v1.9.0

Mintplex-Labs/anything-llmv1.9.0Oct 9, 2025by timothycarambat

AI Summary

Major agent overhaul introducing real-time streaming for all providers and models. Agents can now stream tool calls and responses, and download/ingest files from the web in real-time. Includes Microsoft Foundry Local integration.

Key Highlights

  • Agent experience overhaul with real-time streaming
  • Real-time agent tool call streaming for all providers
  • Microsoft Foundry Local integration
  • Ephemeral web resource scraping/downloading via agent
  • All models and providers now support agentic streaming

New Features

  • Real-time agent tool call streaming
  • Web resource download via agent (PDF, excel, CSV)
  • Microsoft Foundry Local LLM & agent provider
  • OpenAI migrated to Responses API
  • New default system prompt variables (User ID, Workspace ID, Workspace Name)
  • Model context limit auto-detection for LM Studio and Ollama
  • Helm Chart for Kubernetes deployment
  • Cohere models reimplemented for basic chat
  • Tooltips for workspace and threads

Full Release Notes

## `@agent` Overhaul & streaming ⚡️️

<video src="https://github.com/user-attachments/assets/fbbfab37-e1b0-442b-b7d4-277aacfcf9bb"></video>

When anythingllm first launched, the word "agent" was not in the vocabulary of the LLM world. Agents are quickly becoming the standard for building AI applications and also the core experience for interacting with LLMs.

For too long, due to the complexity of building agents, spotty tool call support, models that can't even use tools and more nerd stuff, we often had to settle an experience that was not really fun to use since 99% of the time you were just looking at loading spinners waiting for the response.

### The new agent experience is now here

Streams tool calls and responses in real time (all providers, all models)
Agents can now real-time download and ingest files from the web (eg: link to PDF, excel, csv). Anything you would use a document can be read in real time by the agent from the web.

### Upcoming:
- Agent real-time API calling without agent flows
- Agent image understanding
- Agent system prompt passthrough + user context awareness
- Realtime file searching cross-platform default skill

## Notable Improvements: 🚀
 * All models and providers now support agentic streaming
 * Microsoft Foundry Local integration
 * Ephemerally scrape/download any web-resource via agent or uploader

## What's Changed
* Allow default users to reorder workspaces by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4292
* Export image support for JSON and JSONL by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4359
* Fix: missing edit icon for prompts by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/4344
* feat(i18n): add missing Portuguese (Brazil) translations by @beckeryuri in https://github.com/Mintplex-Labs/anything-llm/pull/4328
* feat: Implement CometAPI integration for chat completions and model m… by @TensorNull in https://github.com/Mintplex-Labs/anything-llm/pull/4379
* Resize chat textarea on paste by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4369
* update save file agent text by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4389
* Added metadata parameter to document/upload, document/upload/{folderName}, and document/upload-link by @jstawski in https://github.com/Mintplex-Labs/anything-llm/pull/4342
* Add support for `SIMPLE_SSO_NO_LOGIN_REDIRECT` config setting by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4394
* patch folder name GET request response by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4395
* Add User-Agent header on the requests sent by Generic OpenAI providers. by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4393
* Report sources in API responses on finalized chunk by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4396
* Allow user to specify args for chromium process so they dont need SYS_ADMIN on container. by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4397
* API request delay for Generic OpenAI embedding engine by @chaserhkj in https://github.com/Mintplex-Labs/anything-llm/pull/4317
* Enhanced Chat Embed History View by @MateKristof in https://github.com/Mintplex-Labs/anything-llm/pull/4281
* Ignore hasOwnProperty linting errors by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4406
* Migrate OpenAI LLM provider to use Responses API by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4404
* Update the timeout value on all stream-timeout providers: by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4412
* [BUGFIX] Update Dell Pro AI Studio Default URL by @spencerbull in https://github.com/Mintplex-Labs/anything-llm/pull/4433
* Add PostgreSQL vector extension in createTableIfNotExists function by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4430
* fix: resolve Firefox search icon overlapping placeholder text by @naaa760 in https://github.com/Mintplex-Labs/anything-llm/pull/4390
* Refactor Class Name Logging by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4426
* Change incorrect notation of Weaviate to PG Vector in env.example by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4439
* Enable custom HTTP response timeout for ollama by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4448
* fix: youtube transcript collector not work well with non en or non asr caption by @AoiYamada in https://github.com/Mintplex-Labs/anything-llm/pull/4442
* Add HTTP request/response logging middleware for development mode by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4425
* Sanitize Metadata Before PG Vector Database Insertion by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4434
* New Default System Prompt Variables (User ID, Workspace ID, & Workspace Name) by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4414
* Apply renderer from chat widget history to workspace chats by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4456
* Patch OpenAI metrics by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4458
* fix(uiux): correct typo in System Prompt description text by @vansh2408 in https://github.com/Mintplex-Labs/anything-llm/pull/4461
* Enable real-time agent tool call streaming for all providers by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4279
* Add stream options to Gemini LLM for usage tracking by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4466
* Fetch, Parse, and Create Documents for Statically Hosted Files by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4398
* Migrate OpenAI Agent to use ResponsesAPI by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4467
* Microsoft Foundry Local LLM provider & agent provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4435
* Model context limit auto-detection for LM Studio and Ollama LLM Providers by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4468
* Sync models from remote for FireworksAI by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4475
* Render html optional by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4478
* Adding AnythingLLM Helm Chart by @sculley in https://github.com/Mintplex-Labs/anything-llm/pull/4484
* Reimplement Cohere models for basic chat by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4489
* Tooltips for workspace and threads by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4500
* Improve URL handler for collector processes by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4504
* Migrate gemini agents away from `Untooled` by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4505
* Update .gitignore by @jaynedoezy-web in https://github.com/Mintplex-Labs/anything-llm/pull/4507
* refactor: change naming - contextwarpper to authprovider #4510 by @Guru6163 in https://github.com/Mintplex-Labs/anything-llm/pull/4511
* fix label for chunk length setting by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4515
* Fix: File pulling fails with uppercase URL characters by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4516

## New Contributors
* @beckeryuri made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4328
* @TensorNull made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4379
* @jstawski made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4342
* @angelplusultra made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4393
* @chaserhkj made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4317
* @MateKristof made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4281
* @spencerbull made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4433
* @AoiYamada made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4442
* @vansh2408 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4461
* @sculley made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4484
* @jaynedoezy-web made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4507
* @Guru6163 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4511

**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.5...v1.9.0