diff --git a/README.md b/README.md
index 066807597..13887c574 100644
--- a/README.md
+++ b/README.md
@@ -101,7 +101,7 @@ headroom perf
 headroom dashboard                      # live savings dashboard (proxy must be running)
 ```
 
-Granular extras: `[proxy]`, `[mcp]`, `[ml]`, `[code]`, `[memory]`, `[relevance]`, `[image]`, `[agno]`, `[langchain]`, `[evals]`, `[pytorch-mps]` (Apple-GPU memory-embedder offload — set `HEADROOM_EMBEDDER_RUNTIME=pytorch_mps`). Requires **Python 3.10+**.
+Granular extras: `[proxy]`, `[mcp]`, `[ml]`, `[code]`, `[memory]`, `[vector]` (optional HNSW backend — needs a C++ toolchain, not in `[all]`), `[relevance]`, `[image]`, `[agno]`, `[langchain]`, `[evals]`, `[pytorch-mps]` (Apple-GPU memory-embedder offload — set `HEADROOM_EMBEDDER_RUNTIME=pytorch_mps`). Requires **Python 3.10+**.
 
 ## Proof
 
@@ -325,7 +325,7 @@ npm install headroom-ai                 # TypeScript / Node
 docker pull ghcr.io/chopratejas/headroom:latest
 ```
 
-Granular extras: `[proxy]`, `[mcp]`, `[ml]` (Kompress-base), `[code]`, `[memory]`, `[relevance]`, `[image]`, `[agno]`, `[langchain]`, `[evals]`, `[pytorch-mps]` (Apple-GPU memory-embedder offload — set `HEADROOM_EMBEDDER_RUNTIME=pytorch_mps`). Requires **Python 3.10+**.
+Granular extras: `[proxy]`, `[mcp]`, `[ml]` (Kompress-base), `[code]`, `[memory]`, `[vector]` (optional HNSW backend — needs a C++ toolchain, not in `[all]`), `[relevance]`, `[image]`, `[agno]`, `[langchain]`, `[evals]`, `[pytorch-mps]` (Apple-GPU memory-embedder offload — set `HEADROOM_EMBEDDER_RUNTIME=pytorch_mps`). Requires **Python 3.10+**.
 
 > **Note**: `[all]` covers the core stack but excludes framework adapters. Install them separately: `pip install "headroom-ai[langchain]"` (also `[agno]`, `[strands]`, `[anyllm]`, `[bedrock]`).
 
diff --git a/docs/content/docs/installation.mdx b/docs/content/docs/installation.mdx
index 162cc2a91..00187993c 100644
--- a/docs/content/docs/installation.mdx
+++ b/docs/content/docs/installation.mdx
@@ -41,7 +41,8 @@ pip install "headroom-ai[all]"
 | `proxy` | Proxy server, MCP tools, HTTP API | `pip install "headroom-ai[proxy]"` |
 | `ml` | Kompress (ModernBERT text compression, requires PyTorch) | `pip install "headroom-ai[ml]"` |
 | `code` | CodeCompressor (tree-sitter AST parsing) | `pip install "headroom-ai[code]"` |
-| `memory` | Persistent memory (hnswlib, sqlite-vec, sentence-transformers) | `pip install "headroom-ai[memory]"` |
+| `memory` | Persistent memory (sqlite-vec, sentence-transformers) — pure-Python default backend, no compiler | `pip install "headroom-ai[memory]"` |
+| `vector` | Optional HNSW vector backend (hnswlib) — needs a C++ toolchain; **not in `[all]`** | `pip install "headroom-ai[vector]"` |
 | `relevance` | fastembed-based relevance scoring (BAAI/bge-small-en-v1.5, ONNX) | `pip install "headroom-ai[relevance]"` |
 | `image` | Image compression (Pillow, ONNX runtime, OCR) | `pip install "headroom-ai[image]"` |
 | `reports` | HTML/Markdown report generation (Jinja2) | `pip install "headroom-ai[reports]"` |
diff --git a/pyproject.toml b/pyproject.toml
index 0db33160d..2863896a8 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -107,12 +107,22 @@ ml = [
     # strands-agents`) drags huggingface-hub backwards.
     "huggingface-hub>=1.5.0,<2.0",
 ]
-# Memory system (hierarchical memory with vector search)
+# Memory system (hierarchical memory with vector search).
+# Uses the pure-Python sqlite-vec backend by default (VectorBackend.AUTO ->
+# SQLITE_VEC), so no C++ toolchain is required. The optional HNSW backend lives
+# in the [vector] extra below; installing it here would make `[all]` (which pulls
+# [memory]) fail on any machine without a compiler — see #1368.
 memory = [
-    "hnswlib>=0.8.0",
     "sqlite-vec>=0.1.6",
     "sentence-transformers>=2.2.0,<6.0",
 ]
+# Optional HNSW vector backend. Needs a C++ toolchain to build hnswlib, so it is
+# kept out of [memory] and [all]; opt in with `pip install headroom-ai[vector]`
+# and select it via MemoryConfig(vector_backend=VectorBackend.HNSW). The default
+# sqlite-vec backend needs no compiler.
+vector = [
+    "hnswlib>=0.8.0",
+]
 # Qdrant + Neo4j memory backend helpers
 memory-stack = [
     "mem0ai>=2.0.0,<3.0",