docs(inference): add Atomic Chat as OpenAI-compatible LLM provider#1809
Closed
yanalialiuk wants to merge 1 commit into
Closed
docs(inference): add Atomic Chat as OpenAI-compatible LLM provider#1809yanalialiuk wants to merge 1 commit into
yanalialiuk wants to merge 1 commit into
Conversation
Add workspace and Cloud custom-provider examples for Atomic Chat (local /v1 API). Merge local-providers.json into the inference model catalog alongside base.json, without MCP or app-specific integration code. Co-authored-by: Cursor <cursoragent@cursor.com>
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
|
@yanalialiuk is attempting to deploy a commit to the Different AI Team on Vercel. A member of the Team first needs to authorize it. |
Collaborator
|
Sorry, we dont accept PRs for custom providers/models - please make your PR to upstream models.dev repo |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Documents Atomic Chat as a local OpenAI-compatible LLM provider for OpenWork (workspace
opencode.jsonand Cloud custom provider JSON). Adds an inference catalog overlay entry for self-hostedGET /models/api.json.This PR does not add MCP servers, MCP clients, or desktop/den-app integration code.
Reference: AtomicBot-ai/Atomic-Chat
What changed
add-a-custom-llm.mdx; Cloud custom-provider example incustom-llm-provider.mdxlocal-providers.jsonwithatomic-chat(defaulthttp://127.0.0.1:1337/v1), merged inbuild-models.mjsHow to test
Desktop (workspace)
http://127.0.0.1:1337.curl http://127.0.0.1:1337/v1/modelsand note a modelid.provider.atomic-chatblock from the docs; setyour-model-idandATOMIC_CHAT_API_KEYif needed.Cloud
Inference catalog (optional)
pnpm --dir ee/apps/inference models:build node -e "console.log(require('./models-site/models/api.json')['atomic-chat']?.api)"Notes
-Model id must match GET /v1/models on your server (placeholder in examples).
-Cloud Catalog tab still uses live models.dev; use Custom provider or workspace config for Atomic Chat until upstream models.dev lists it.