Chris-o-O hooks Mike into more brains and gives it real search

One pull request adds five extra AI models and turns the document library into something users can search by meaning.

searchintegration

Until now this fork, like upstream Mike, only spoke to Claude and Gemini. The team wired in OpenRouter - a broker that fans a single API key out across many AI vendors - unlocking GPT-4o, Mistral Large, Llama and Gemma alongside the existing options. Users supply their own key and toggle models from the chat UI.

The same PR adds proper semantic search. Uploaded documents are sliced into chunks, fed to Voyage AI's legal-tuned embedding model (it converts passages into mathematical fingerprints trained on case law), and stored so the system can match by meaning rather than keyword. A widget on the project page surfaces relevant passages, and the chat assistant can run the same search on its own.

So what Anyone whose Mike fork is locked to a single vendor, or whose users keep losing documents in the pile, should watch this branch.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

1 commit from Chris-o-O/mike-intell, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date

3279a584 Add OpenRouter multi-model support and Voyage AI semantic search Claude 2026-05-07 ↗ GitHub

SHA	Subject	Author	Date
`3279a584`	Add OpenRouter multi-model support and Voyage AI semantic search	Claude	2026-05-07	↗ GitHub
commit body OpenRouter: extends the LLM provider abstraction to support GPT-4o, GPT-4 Turbo, Mistral Large, Llama 3.3 70B, and Gemma 3 27B via a single OpenRouter API key. Follows the same provider pattern as Claude and Gemini - new openrouter.ts adapter, model routing by prefix, per-user API key stored in user_profiles, and full UI integration (model toggle, availability checks, account settings key field). Semantic search: adds Voyage AI embeddings (voyage-law-2, optimised for legal documents) to index document chunks at upload time (fire-and-forget, controlled by VOYAGE_API_KEY env var). Chunks are stored in a new document_chunks pgvector table. A /search/semantic endpoint and a semantic_search LLM tool enable concept-level retrieval. A new SemanticSearchWidget in ProjectPage exposes document search by meaning. https://claude.ai/code/session_01NJxa5NasJ9qhaMkzEyqr2u

commit body

OpenRouter: extends the LLM provider abstraction to support GPT-4o,
GPT-4 Turbo, Mistral Large, Llama 3.3 70B, and Gemma 3 27B via a
single OpenRouter API key. Follows the same provider pattern as Claude
and Gemini - new openrouter.ts adapter, model routing by prefix, per-user
API key stored in user_profiles, and full UI integration (model toggle,
availability checks, account settings key field).

Semantic search: adds Voyage AI embeddings (voyage-law-2, optimised for
legal documents) to index document chunks at upload time (fire-and-forget,
controlled by VOYAGE_API_KEY env var). Chunks are stored in a new
document_chunks pgvector table. A /search/semantic endpoint and a
semantic_search LLM tool enable concept-level retrieval. A new
SemanticSearchWidget in ProjectPage exposes document search by meaning.

https://claude.ai/code/session_01NJxa5NasJ9qhaMkzEyqr2u

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-172.md from inside the repo you want the changes in.

⬇ Download capture-thread-172.md