A major platform update makes chat more capable, more connected, and easier to control.
New features
Skills, tools, memory, and connectors. Babbily can now personalize replies with persistent memory, use tools and skills when they help, and pull live context from connected apps through Smithery MCP connectors. The new tool system powers web search, deep research, site mapping, finance research, weather, stats, QR codes, image generation, video generation, and memory.
Choose how much Babbily uses tools. New Auto, Manual, and Off modes control tool use. Auto can choose available capabilities when they seem useful.
API usage billing. A monthly API usage budget replaces fixed message limits. Track what you’ve used, see what counts, and know when it resets, all from the chat sidebar.
Memory and profile personalization. When memory is on, saved profile details can sync into memory, helping Babbily learn your preferences and work style over time.
Updates
Tool progress, research status, memory citations, connector diagnostics, and media generation states now stream more clearly while Babbily works.
Saved-thread context compaction keeps long conversations useful by preserving important context while trimming the rest.
The context window tracker updates more reliably during long chats, so you can tell when Babbily will compact older turns.
Your usage view refreshes faster after each turn. Final usage may continue to settle as billing data refreshes.
A cleaner floating thread header, better attachment and connector persistence, and more reliable long-running research and tool jobs.
Fixes
Resolved a stall when the context-limit warning appeared mid-send.
Restored model fallback so chat keeps working when a preferred model is briefly unavailable.
Fixed scrolling and layout glitches in temporary chats and on tablet viewports.
Sign-in with Google and Apple is more reliable on mobile.