aboutsummaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAgeFilesLines
...
* chore: remove unused packages (#551)VIshal Anton2025-11-022-15/+1
| | | Co-authored-by: antonvishal <[email protected]>
* fix: chat messages scroll effect (#544)Mahesh Sanikommu2025-10-293-170/+170
|
* chore: remove unused files (#540)10-28-chore_remove_unused_filesMaheshtheDev2025-10-294-3/+1
| | | | | | | | | | | ### Relocated logo file and removed unnecessary configuration files. ### What changed? - Moved `logo.svg` to `apps/web/public/logo-fullmark.svg` - Updated the logo path in `README.md` to reflect the new location - Removed empty `.npmrc` file - Removed `apps/web/public/_headers` file that contained Next.js static caching configuration
* fix: skeleton and mobile chat improvments (#541)10-28-fix_skeleton_and_mobile_chat_improvmentsMaheshtheDev2025-10-294-12/+30
| | | | | | | | | | | ### Improved mobile responsiveness across chat interface and memory list with better loading states. ### What changed? - Added responsive padding in chat page for mobile devices - Enhanced header layout for chat titles with proper truncation and responsive text sizes - Replaced the simple loading spinner in memory list with skeleton loading cards - Improved message container width constraints on mobile devices
* fix: add type safety annotations and fix hook dependencies in chat (#521)Aman pandit2025-10-281-15/+37
|
* Updated contribute.md and .env.example for better onboarding (#536)Nikhil Joshi2025-10-281-1/+10
|
* feat(@supermemory/tools): capture assitant responses with filtered memory (#539)MaheshtheDev2025-10-289-161/+405
| | | | | | | | | | | | | | | ### Added streaming support to the Supermemory middleware and improved memory handling in the AI SDK integration. ### What changed? - Refactored the middleware architecture to support both streaming and non-streaming responses - Extracted memory prompt functionality into a separate module (`memory-prompt.ts`) - Added memory saving capability for streaming responses - Improved the formatting of memory content with a "User Supermemories:" prefix - Added utility function to filter out supermemories from content - Created a new streaming example in the test app with a dedicated route and page - Updated version from 1.3.0 to 1.3.1 in package.json - Simplified installation instructions in [README.m](http://README.md)d
* feat: docs with new array contains (#534)Dhravya Shah2025-10-272-722/+569
|
* feat: improved add memory UI bits (#502)Hardik Vora2025-10-276-21/+21
|
* feat: optional posthog intialization (#525)Saksham Kushwaha2025-10-273-25/+40
|
* Fix/invalid dom property (#526)Saksham Kushwaha2025-10-272-34/+20
| | | Co-authored-by: Mahesh Sanikommu <[email protected]>
* fix: openai sdk packaging issue (#532)MaheshtheDev2025-10-272-2/+2
|
* chore: skip the conditional org switch for better auth state share (#533)MaheshtheDev2025-10-271-8/+9
|
* feat: withSupermemory for openai sdk (#531)MaheshtheDev2025-10-2711-8/+744
| | | | | | | | | | | | | | | ### TL;DR Added OpenAI SDK middleware support for SuperMemory integration, allowing direct memory injection without AI SDK dependency. ### What changed? - Added `withSupermemory` middleware for OpenAI SDK that automatically injects relevant memories into chat completions - Implemented memory search and injection functionality for OpenAI clients - Restructured the OpenAI module to separate tools and middleware functionality - Updated README with comprehensive documentation and examples for the new OpenAI middleware - Added test implementation with a Next.js API route example - Reorganized package exports to support the new structure
* feat: more clarity on the connectors sync (#523)MaheshtheDev2025-10-271-10/+51
| | | | | | | | When connector is syncing ![image.png](https://app.graphite.dev/user-attachments/assets/68ab8a7f-6e0c-4900-8b6e-a7f1e1ae99f2.png) After connected showing the metadata ![image.png](https://app.graphite.dev/user-attachments/assets/d53d3cc9-234b-4365-b4e0-c50ab23d8876.png)
* fix: pricing in the settings (#528)MaheshtheDev2025-10-272-3/+3
|
* fix: auto switch to expected org (#522)MaheshtheDev2025-10-251-17/+23
|
* fix: bun lock build issue (#519)MaheshtheDev2025-10-241-30/+597
|
* Merge pull request #517 from lirena00/feature/better-loading-screenMahesh Sanikommu2025-10-242-8/+44
|\ | | | | feat: update app component to have a better loading screen
| * feat: update App component to have a better loading screenSaksham2025-10-242-8/+44
|/ | | | | | | - Changed the logo image source in App.tsx to use a file based svg rather than url one. - Enhanced the loading indicator with an animated SVG. - Adjusted styles for better alignment and spacing in the loading section. - Added the dark-transparent.svg file to the public directory.
