A1 ratingsStanford UniversitySTORM

STORM

Stanford University · framework · Any industry
C
CGrade
43Score
±995% range
#549Rank of 1134
0%From fleets
FR-CAT-01098Catalog no.

The six pillars

Each bar is the score; the bracket is its 95% range.

Can you see what it costs?

Only through a gateway you run · prices published
58±17
Desk research 60 · 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?

No usage API found
50±17
Desk research 50 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.

Can you tie cost to one agent?

Nothing a buyer can read
10±17
Desk research 0 · 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 · Python library using litellm for any model provider; no MCP support mentioned.
66±17
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?

50±59
Not known yet. Sits at a neutral 50 with a wide range until facts arrive · 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
10±17
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 research72%Neutral starting point28%

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

Being researched now. Spend caps, per-agent keys, audit logs, revoking and SSO land here as the research writes them.

History

11-11 C 4311-12 C 4311-13 C 4311-14 C 4311-15 C 4311-16 C 4311-17 C 4311-18 C 43
First rated 2026-10-02 at 42 (C). Now 43. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-02.

Every fact, with its rung and source

Each fact stands on its own source and its own rung of the evidence ladder (Rule N2.1). Verified Observed Declared Inferred. The weakest fact in a pillar sets its weight.

FactValueRungCheckedSources
How a buyer sees cost
Cost
Only through a gateway you run Declared
high confidence
2026-10-13
1 earlier
[1][2] Correct
Prices published
Cost
Yes Declared
high confidence
2026-10-13 [1][2] Correct
Usage API
Usage
None found Declared
high confidence
2026-10-13
1 earlier
[1][2] Correct
Cost per agent
Per agent
None found Declared
high confidence
2026-10-13
1 earlier
[1][2] Correct
How an agent reports out
Reports out
SDK Declared
high confidence
2026-10-13
1 earlier
[1][2] Correct
Small plans get the data
Small plans
No Declared
high confidence
2026-10-13
1 earlier
[1][2] Correct

Prices · Free (MIT, pip install knowledge-storm); hosted research preview at storm.genie.stanford.edu is free

Notes · Academic open-source research/article-writing system; all spend is at the LLM and search providers you configure. Repo not archived; latest news Jan 2025 (v1.1.0).

Scored with the rubric for Open-source frameworks (Rule N7.1). Each pillar blends a neutral 50, desk facts weighted by rung, and independent fleets. A1 is 85+ with fleet proof, A 70, B 55, C 40, D 25, E below. Part N of the Rules

Run agents on STORM?

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.