your machine |
| `rigma plan --explain` | What `up` would run, with the math |
| `rigma doctor` | What Rigma detects on this machine |
| `rigma update` | Pull the latest [community combo registry](https://github.com/IxMxAMAR/rigma-registry) |

`rigma up` flags: `--use-case coding` · `--model SLUG` · `--port 11500` · `--no-browser` ·
`--turbo` (fast download, may hog your bandwidth) · `--yes` · `--dry-run`

## Status

Pre-alpha (M2). Combos come in two grades: **verified** (benchmarked on real hardware,
evidence attached) and **provisional** (research-seeded fit math — run one and PR your
numbers to [rigma-registry](https://github.com/IxMxAMAR/rigma-registry)). Verified so far:

| Hardware | Model | Backend | Result |
|---|---|---|---|
| RX 9070 XT 16GB + 16GB RAM (Windows) | Qwen3.6-35B-A3B UD-Q3_K_XL, ctx 32K, n_cpu_moe 10 | Vulkan (llama.cpp b9867) | **verified 2026-07-06**: 57.1 t/s gen, 689 t/s prefill @ 4K prompt |

Design: `docs/superpowers/specs/2026-07-03-rigma-design.md`. License: Apache-2.0.
RAG integration (via [Raggity](https://github.com/IxMxAMAR/raggity), AGPL-3.0, separate process) lands in M4.