* Merge pull request #509 from supermemoryai/prompt-mutationDhravya Shah2025-10-2223-383/+506
|\ | | | | fix: prompt mutation in withSupermemory and types for props
| * chat app withSupermemory testMahesh Sanikommmu2025-10-2219-1/+433
| |
| * add props interface exportMahesh Sanikommmu2025-10-223-9/+10
| |
| * add commentShoubhit Dash2025-10-221-1/+2
| |
| * add testShoubhit Dash2025-10-221-0/+24
| |
| * fix prompt mutation in vercel middlewareShoubhit Dash2025-10-222-374/+39
| |
* | Merge pull request #498 from max-programming/mainMahesh Sanikommu2025-10-223-36/+36
|\ \ | |/ |/| docs: fixed naming convention of SDK usage examples
| * Fixed naming convention of SDK usage examplesUsman Sabuwala2025-10-193-36/+36
| |
* | fix: t3chat prompt injection (#505)MaheshtheDev2025-10-212-64/+92
| |
* | chore: update to new supermemory support email (#503)MaheshtheDev2025-10-217-13/+10
| | | | | | | | updated the new supermemory support email to `[email protected]`
* | Merge pull request #497 from aryankeluskar/patch-stepsMahesh Sanikommu2025-10-201-1/+1
|\ \ | | | | | | feat(chat): increase maxSteps to allow multiple tool-calling rounds
| * | Fix formatting in chat-messages.tsxMahesh Sanikommu2025-10-181-1/+1
| | |
| * | feat(chat): increase maxSteps to allow multiple tool-calling roundsAryan Keluskar2025-10-181-1/+1
| |/
* | Merge pull request #500 from ↵Dhravya Shah2025-10-206-42/+167
|\ \ | | | | | | | | | | | | supermemoryai/10-19-chore_browser-extension_t3_chat_search_memories feat(browser-extension): setting to enable/disable auto prompt captures
| * | feat: auto capture disabled by defaultMahesh Sanikommmu2025-10-195-13/+140
| | |
| * | chore(browser-extension): t3 chat search memoriesMahesh Sanikommmu2025-10-192-29/+27
| |/
* | Merge pull request #501 from ↵Dhravya Shah2025-10-202-4/+24
|\ \ | | | | | | | | | | | | supermemoryai/10-19-fix_tools_update_the_docs_for_conversational fix(tools): update the docs for conversational
| * | fix(tools): update the docs for conversationalMahesh Sanikommmu2025-10-192-4/+24
|/ /
* / add conversationId functionality to map to customId in ingestion (#499)sohamd222025-10-192-5/+37
|/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ### TL;DR Added support for conversation grouping in Supermemory middleware through a new `conversationId` parameter. ### What changed? - Added a new `conversationId` option to the `withSupermemory` function to group messages into a single document for contextual memory generation - Updated the middleware to use this conversation ID when adding memories, using a `customId` format of `conversation:{conversationId}` - Created a new `getConversationContent` function that extracts the full conversation content from the prompt parameters - Enhanced memory storage to save entire conversations rather than just the last user message - Updated documentation and examples to demonstrate the new parameter usage ### How to test? 1. Import the `withSupermemory` function from the package 2. Create a model with memory using the new `conversationId` parameter: ```typescript const modelWithMemory = withSupermemory(openai("gpt-4"), "user-123", { conversationId: "conversation-456", mode: "full", addMemory: "always" }) ``` 3. Use the model in a conversation and verify that messages are grouped by the conversation ID 4. Check that memories are being stored with the custom ID format `conversation:{conversationId}` ### Why make this change? This enhancement improves the contextual understanding of the AI by allowing related messages to be grouped together as a single conversation document. By using a conversation ID, the system can maintain coherent memory across multiple interactions within the same conversation thread, providing better context retrieval and more relevant responses.
* version bump'Dhravya Shah2025-10-181-1/+1
|
* feat(browser-extension): folder level x bookmarks import with project ↵MaheshtheDev2025-10-198-18/+573
| | | | | | | | selection (#495) Feature : Import folder level x bookmarks [Screen Recording 2025-10-17 at 1.37.52 PM.mov <span class="graphite__hidden">(uploaded via Graphite)</span> <img class="graphite__hidden" src="https://app.graphite.dev/user-attachments/thumbnails/15cd60ff-856e-4f29-8897-74ae3c869c87.mov" />](https://app.graphite.dev/user-attachments/video/15cd60ff-856e-4f29-8897-74ae3c869c87.mov)
* Merge pull request #472 from Mikethebot44/feature/show-memory-content-markdownMahesh Sanikommu2025-10-181-9/+152
|\ | | | | Add markdown rendering support to memory content display
| * removed unneccasry commentsMahesh Sanikommmu2025-10-101-7/+1
| |
| * removed unused code and lint issuesMahesh Sanikommmu2025-10-101-50/+98
| |
| * feat: format memory dialog content in markdownYour Name2025-10-091-9/+110
| | | | | | | | | | | | | | - Add markdown rendering support to memory content display - Auto-detect and format JSON responses in code blocks - Convert terminal commands to bash code blocks - Improve code block styling with monospace font and compact spacing
* | Merge pull request #491 from vorahardik7/fix/graph-viewDhravya Shah2025-10-173-74/+249
|\ \ | | | | | | fix: mount graph dialog globally to fix chat page issue
| * | comment fixesMahesh Sanikommmu2025-10-171-1/+0
| | |
| * | fix: mount graph dialog globally to fix chat page issuevorahardik72025-10-153-74/+250
| | |
* | | fix: magic link auth for chrome extension (#492)MaheshtheDev2025-10-171-6/+9
|/ / | | | | | | The issue is whenever a user is trying to log in with an email and a one-time code, the Chrome extension is not able to authenticate. The fix is to add a callback URL with a query parameter of `extension-auth-success` equal to `true`, which will allow the Chrome extension to identify and verify the auth whenever a user is trying to log in into the Chrome extension.
* | Merge pull request #488 from naman06dev/mainDhravya Shah2025-10-1314-28/+252
|\ \ | | | | | | feat: n8n + zapier integration page
generated by cgit v1.2.3 (git 2.25.1) at 2026-03-11 13:29:59 +0000