docs(readme): adapter ecosystem now 22 — Mistral + DeepSeek + Mercury + Hugging Face#116
Merged
Merged
Conversation
…gingface) Brings the public adapter ecosystem to 22 production adapters. New rows: - Mistral AI (EU-hosted: Large, Codestral, Pixtral vision) - DeepSeek (V3 chat + R1 reasoning, OpenAI-compat) - Mercury (Inception Labs, diffusion LLM, GA + OpenAI-compat verified) - Hugging Face Inference Endpoints (dual-mode: dedicated + serverless) Updates the "Why Compendium?" bullet to reflect twenty-two adapters. The Compendium framework itself also gained an InMemoryCache implementation in v1.0.3 (Compendium.Infrastructure.Caching) plus a new Compendium.Abstractions.Caching abstraction — drop-in alternative to Compendium.Adapters.Redis for dev / single-instance deploys. The packages list below will reflect it once added in a follow-up.
There was a problem hiding this comment.
Pull request overview
Updates the repository README to reflect the newly shipped public AI adapters and keeps the “Adapters” index consistent with the current adapter ecosystem size (22), per the project’s multi-repo adapter model.
Changes:
- Updates the “Why Compendium?” bullet to reflect twenty-two production adapters and includes the four new AI providers.
- Adds four new rows to the README “Official adapters” table for Mistral, DeepSeek, Mercury, and Hugging Face Inference Endpoints.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Phase 6 shipped 4 more public adapters today. README `## Adapters` catches up to 22 entries.
Phase 6 also shipped a framework-internal `Compendium.Abstractions.Caching` + `Compendium.Infrastructure.Caching.InMemoryCache` (POM-512, see PR #115 → `v1.0.3`). Not an adapter — lives in the framework. Drop-in alternative to `compendium-adapter-redis` for dev / single-instance / unit-test scenarios.
Per memory `project_compendium_readme_adapter_index.md`, every public adapter ship updates this table.
Test plan