github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 04:34:16 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #2567] Clarify abou Telemetry #1506

New Issue
Closed
opened 2026-04-12 11:25:07 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 11:25:07 -05:00
Owner
Copy Link

Originally created by @user82622 on GitHub (Feb 17, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2567

It seems the ollama binary is using some type of telemetry. Please clarify what this data is and where it is sent to, also give us an option to opt out or better have this as an opt-in. Many users assume this is a private alternative to the big cloud LLM's if the program then has telemetry that potentially reveals private data this can be super misleading.

Originally created by @user82622 on GitHub (Feb 17, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2567 It seems the ollama binary is using some type of telemetry. Please clarify what this data is and where it is sent to, also give us an option to opt out or better have this as an opt-in. Many users assume this is a private alternative to the big cloud LLM's if the program then has telemetry that potentially reveals private data this can be super misleading.
GiteaMirror added the question label 2026-04-12 11:25:07 -05:00
GiteaMirror commented 2026-04-12 11:25:08 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Feb 17, 2024):

Why do you think it uses telemetry?

<!-- gh-comment-id:1950295972 --> @easp commented on GitHub (Feb 17, 2024): Why do you think it uses telemetry?
GiteaMirror commented 2026-04-12 11:25:09 -05:00
Author
Owner
Copy Link

@user82622 commented on GitHub (Feb 17, 2024):

There is often traffic going to cloudflare IPs and others (not sure what), i was not doing a full investigation on it but to me it seems like there is traffic happening with every now and then without user action. I may could also be wrong and it is only the Ollama WebUI that is the root of all of the traffic.

<!-- gh-comment-id:1950300035 --> @user82622 commented on GitHub (Feb 17, 2024): There is often traffic going to cloudflare IPs and others (not sure what), i was not doing a full investigation on it but to me it seems like there is traffic happening with every now and then without user action. I may could also be wrong and it is only the Ollama WebUI that is the root of all of the traffic.
GiteaMirror commented 2026-04-12 11:25:09 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Feb 19, 2024):

Hi @user82622, what you're seeing is probably the auto-update check that you can see here:
1e23e82324/app/lifecycle/updater.go (L79)

This should be the only outgoing call from Ollama, it is used to download new versions of Ollama when they are released. It includes information needed to update your system (OS and architecture).

Ollama does not track any of your data or input. This is the only outgoing call. Let me know if you see anything else and I'd be happy to help investigate.

<!-- gh-comment-id:1952876415 --> @BruceMacD commented on GitHub (Feb 19, 2024): Hi @user82622, what you're seeing is probably the auto-update check that you can see here: https://github.com/ollama/ollama/blob/1e23e82324e7052fac0dc58d977cfc1948e19b00/app/lifecycle/updater.go#L79 This should be the only outgoing call from Ollama, it is used to download new versions of Ollama when they are released. It includes information needed to update your system (OS and architecture). Ollama does not track any of your data or input. This is the only outgoing call. Let me know if you see anything else and I'd be happy to help investigate.
GiteaMirror commented 2026-04-12 11:25:09 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Oct 9, 2024):

None of that has anything to do with reality. Large Language Models are not self aware of their own capabilities and they make things up.

If you aren't reassured by BruceMacD's statement, you should monitor outgoing connections from Ollama.

<!-- gh-comment-id:2401285081 --> @easp commented on GitHub (Oct 9, 2024): None of that has anything to do with reality. Large Language Models are not ~~self~~ aware of their own capabilities and they make things up. If you aren't reassured by BruceMacD's statement, you should monitor outgoing connections from Ollama.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label question
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#1506
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?