Quickstart¶
Start a chat — it auto-detects a running Ollama (:11434) or vLLM
(:8000/:8001) and uses the model the server serves (on Ollama a 7B, pulled on
first run); the server needs a 32k context, see Installation:
>>> load the Marmousi benchmark model and run a forward — show the shot gather
>>> here is vp_init.npy — run a 2-D acoustic forward and show me the shot gather
>>> make an elastic model (vp/vs/rho) and run an Elastic forward
>>> :reset # clear conversation history
Other entry points:
sweep-agent ui # same agent in a browser (needs sweepx[agent-ui] + a running LLM) → :7860
sweep-agent tools # list the ~30 tools — no LLM/GPU needed; --json emits tool specs
Every tool is also a plain function (.fn, with a pydantic params model) — handy
for scripts and tests, no LLM required: