A1 ratingsLangChainLangGraph

LangGraph
LangChain · framework · Any industry
BGrade
69Score
±1095% range
#88Rank of 1134
0%From fleets
FR-CAT-00891Catalog no.
The six pillars
Each bar is the score; the bracket is its 95% range.
Can you see what it costs?
Vendor cost API · prices published
Desk research 100 · counts for 25% · A cost API you can call scores highest; an admin console or cloud billing export next; a card statement or emailed invoice is all some products leave you. Published prices add to it.
Can you see how much it's used?
Granular billable usage: GET /api/v1/orgs/current/billing/granular-usage (kind=traces or langsmith_deployments)
Desk research 100 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.
Can you tie cost to one agent?
By project
Desk research 70 · counts for 15% · Exact (one key or project per agent) beats by-project, by-workspace or by-user.
Can an agent on it report out?
SDK
Desk research 70 · counts for 15% · A remote MCP connector scores highest, then a local MCP server, an SDK, an API or a workflow step; copy-and-paste lowest. Any open standard counts, not just FleetRegistry.
Can you control spend and access?
Spend cap: Hard cap · Per-agent keys: Scoped · Audit log: By API · Revoke: Console only · SSO: SSO only
Desk research 93 · counts for 20% · Hard spend caps (30%), scoped per-agent keys (25%), an audit log you can read by API (20%), revoking by API (15%), SSO with SCIM (10%).
Does it work on small plans?
Small plans don't get the data
Desk research 0 · counts for 10% · Whether the plan a person or small business buys gets the cost and usage data at all.
Where the evidence comes from
Independent fleets0%Desk research74%Neutral starting point26%
Once three independent fleets report on a pillar, desk research counts for at most a third of it. FleetRegistry's own fleets never count.
Controls on record
Spend capHard cap
Per-agent keysScoped
Audit logBy API
RevokeConsole only
SSOSSO only
PricesPublished
Controls are LangSmith's (the paid platform for LangGraph): workspace/project/user monthly trace-count limits (approximate enforcement); admin-created service keys scoped to workspaces, optional expiry, deactivate/delete; audit logs via API on Enterprise only; Google/GitHub SSO on all plans, custom SSO on Enterprise. SCIM not confirmed.
History
11-11 B 6911-12 B 6911-13 B 6911-14 B 6911-15 B 6911-16 B 6911-17 B 6911-18 B 69
First rated 2026-10-02 at 62 (B). Now 69. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-02.Run agents on LangGraph?
Give each one a permanent number, a named person who answers for it, and a record of what it can touch and what it costs. Free.