We're playing catch up since rebuilding Babbily. Things we're adding in short order:
- Context windows
- Context Summarization (will include when switching models mid thread)
- Memory moving out of beta
- Skills (and skill creation)
- Slash Commands
- Connectors
- Auto mode
We've improved file parsing across all models! Attach any file to any chat model.
No more switching models first. Babbily now reads PDFs, Word, Excel, PowerPoint, code, images, audio, video, and ZIPs on every chat model... and reads each file once, so follow-ups don't pay for it again.
Finishing up a major update to file parsing.
Our goal is to simplify and unify the model picker so users donโt have to know what every model can or canโt do.
Instead, Babbily will handle those capability gaps behind the scenes, giving models access to capabilities they donโt natively support and letting you focus on choosing the model you want to use.
Speaking of our new character glow-ups: Fun style, way more personality.
Soon you'll get to build your own Babbily avatar into one of these looks, for more personalization.
We've been heads-down building, not posting. Here's what shipped in Babbily since Sept 2:
- GPT-6 Astra now live, with Fast and Max reasoning modes
- GPT Image 2.5 Flare for image generation and editing
- Edit earlier messages without losing your thread
- Move existing chats into Projects
- Clearer controls for reviewing what Babbily remembers
- Search results now surface more relevant photos
We've also changed our characters in our graphics ๐
More to come.
Now live in Babbily โจ
๐ Projects keep chats, instructions, files, and memory together.
โฐ Scheduled Tasks automate recurring prompts on paid plans.
๐ Connectors are now Plugins, with a new Composio-powered connection flow.
Existing apps may need to be reconnected.
...Fable 5.1 will be added shortly.
Where should we focus our dev efforts over the next couple of weeks?
We're about to launch Projects (Individual and Team), Scheduled Tasks, Updated Plugins, and QOL improvements for both web and mobile.
Outside of that:
We've added Grok 4.6 amongst other model updates. Grok 4.6 delivers frontier intelligence and is a significant improvement over Grok 4.5 at the same price.
Weโve retired Saved Prompts/Babs in Babbily.
Usage was low, and as Babbily evolves toward more agentic ways of working, Memory now carries the context and preferences youโd otherwise repeatโwhile Skills support reusable workflows.
Less setup. More adaptive work.
Babbily has a new Deep Research Agent ๐
Ask a broad question and it will plan the work, break it into focused sub-questions, gather and verify sources, and stream a cited report directly into Canvas. Follow the progress, edit the report, and export it when youโre ready. If a run is interrupted, your useful work stays available.
Finance got smarter too ๐
Finance context now persists across follow-ups, reloads, and retries, with improved coverage for live quotes, historical periods, earnings, peer comparisons, and company filings.
Research more deeply. Make better-informed decisions.
Your work. Your team. The right workspace. ๐ง โจ
Babbily now supports multiple workspacesโkeep personal projects separate, switch into dedicated team spaces, and collaborate through shared chats and media.
With the new Shared Team Brain, useful context from team conversations can carry across your workspace, helping everyone build on what the team already knows.
Less repetition. More continuity. One shared place to think, create, and move work forward.