Human journey
Problem
My agent needs tools, but the landscape is risky.
Guide
Rhumb shows the safest route.
Action
I research and compare with the public Index. Resolve is coming soon.
Reward
I get a more capable, trustworthy agent.
surface: homepage
purpose: public Index research only
first_action: search Index
index_definition: public discovery and comparison
available_now: research capabilities, providers, AN Score, evidence, freshness, credential mode, estimates, and failure modes
temporarily_unavailable: Resolve, API, MCP, account access, billing
execution_instruction: do not execute requests; return public Index research and evidence
machine_entrypoints: /llms.txt, /agent-capabilities.json, /.well-known/agent-capabilities.json; MCP and REST API are temporarily unavailable
current_public_truth: Discovery breadth: 999 scored services and 435 capability definitions. Current runtime-callable surface: 28 callable providers, strongest today for research, extraction, generation, and narrow enrichment.
THE NAVIGATION LAYER FOR AGENT TOOLS
From task to trusted tool research.
Rhumb provides public research for AI agents: Index shows what can be trusted across capabilities, providers, and evidence.
Resolve, API and MCP access, account access, and billing are temporarily unavailable. Public Index research remains available.
Public discovery and comparison are available now. Resolve, API and MCP access are coming soon.
Read-only route trace Index → Evidence → Availability → Research
- 01 · Task Intent received
Research Acme and summarize the current facts.
A human gives the agent an outcome, not a provider decision.
- 02 · Index Compare routes
Search capability: company.research
Index is discovery and comparison: services, capabilities, AN Score, evidence, freshness, and failure modes.
- 03 · Evidence AN 91 · Fresh
Inspect trust before action.
Check score, proof, freshness, credentials, estimate, and failure modes before the agent acts.
- 04 · Resolve Unavailable
Resolve is coming soon.
Resolve, API and MCP access, account access, and billing are temporarily unavailable.
- 05 · Outcome Research only
Return public research.
Return the Index evidence, freshness, and failure modes. Do not execute requests.
999 services scored
435 capabilities mapped
28 callable providers
API + MCP governed surfaces
Reliable bearing
Two journeys. One reliable bearing.
Rhumb helps both the human and the agent become more capable.
Agent journey
Problem
I have a task but no reliable route.
Guide
Rhumb maps capabilities and evidence.
Action
I inspect Index evidence and return research; live execution is temporarily unavailable.
Reward
I become the hero for my human.
Product model
Find. Trust. Research.
Use the public Index to research the right service.
01 · Index
Find with Index
Search the Index for capabilities by task or provider.
company.researchweb.searchmath.solve
Explore Index → 02 · AN Score
Trust with AN Score
Evaluate with evidence-backed confidence.
91 / 100
See methodology → 03 · Resolve
Resolve is coming soon
Resolve, API and MCP access, account access, and billing are temporarily unavailable.
Resolve coming soon →Evidence ledger
Why agents can explain the route.
Every good call has a source trail, a freshness boundary, and a visible stop condition.
Evidence tiers Clear quality signals you can trust.
Freshness Know how current the data is.
Failure modes See what can go wrong.
Dispute path Open issues. We listen and improve.
Evidence ledger sample
SourceTypeFreshnessAN Score
Acme Investor RelationsWeb2h ago95
CrunchbaseAPI5h ago90
Company WebsiteWeb6h ago88
News APIAPI12h ago82
Programmatic access
API and MCP access are coming soon.
Resolve, API and MCP execution, account access, and billing are temporarily unavailable. Public discovery and comparison remain available through the Index.
Browse the Index