adding funcitonality
mwcyu/Mike-fork
A chat-focused Mike fork that combines live web search with a cleaner, more consistent AI experience.
mwcyu is shaping Mike around a more capable main chat: one where AI assistants can draw on current web results during a conversation, rather than answering from their existing knowledge alone.
The fork also puts emphasis on making the chat experience more consistent across AI providers and on testing the server-side journey that supports it. It looks like a focused effort to make Mike's conversational core more dependable and more useful for current-information questions.
What's in it
- Live web search in chat The assistant can search the open web mid-conversation and incorporate current results into its response.
- Consistent model experience Chat streaming is organised around a shared experience across supported AI providers.
- Simpler chat foundation The fork consolidates the moving parts behind live AI responses into one central flow.
- Automated route testing A dedicated integration suite checks that key server-side routes keep working together as the product evolves.
Direction
searchinfrastructureintegration
Activity
✅ #1 Use OpenAI SDK for Responses API streaming +3,383 -311 3mo ago self by
mwcyu ↗ analysis ↗ GitHub Replace the hand-rolled fetch + SSE parsing in the OpenAI adapter with the
📝 mwcyu unifies Mike's chat engine and hands every model web search 4 commits 3mo ago searchinfrastructure draft
A single streaming core replaces three hand-built ones, and once it landed, giving every AI model live web search became almost free.
📝 mwcyu writes the back-end tests upstream never bothered with 1 commit 3mo ago infrastructure draft
This fork is the first to wrap Mike's server-side plumbing in an automated test suite, so changes can't quietly break the wiring.
📝 mwcyu stops maintaining its AI plumbing in triplicate 3 commits 3mo ago infrastructureintegration draft
This fork ran three near-identical pipelines to talk to its AI models - now they share one.
The assistant can now reach out to the open web mid-conversation and fold current results straight into its answer.
Threads of work (detailed view)
mwcyu unifies Mike's chat engine and hands every model web search
A single streaming core replaces three hand-built ones, and once it landed, giving every AI model live web search became almost free.
mwcyu writes the back-end tests upstream never bothered with
This fork is the first to wrap Mike's server-side plumbing in an automated test suite, so changes can't quietly break the wiring.
mwcyu stops maintaining its AI plumbing in triplicate
This fork ran three near-identical pipelines to talk to its AI models - now they share one.
mwcyu wires live web search into Mike's main chat
The assistant can now reach out to the open web mid-conversation and fold current results straight into its answer.
Pull requests (detailed view)
✅ Merged (1)
by
mwcyu · opened 3mo ago · merged 3mo ago by mwcyu ⛔ Closed without merge (1)
by
mwcyu · opened 3mo ago · closed 2mo ago