This branch is 2 commits behind evanp/inference-coop-copilot:main

Inference Coop for Copilot Chat

Inference Coop

Official model provider for inference.coop, usable in GitHub Copilot Chat. An official project of the Inference Cooperative, maintained in the Inference Cooperative's Git at code/inference-coop-copilot.

About the Inference Cooperative

The Inference Cooperative is a member-owned cooperative that pools its members' purchasing power to support privacy-preserving, renewable-energy, and open-weights AI services. Members choose among powerful, open-weights models — hosted in encrypted enclaves, on 100% renewable power, or built as public goods — instead of accepting whatever Big Tech offers.

Membership is a sliding scale starting at $5 a month. Every member gets the same $15 monthly credit for chat and API use, plus a vote in how the Inference Cooperative is run. Credits never expire, and you can cancel any time.

To join, visit inference.coop and sign up. Your membership includes access to the chat and the developer API — this extension brings those same models into GitHub Copilot Chat.

Requirements

  • VS Code 1.145 or newer
  • GitHub Copilot Chat, installed and signed in

Copilot Business/Enterprise: your administrator must leave "Bring Your Own Language Model Key" enabled, or these models will not appear.

Setup

  1. Create an API key at dashboard.inference.coop/#keys-card. The key is only shown once, right after it is created — copy it somewhere safe before you close the page.
  2. Run Inference Coop: Set API Key from the Command Palette and paste the key. It is stored in VS Code's secret storage, not in settings.
  3. Open Copilot Chat, click the model name, and pick an inference-coop/… model. Tool calling works, so agent mode is usable.

To sign out, run Inference Coop: Sign Out. (You can create a new key any time and run Set API Key again — keys are not deleted when you sign out, so revoke unused keys from the dashboard.)

Limitations

  • No image input; models are advertised as text-and-tools only.
  • Token counts are estimated rather than computed with a real tokenizer, so context budgeting is approximate.
  • No inline code completions. Copilot does not support third-party providers for completions; this extension only adds chat models.

License

Apache-2.0. See LICENSE and NOTICE.

S
Description
VSCode plugin to add inference.coop models to the CoPilot chat
Readme Apache-2.0
657 KiB
0 Stars 2 Watchers 0 Forks
Languages
TypeScript 87%
JavaScript 13%