search for agents
exact text, regex, filters and vectors built on object storage: fast when warm, cheap when idle, one call to start
or app
cache
storage (S3)
Cold queries also pass on their object-storage reads ($0.50 per million reads; a warm query makes none). Idle namespaces cost only their bytes.
Memory for every agent
A namespace per agent, user or task, created on the fly. Thousands of them sit idle at the price of their bytes and answer again in a round trip or two.
Docs →Exact lookups, not guesses
Order numbers, error codes, function names, emails: literal and regex search that never misses a match, with exact counts and metadata filters.
Docs →Vectors on the same data
Store an embedding with each document and search by meaning, alone or narrowed by text and filters in the same query. One copy, one bill.
Docs →One API for every kind of lookup
Every answer says whether the namespace was warm or cold and how many object-storage reads it made, so you always know what a query cost.
NS=https://skimmerdb.com/api/namespaces/support
# upsert: text, metadata, an embedding (optional)
curl $NS/docs -H "Authorization: Bearer $KEY" -d '{
"docs": [{"id": "t-1",
"text": "Refund requested for order ACME-1042",
"meta": {"status": "open", "priority": 3},
"vector": [0.12, -0.03, ...]}]}'# exact text (or "regex": true), filtered, newest first curl $NS/search -H "Authorization: Bearer $KEY" -d '{ "q": "acme-1042", "filter": {"status": "open"}}' # nearest neighbours, narrowed by text and a filter curl $NS/search -H "Authorization: Bearer $KEY" -d '{ "vector": [0.12, -0.03, ...], "q": "refund", "filter": {"priority": {"gte": 2}}, "limit": 10}'
Built for agents
skimmerdb speaks MCP with OAuth. The user signs in and picks which namespaces the agent may use and whether it can write. Each connection gets its own key, revocable any time.
- Scoped keys. Read, write or admin; optionally only some namespaces, like
agent-7-*. - Isolation. Another tenant's namespace looks exactly like one that doesn't exist.
- Caps per key. Request rate, queries and writes per billing period.
# Claude Code claude mcp add --transport http \ skimmerdb https://skimmerdb.com/mcp # Claude, ChatGPT, Cursor, Codex: a remote MCP server https://skimmerdb.com/mcp
| Limit | Current |
|---|---|
| Namespaces | Unlimited |
| Write throughput (one server, measured) | 50k+ docs/s to S3 |
| Time to searchable (measured) | ~33 ms |
| Vector search recall@10 (defaults) | 0.97 |
| Vector queries / s (one server, measured) | 5,600 |
| Vector dimensions | 1 to 2,048 |
| Document text | 2 MB |
| Metadata per document | 16 KB |
| Documents per write | 10,000 (64 MB) |
| Results per query | 1,000 |
| Regex | RE2, linear time |