Search was built for finite attention. Agents have infinite attention. Synorb observes 10,000+ sources and publishes Briefs, Signals, and Records—with stable IDs and provenance.
API + MCP connectors · Deterministic formats · 1,000+ streams
On January 17, 2026, the Board of Directors of NVIDIA Corporation (the “Company”) appointed Michael L. Thompson as Executive Vice President, AI Infrastructure, effective February 1, 2026.
Mr. Thompson, age 48, has served as Senior Vice President of Data Center Engineering since March 2022. Prior to joining NVIDIA, Mr. Thompson served as Vice President of Engineering at Google Cloud from 2018 to 2022.
In connection with his appointment, Mr. Thompson will receive a base salary of $750,000, an annual target bonus opportunity of 150% of his base salary, and a restricted stock unit award with a grant date fair value of approximately $12,000,000...
At Stripe, we process millions of API requests per second across 46 countries. Last quarter, our infrastructure team deployed inference models at the edge — moving fraud detection and payment routing closer to the merchant.
The results exceeded our projections. Median API response times dropped by 40%, with the largest gains in fraud detection where round-trips to centralized GPU clusters had been the primary bottleneck.
This post details the architecture, the tradeoffs we navigated, and what we learned about deploying ML models at the edge of a global payments network.
Why the edge? Every millisecond matters in payments. When a customer taps their card at a terminal in Dublin, the fraud check previously had to round-trip to us-east-1 — adding 80-120ms of pure network latency. Multiply that by billions of transactions and you start to see why we were motivated.
Our approach was to deploy lightweight inference models to 14 edge locations globally, co-located with our existing API infrastructure. The models run on custom ONNX runtimes optimized for CPU inference — no GPUs required at the edge.
The fraud detection model was the first candidate. It evaluates 47 features per transaction: merchant category, velocity patterns, device fingerprint, geographic anomaly scores, and behavioral signals from the session. Previously this ran on a centralized cluster in Virginia.
After six weeks of shadow testing, we cut over Dublin, London, and Singapore. The p50 latency for fraud scoring dropped from 145ms to 12ms. The p99 dropped from 380ms to 34ms. We were stunned.
A new study from the Federal Reserve Bank of Cleveland reveals a significant divergence in short-term inflation expectations between consumers and professional forecasters in 2025.
While professional forecasters' expectations remained anchored near the Federal Reserve's 2 percent inflation target, consumer expectations deteriorated notably, moving further from the target.
This weakening in consumer expectations was linked to increased disagreement among consumers and growing distance from the Fed's goal. Surprisingly, the divergence correlated with self-reported political affiliations, with Democrat and Independent-leaning consumers reporting higher expectations...
Get the complete manifest schema reference and 1,000 free manifests/month.
Search is a noisy prior from a world built for audiences with finite attention hours. Every page and result was shaped by what humans would click, read, and share. The ceiling was human time. The incentive was human attention.
The promise of AI isn't better search. It's surfacing insights you'd never have searched for. Reasoning systems have infinite attention hours—they ingest continuously, maintain state, and reason between state changes. The paradigm shifts from retrieval to receival. Synorb builds for that shift.
Read the full thesis →Every stream. Every format. REST, MCP, webhooks, S3. Build custom digests from any combination of streams, tags, and topics.
Free – $450+/mo
For developers building intelligent systems.
Everything we produce. The moment we write it.
Pricing upon request
For platforms that need the complete feed.
No signup form. Your agent gets credentials and starts querying immediately.
1. Get free credentials
curl -s https://synorb.ai/connect
Returns: api_key, api_secret, mcp_token
1,000 manifests/mo. No signup form.
Secret shown once — save it.
2. Connect your coding assistant
Claude Code
claude mcp add synorb \
--transport sse URL
Cursor / Windsurf
{ "mcpServers": {
"synorb": { "url": "..." }
} }
Codex / Copilot
curl -s synorb.ai/connect?format=md
Lovable / Bolt / v0
curl -s synorb.ai/connect?format=md
Or use the REST API directly
curl -H "api-key: YOUR_API_KEY" -H "secret: YOUR_API_SECRET" https://api.synorb.ai/streams?page_size=5
Full API reference ·
agents.md ·
llms.txt ·
openapi.json
Give your agents the context they deserve.
Get Credentials