atomic-chat: add provider with initial blessed models#1476
Open
Vect0rM wants to merge 1 commit intoanomalyco:devfrom
Open
atomic-chat: add provider with initial blessed models#1476Vect0rM wants to merge 1 commit intoanomalyco:devfrom
Vect0rM wants to merge 1 commit intoanomalyco:devfrom
Conversation
Adds Atomic Chat as a local OpenAI-compatible provider at http://127.0.0.1:1337/v1. Includes logo and three curated models: - unsloth/Qwen3.5-9B-IQ4_XS (id: Qwen3_5-9B-IQ4_XS) - unsloth/gemma-4-E4B-it-IQ4_XS (id: gemma-4-E4B-it-IQ4_XS) - unsloth/MiniMax-M2.5-UD-TQ1_0 (id: MiniMax-M2_5-UD-TQ1_0) Model ids match the normalized form returned by Atomic Chat's /v1/models endpoint (dots replaced with underscores). Made-with: Cursor
6 tasks
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds Atomic Chat as a new OpenAI-compatible local provider serving at
http://127.0.0.1:1337/v1.After merge, any opencode user will see
Atomic Chatin/connectand the registered models in/modelswith zero extra configuration.Provider manifest
name:Atomic Chatnpm:@ai-sdk/openai-compatibleapi:http://127.0.0.1:1337/v1(port1337is a hard public contract — Atomic Chat's local API server binds it by default)env:["ATOMIC_CHAT_API_KEY"](declared for schema compliance — server ignores it for local auth, mirroring LMStudio's approach)doc:https://atomic.chatIncluded models
Model IDs match the normalized form returned by Atomic Chat's
GET /v1/modelsendpoint (dots in HF repo IDs are replaced with underscores, author prefix is stripped):Qwen3_5-9B-IQ4_XS.tomlQwen3_5-9B-IQ4_XSunsloth/Qwen3.5-9B-IQ4_XSgemma-4-E4B-it-IQ4_XS.tomlgemma-4-E4B-it-IQ4_XSunsloth/gemma-4-E4B-it-IQ4_XSMiniMax-M2_5-UD-TQ1_0.tomlMiniMax-M2_5-UD-TQ1_0unsloth/MiniMax-M2.5-UD-TQ1_0All three are local GGUF quantizations served via llama.cpp — cost is
$0.Qwen3.5 9B ID was empirically verified against a running Atomic Chat server:
Test plan
bun validatepassesGET /v1/modelsof a running Atomic Chat instancelogo.svg(PNG source embedded via base64)env.min(1),doc.min(1),@ai-sdk/openai-compatible+apipairing)