A1 ratingsLiveKitLiveKit Agents

LiveKit Agents

LiveKit · framework · Any industry Not enough facts yet
-
-Grade
-Score
±2095% range
-Rank of 1134
0%From fleets
FR-CAT-00426Catalog no.
Researched, but under 60% of the method could be measured from public sources, and a grade needs 60%. Vendors can send the missing facts.

The six pillars

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

Can you see what it costs?

Admin or analytics API · prices published
69±27
Desk research 76 · 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?

Analytics API (Scale plan or higher): per-session billable connectionMinutes and bandwidth
86±27
Desk research 100 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.

Can you tie cost to one agent?

partial
50±59
Not known yet. Sits at a neutral 50 with a wide range until facts arrive · 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?

50±59
Not known yet. Sits at a neutral 50 with a wide range until facts arrive · 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: None · Per-agent keys: Not scoped · Revoke: Console only · SSO: SSO only
43±27
Desk research 41 · 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
14±27
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 research39%Neutral starting point61%

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 capNone
Per-agent keysNot scoped
Audit logNot known
RevokeConsole only
SSOSSO only
PricesPublished

Only the free Build plan hard-caps at its allowance; paid plans bill overage with no documented spending cap. SSO Enterprise-only; no SCIM or audit log found. The OSS framework itself provides none of these.

History

11-11 - 11-12 - 11-13 - 11-14 - 11-15 - 11-16 - 11-17 - 11-18 -
Not saved yet. 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
Admin or analytics API Declared
medium confidence
2026-10-08 [1][2][3][4] Correct
Prices published
Cost
Yes Declared
medium confidence
2026-10-08
2 earlier
[1][2][3] Correct
Usage API
Usage
Analytics API (Scale plan or higher): per-session billable connectionMinutes and bandwidth Declared
medium confidence
2026-10-08 [1][2][3][4] Correct
Cost per agent
Per agent
partial Declared
medium confidence
2026-10-08 [1][2][3][4] Correct
Per-agent keys
Controls
Not scoped Declared
medium confidence
2026-10-08
2 earlier
[1][2][3] Correct
Revoke access
Controls
Console only Declared
medium confidence
2026-10-08
2 earlier
[1][2][3] Correct
Spend cap
Controls
None Declared
medium confidence
2026-10-08
2 earlier
[1][2][3] Correct
SSO
Controls
SSO only Declared
medium confidence
2026-10-08
2 earlier
[1][2][3] Correct
Small plans get the data
Small plans
No Declared
medium confidence
2026-10-08 [1][2][3][4] Correct

Prices · Build $0/mo; Ship from $50/mo; Scale from $500/mo; Enterprise custom; agent session overage $0.01/min

Notes · LiveKit Cloud charges a plan fee plus metered usage, invoiced monthly per project. The Analytics API reports billable usage per session but no dollar costs. The OSS Agents framework is free.

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

Corrections

1 awaiting review. Accepted corrections are published in the corrections register with an FR-C number.

Run agents on LiveKit Agents?

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.