let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: clarify semantic memory key requirements

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-13 01:53:34 +00:00
parent 4f1c6e76fd
commit d57db17300
1 changed files with 9 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
docs/start/faq.md
View File

@@ -231,13 +231,16 @@ Clawdbot also runs a **silent pre-compaction memory flush** to remind the model
to write durable notes before auto-compaction. This only runs when the workspace to write durable notes before auto-compaction. This only runs when the workspace
is writable (read-only sandboxes skip it). See [Memory](/concepts/memory). is writable (read-only sandboxes skip it). See [Memory](/concepts/memory).
### Why does memory search need an OpenAI API key if I already signed in with Codex? ### Does semantic memory search require an OpenAI API key?
Vector memory search uses **embeddings**. Codex OAuth only covers Only if you use **remote embeddings** (OpenAI). Codex OAuth covers
chat/completions and does **not** grant embeddings access, so the upstream chat/completions and does **not** grant embeddings access, so **signing in with
memory indexer needs a real OpenAI API key (`OPENAI_API_KEY` or Codex (OAuth or the Codex CLI login)** does not help for semantic memory search.
`models.providers.openai.apiKey`). If you don’t want to set a key, switch to Remote memory search still needs a real OpenAI API key (`OPENAI_API_KEY` or
`memorySearch.provider = "local"` or set `memorySearch.fallback = "none"`. `models.providers.openai.apiKey`). If you’d rather stay local, set
`memorySearch.provider = "local"` (and optionally `memorySearch.fallback =
"none"`). We support **remote or local embedding models** — see [Memory](/concepts/memory)
for the setup details.
## Where things live on disk ## Where things live on disk