feat(memory): support custom OpenAI-compatible embedding endpoints#819
Merged
steipete merged 2 commits intoJan 13, 2026
Merged
Conversation
mukhtharcm
changed the title
steipete
force-pushed
the
feature/memory-search-custom-endpoint
branch
from
January 13, 2026 03:11
825f334 to
da0a062
Compare
Contributor
|
Landed via temp rebase onto main.\n\n- Gate: pnpm lint && pnpm build && pnpm test\n- Land commit: da0a062\n- Merge commit: cb871a3\n\nThanks @mukhtharcm! |
victorarias
pushed a commit
to victorarias/clawdbot
that referenced
this pull request
Jan 13, 2026
3 tasks
lovewanwan
pushed a commit
to lovewanwan/openclaw
that referenced
this pull request
Apr 28, 2026
lovewanwan
pushed a commit
to lovewanwan/openclaw
that referenced
this pull request
Apr 28, 2026
…-custom-endpoint feat(memory): support custom OpenAI-compatible embedding endpoints
github-actions Bot
pushed a commit
to Desicool/openclaw
that referenced
this pull request
May 9, 2026
github-actions Bot
pushed a commit
to Desicool/openclaw
that referenced
this pull request
May 9, 2026
…-custom-endpoint feat(memory): support custom OpenAI-compatible embedding endpoints
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR introduces the ability to configure custom OpenAI-compatible embedding endpoints for the built-in memory search system.
Why is this needed?
Currently, the core memory system only supports the official OpenAI API or local embeddings via
node-llama-cpp. This limitation makes it difficult for users who want to use:Key Changes
remoteobject tomemorySearchconfiguration.baseUrl: Allows pointing to any OpenAI-compatible embedding endpoint.apiKey: Allows specifying a provider-specific key directly for embeddings (useful when your main chat model uses a different provider/key).headers: Supports custom HTTP headers for proxy authentication or routing.src/memory/embeddings.tsto prioritize theseremotesettings when theopenaiprovider is selected.src/config/schema.tswith UI hints so these fields appear in the Control UI and CLI.docs/concepts/memory.mdexplaining how to use custom endpoints.docs/gateway/configuration-examples.md.Backward Compatibility
This change is strictly additive. If the
remoteobject is missing, the system falls back to the existing behavior (using official OpenAI endpoints and the globalOPENAI_API_KEY).Testing Done
memory_searchtool) correctly retrieves conceptually relevant documents from a large corpus.pnpm buildandpnpm lintpass successfully.Generated by Mage 🪄 on behalf of @mukhtharcm