
AG2
AG2AI (ex-AutoGen creators) · framework · Any industry
BGrade
67Score
±1095% range
#120Rank of 1136
0%From fleets
FR-CAT-00899Catalog 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
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?
OpenTelemetry spans with gen_ai.usage.input_tokens/output_tokens/cost
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 · Python SDK emitting OTel traces you can export anywhere; MCP not confirmed in docs
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: None · Per-agent keys: One shared key · Audit log: None · Revoke: None · SSO: None
Desk research 0 · 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 get the data
Desk research 100 · 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 research73%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
Spend capNone
Per-agent keysOne shared key
Audit logNone
RevokeNone
SSONone
PricesPublished
AG2 is an Apache-2.0 open-source Python framework with no hosted tier; it reads provider keys from env vars and provides no buyer controls itself. Spend, keys, logging and identity depend on the LLM provider and infrastructure you deploy on.
History
11-12 B 6711-13 B 6711-14 B 6711-15 B 6711-16 B 6711-17 B 6711-18 B 6711-19 B 67
Rated since 2026-10-02. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-02.Run agents on AG2?
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.