Devika Verma 514c0beb37 llama.cpp and vLLM as providers ...

Each is a provider of its own with an address and an optional key; the served model, its window and tool support are read from the server (vLLM is probed for tool calling).
Providers carry a kind (local, subscription, api_key) for the settings page; docs/local-servers.md.

2026-10-05 19:49:34 -07:00

..

assets

README: add how-it-works diagram from the website

2026-07-23 09:29:00 -07:00

approval-guidance.md

Document approval context and refine Advanced disclosure

2026-09-20 19:36:09 -07:00

config.example.toml

Sandbox settings v6: allowed-sites tick list, three-row OpenShell setup

2026-09-28 16:45:49 -07:00

headless.md

run: retry a failed model call after 2 s, then back off

2026-10-05 11:20:53 -07:00

local-servers.md

llama.cpp and vLLM as providers

2026-10-05 19:49:34 -07:00

macos-sandbox.md

Access section: the session's allowed sites, with a list of its own

2026-10-03 15:45:53 -07:00

model-settings.md

Per-model settings and a recommended-settings table

2026-10-05 19:49:34 -07:00

openshell-inside.md

Publish the CLI image to GitHub's container registry

2026-10-05 10:10:05 -07:00

openshell.md

OpenShell doc: Docker Desktop's host networking on a Mac

2026-10-04 18:22:02 -07:00

remote-machines.md

The openworker program for the Mac

2026-10-05 15:28:03 -07:00

team-board-evidence.md

Make team coordination event driven and quiet

2026-09-21 06:02:41 -07:00

windows-sandbox.md

Access section: the session's allowed sites, with a list of its own

2026-10-03 15:45:53 -07:00