Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #1702] [FEAT]: multiple chatbots #1115

New Issue
Closed
opened 2026-02-22 18:23:10 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:23:10 -05:00
Owner
Copy Link
Copy Source

Originally created by @chalitbkb on GitHub (Jun 17, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1702

What would you like to see?

It would be fantastic if the "AnythingLLM" workspace could support live chat through multiple provider Model APIs simultaneously.

Additionally, enabling chats across several workspaces at the same time would be beneficial. Instead of being limited to chatting within a single workspace, this feature would allow interaction with different workspaces that might use varying model APIs and system prompts but share similar approaches. This simultaneous chatting capability would save time by reducing the need to switch between workspaces. Sometimes, I'm not satisfied with the responses from one workspace and would like to try another.

image

image

Originally created by @chalitbkb on GitHub (Jun 17, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1702 ### What would you like to see? It would be fantastic if the "AnythingLLM" workspace could support live chat through multiple provider Model APIs simultaneously. Additionally, enabling chats across several workspaces at the same time would be beneficial. Instead of being limited to chatting within a single workspace, this feature would allow interaction with different workspaces that might use varying model APIs and system prompts but share similar approaches. This simultaneous chatting capability would save time by reducing the need to switch between workspaces. Sometimes, I'm not satisfied with the responses from one workspace and would like to try another. ![image](https://github.com/Mintplex-Labs/anything-llm/assets/32437546/58bffc4f-befe-4628-b525-9efe076df2d3) ![image](https://github.com/Mintplex-Labs/anything-llm/assets/32437546/13fb3242-a16d-48bc-875b-a8e391666a46)
yindo added the enhancementfeature request labels 2026-02-22 18:23:10 -05:00
yindo closed this issue 2026-02-22 18:23:10 -05:00
yindo commented 2026-02-22 18:23:11 -05:00
Author
Owner
Copy Link
Copy Source

@PGTBoos commented on GitHub (Jul 18, 2024):

I think for this idea, (i did those things directly in python in the past).
There should be various discussion types and settings

  • What's the role of a participant, may it act as a discussion leader ? (keeping it on topic, and asking other experts)
  • Can an agent talk to any other agent, or is there a strict follow up pattern, ea next agent = "agent name"
  • Group chat, bots, all writing on the same output screen,
    • Will there be an agent, or agentless, single output file (so to keep the chatter out of the doc).
    • output may also be perhaps not a file but a custom api endpoint (blog) /and maybe input as well (ea some news article)
  • Should a discussion cycle wait for human input, or can agents continue themselves.
  • Should an agent be able to adjust the past history chat to summarize / or to steer topic back
  • Should agents be able to be turned on / off on a per need basis (to reduce memory and chat participation).
  • Should agents have access read write to some kind of a simple value store, on which end users can apply some python.
    ea current time, current mood as a string, ... etc
  • Should there be a generic prepompt database to quickly config llm chat participants

Maybe i dive a bit to deep here, but since i did this in python so i share some ideas here.
the list probably can be made longer.

@PGTBoos commented on GitHub (Jul 18, 2024): I think for this idea, (i did those things directly in python in the past). There should be various discussion types and settings - What's the role of a participant, may it act as a discussion leader ? (keeping it on topic, and asking other experts) - Can an agent talk to any other agent, or is there a strict follow up pattern, ea next agent = "agent name" - Group chat, bots, all writing on the same output screen, - Will there be an agent, or agentless, single output file (so to keep the chatter out of the doc). - output may also be perhaps not a file but a custom api endpoint (blog) /and maybe input as well (ea some news article) - Should a discussion cycle wait for human input, or can agents continue themselves. - Should an agent be able to adjust the past history chat to summarize / or to steer topic back - Should agents be able to be turned on / off on a per need basis (to reduce memory and chat participation). - Should agents have access read write to some kind of a simple value store, on which end users can apply some python. ea current time, current mood as a string, ... etc - Should there be a generic prepompt database to quickly config llm chat participants Maybe i dive a bit to deep here, but since i did this in python so i share some ideas here. the list probably can be made longer.
yindo changed title from [FEAT]: multiple chatbots to [GH-ISSUE #1702] [FEAT]: multiple chatbots 2026-06-05 14:39:02 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label enhancement feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1115
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?