diff --git a/README.md b/README.md
index 7993968..5816a7a 100644
--- a/README.md
+++ b/README.md
@@ -37,91 +37,9 @@ go run . search -did did:plc:abc123 -rkey 3abc                         # find si
 go run . search -did did:plc:abc123 -rkey 3abc -cluster                # find similar + cluster
 ```
 
-### Search API
-
-`POST /api/v1/search` — bearer token optional.
-
-**Request:**
-```json
-{
-  "query": "machine learning",
-  "did": "did:plc:abc123",
-  "rkey": "3abc",
-  "limit": 100,
-  "distinct": true,
-  "cluster": true,
-  "include_embeddings": true
-}
-```
-
-| Field                | Type   | Default | Description |
-|----------------------|--------|---------|-------------|
-| `query`              | string | —       | Search query text (exclusive with `rkey`) |
-| `did`                | string | —       | Scope search to a specific account (AT Protocol DID) |
-| `rkey`               | string | —       | Use this post's embedding as query (requires `did`, exclusive with `query`) |
-| `limit`              | int    | 400/1200 | Max results. Global: max 400. DID-scoped: max 1200 |
-| `distinct`           | bool   | true    | One result per account |
-| `cluster`            | bool   | false   | Enable UMAP+HDBSCAN clustering with c-TF-IDF topic extraction |
-| `include_embeddings` | bool   | false   | Include per-result cluster embeddings (128d non-bearer, 768d bearer) |
-
-**Search modes:** At least one of `query`, `did`, or `rkey` is required.
-
-| Mode | Fields | Behavior |
-|------|--------|----------|
-| Global search | `query` | Semantic search across all posts (max 400) |
-| Browse account | `did` | Newest posts, always clustered (max 1200) |
-| Search in account | `did` + `query` | Semantic search within account's posts (max 1200) |
-| Similar posts | `did` + `rkey` | Use post's embedding as query for global search |
-
-**Response:**
-```json
-{
-  "results": [
-    {
-      "did": "did:plc:abc123",
-      "handle": "user.bsky.social",
-      "collection": "app.bsky.feed.post",
-      "rkey": "3abc",
-      "text": "Post text...",
-      "score": -0.82,
-      "created_at": "2025-01-15T10:30:00Z",
-      "detected_lang": "en",
-      "cluster_id": 0,
-      "topics": ["topic1", "topic2"],
-      "embedding": [0.12, -0.34, ...]
-    }
-  ],
-  "clusters": [
-    {
-      "id": 0,
-      "size": 15,
-      "topics": ["topic1", "topic2", "topic3"],
-      "result_indices": [0, 3, 7, 12]
-    }
-  ]
-}
-```
-
-`clusters` and per-result `cluster_id`/`topics` are only present when `cluster: true`. `embedding` only present when `include_embeddings: true`. Score is negative inner product (lower = more similar).
-
-## Firehose protocol
-
-Zstd-compressed NDJSON over HTTP. Each line is a columnar batch:
-
-```json
-{"did":["did:plc:abc","did:plc:xyz"],"col":["app.bsky.feed.post","app.bsky.actor.profile"],"rkey":["3abc","self"],"lang":["en","de"],"c":[[128 floats],[128 floats]],"r":[[128 floats],[128 floats]]}
-```
-
-| Field  | Description |
-|--------|-------------|
-| `did`  | AT Protocol DID (e.g. `did:plc:abc123`) |
-| `col`  | AT Protocol collection NSID (e.g. `app.bsky.feed.post`, `app.bsky.actor.profile`) |
-| `rkey` | Record key within the collection |
-| `lang` | Detected language (`en`, `de`) |
-| `c`    | Cluster embedding (prefix `"task: clustering \| query: "`) |
-| `r`    | Retrieval embedding (prefix `"title: none \| text: "`) |
+### API documentation
 
-Empty batches (`[]`) are heartbeats sent every 10s.
+Full API spec (search endpoints, firehose protocol, schemas): **[OpenAPI 3.1](https://divepool.social/api/v1/openapi.json)**
 
 ## Verify embeddings
 
diff --git a/experiments/requirements.txt b/experiments/requirements.txt
new file mode 100644
index 0000000..f107310
--- /dev/null
+++ b/experiments/requirements.txt
@@ -0,0 +1,5 @@
+numpy>=1.26.0
+zstandard>=0.20.0
+scikit-learn>=1.3.0
+umap-learn>=0.5.0
+hdbscan>=0.8.33