vrr/openclaw
2
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-10-03 01:29:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 29
openclaw/extensions/huggingface
History
Peter Steinberger b9c5d19649
refactor(providers): deslop small provider plugins (#158437) 
* refactor(providers): deslop small provider plugins

* test(providers): align cleanup fixtures and assertion allowances

* test(exa): reuse guarded request body in wire fixture
2026-09-26 00:32:31 -07:00
..
assets improve(plugins): give bundled logos consistent white icon tiles (#155259) 2026-09-23 19:09:26 -07:00
api.ts
index.test.ts fix(huggingface): keep bundled models available without live discovery (#127118) 2026-09-05 00:20:28 +05:30
index.ts refactor(providers): deslop small provider plugins (#158437) 2026-09-26 00:32:31 -07:00
models.proxy.test.ts
models.test.ts refactor(huggingface): remove redundant retired-model check (#148698) 2026-09-15 10:37:17 +08:00
models.ts refactor(providers): deslop small provider plugins (#158437) 2026-09-26 00:32:31 -07:00
onboard.ts feat(providers): keep registered setup connection-only (#142202) 2026-09-08 20:22:25 +05:30
openclaw.plugin.json feat: group bundled plugin settings by authored manifest metadata (#149331) 2026-09-16 22:03:41 -07:00
package.json chore(release): close out 2026.9.6 on main (#156869) 2026-09-23 23:02:54 -07:00
provider-catalog.ts fix(models): report failed bundled catalog refreshes (#139649) 2026-09-06 10:03:57 +05:30
README.md feat: show declared plugin capabilities and setup guides (#157956) 2026-09-25 16:43:53 -07:00
tsconfig.json

README.md

Hugging Face

Use hosted models through Hugging Face Inference Providers. OpenClaw connects to Hugging Face's router and discovers available models; it does not download or run the model weights locally.

Get started

Create a Hugging Face token with permission to call Inference Providers, then run:

openclaw onboard --auth-choice huggingface-api-key

The Gateway also accepts HUGGINGFACE_HUB_TOKEN or HF_TOKEN. Browse the catalog with openclaw models list --provider huggingface, then choose a model your account can access.

Model availability and supported inputs depend on the selected inference provider. See the Hugging Face guide for token setup, routing, and model configuration.