OMNI Datastream
Raw filings, sharpened.
OMNI Datastream turns SEC and public-market data into compact, provenance-first primitives that work cleanly in APIs, SDKs, CLIs, MCP tools, and downstream investor agents.
Why it exists
Public-market data should not arrive as a pile of HTML, XML, and crossed fingers.
Datastream ingests, normalizes, enriches, filters, and scores the material that OMNI Agent and OMNI Pulse depend on. It is the grounding layer for the whole platform and a first-class product for developers that want source-backed market intelligence without rebuilding the same adapters.
- Canonical entity resolution keeps tickers, filers, insiders, managers, and security identifiers from drifting apart.
- Filing and section workflows stay small enough for agents to use repeatedly.
- Freshness, provenance, and traceability stay visible on the public contract instead of hiding in internal logs.
What it does
A better substrate for research and automation.
Canonical entity graph
Resolve issuers, filers, managers, insiders, funds, and aliases across ticker, CIK, FIGI, ISIN, and CUSIP without rebuilding identity logic in every client.
Filing search that fits agents
Search by ticker, form, accession, date range, and sort order with compact metadata and predictable pagination.
Section and item extraction
Pull the filing slices that matter instead of dragging an entire document through every workflow.
Statements and facts
Use normalized statements, facts, bundles, segmented revenues, and share-float reads with provenance attached.
Ownership and insider reads
Track 13F, insider, beneficial ownership, and ticker-holder workflows from a single data layer.
Fund and governance reads
Pull N-PORT holdings, board composition, and enforcement-event surfaces from the same public contract family.
Historical depth
Keep hot-path reads fast while holding a deeper historical corpus behind the same object model.
Freshness metadata
Every serious downstream system needs to know how fresh the answer is. OMNI makes that explicit.
Parser and provenance metadata
Materialization version, source URLs, accession references, request IDs, and trace references stay close to the payload.
Filing-page traceability
Go from a filing-derived number to the correct filing document and page instead of hand-hunting through PDFs.
Rights-safe market utilities
Market calendars, approved index rosters, and derived public-market utilities live alongside SEC data.
Hosted MCP
The same primitives are exposed to coding agents without forcing a custom wrapper first.
API, SDK, and CLI parity
The platform is built so the docs, reference, SDKs, and programmatic surfaces reinforce each other.
Proof
Smaller payloads. Faster answers. Better agent fit.
Datastream is built to win on the workflows investor agents actually run all day. It is also built to show its work instead of asking you to trust a black box, with benchmark claims kept scoped to the dated suite.
latency
Entity resolve p50 latency
Resolve a public issuer by ticker or identifier with canonical metadata and provenance.
| Provider | Value | Notes |
|---|---|---|
| OMNI | 62.38 ms | — |
| sec-api.io | 231.46 ms | — |
latency
Filing search p50 latency
Search recent SEC filings with agent-ready metadata and a compact response contract.
| Provider | Value | Notes |
|---|---|---|
| OMNI | 61.38 ms | — |
| sec-api.io | 265.23 ms | — |
latency
Structured facts p50 latency
Return normalized financial facts instead of a giant filing payload.
| Provider | Value | Notes |
|---|---|---|
| OMNI | 61.87 ms | — |
| sec-api.io | 400.53 ms | — |
payload
Structured facts payload size
Average bytes returned for the structured-facts workflow in the dated benchmark suite.
| Provider | Value | Notes |
|---|---|---|
| OMNI | 1,522 bytes | — |
| sec-api.io | 1,426,498 bytes | — |
Build
Give your agent a better place to start.
Use the docs to ship a workflow, the API reference to wire an endpoint, or the SDKs to get productive faster.