Memory Support
Memory is now supported on TypingMind 👀
Your AI can remember context about you, your preferences, and the way you work - so you don’t have to repeat yourself in every new chat.
Changelog
Follow new updates and improvements to TypingMind.
Plugin System update: Improve image and file handling in chat
TypingMind now handles generated images and chat files more seamlessly across Plugins, MCP tools, GPT Image plugin, and Artifacts.
For users
Attachment/Generated files are now managed under About this chat → Files.
GPT Image 2.5 can now edit any image available in the current chat, instead of being limited to images from your latest message. The AI will automatically select the relevant images to use.
Interactive Canvas and Web App Builder can now use images directly from the chat. When you share an artifact, the images displayed inside it and are included as part of the shared artifact.
For plugin developers
Plugins can now receive files directly from the chat using the new typingmind-attachment parameter type together with the read_chat_attachments permission. Learn more
Image cards now support a new image.filename field. Base64 images returned by cards are also automatically saved as chat files. Learn more
Chat files can now be referenced directly in plugin output:
HTML:
tm-attachment://<id>Markdown:
#tm-attachment:<id>
For GitHub-hosted plugins, JavaScript functions can now be stored in separate files using the new codeFile field. Learn more
Behavior changes
previousRunOutput no longer includes output from respond_to_ai. Learn more
When importing a plugin from a private GitHub repository, TypingMind now uses the main branch by default. To import from another branch, add **`
TypingMind Teams Update & UXUI Improvements
Teams Updates:
Added user group filtering to org analytics, allowing users to view tokens and messages broken down by user group, plus a new "User Groups" option when exploring analytics data.
Integration API key generation is now restricted to account owners and admins; other roles can still view and revoke existing keys.
UXUI Improvements:
Open "About this chat" in a convenient side panel, better view artifacts on both desktop and mobile.
Improved the button UI in rendering results for artifacts, HTML, and code.
Improved support for reading PowerPoint (.pptx) attachments.
Earlier updates
- Added GPT-6.1 SolAdded GPT-6.1 Sol and GPT-6.1 Sol Pro to TypingMind — OpenAI mid-tier upgrade (Sept 29, 2026, DevDay). Near-Astra on coding, computer use, and pro work at ~1/5 Astra’s token price. Same $2 / $10 as GPT-6 Sol; cached input now $0.10. 1.05M context.NewAI Models
- Claude Sonnet 5.5 is here!You can now use Claude Sonnet 5.5 — Anthropic mid-tier (Sept 28, 2026). Faster, cheaper complement to Opus 5.5 for everyday coding, docs, and agents. ~30% faster than Sonnet 5, up to 30% less per task. Same list price: $2 / $10 per M tokens. 1M context.NewAI Models
- Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna are available!Claude Opus 5.5 — Anthropic’s Sept 2026 flagship for agentic coding and long knowledge work. Fable 5.1–level on most tasks, ~40% cheaper to run than Opus 5. $4 / $20 per M tokens. GPT-6 Sol — OpenAI’s mid-tier GPT-6 (below Astra). Complex coding and agents, much of Astra’s strength at half GPT-5.6 Sol’s price. $2 / $10 per M tokens. GPT-6 Luna — Cheapest/fastest GPT-6. High-volume focused tasks (extract, classify, summarize, simple code). $0.10 / $0.50 per M tokens.NewAI Models
- Added Grok 4.7 and MiMo-V2.6 (Pro and Flash)Grok 4.7 — xAI flagship (Sept 21, 2026) for coding and knowledge work. Larger than 4.6, better on long tasks and self-checks, same price/speed. $2 / $6 per M tokens. MiMo-V2.6-Pro — Xiaomi open-weight flagship (MIT). 1.02T MoE / 42B active, 1M context, text+image+video+audio. Top-tier open model. API ~$0.44 / $0.87 per M tokens. MiMo-V2.6-Flash — Cheaper Xiaomi twin. 309B / 15B active, same 1M context and modalities. Close to Pro on many agent tasks. API $0.14 / $0.28 per M tokens.NewAI Models
- Plugin PresetsIntroducing Plugin Presets in TypingMind 🎉 You can now save your favorite plugins, skills, and MCP servers into named presets and switch between them with a single click. Create presets for different workflows like Frequently Used, Coding, Support, Sales, or Research — so you always have the right tools enabled for the task at hand. Also in this update, you can search plugins, disable all plugins instantly, and export/import presets across devices.NewIntegrations
- Add more quality options for GPT Image 2.5, select model for side chat and more!Added xhigh and max quality options, plus 4K landscape (3840x2160) and portrait (2160x3840) resolutions for GPT Image 2.5. Also reordered resolution and quality options for easier selection. Side Chat Model Selection: Users can now choose which model powers the side chat "Ask..." feature (highlight text in a chat → select Ask...), either via a new setting or directly from the side chat popup. Temporary Chat for Agents: Added support for temporary chat when using agents.New
- DeepSeek V4.1 Flash is now availableAdded DeepSeek V4.1 Flash - the smallest model in DeepSeek’s architecture family, with native visual understanding.NewAI Models