A1 ratingsAll Hands AIOpenHands

OpenHands

All Hands AI · agent · Any industry
B
BGrade
60Score
±1495% range
≈#249Rank of 1134
0%From fleets
FR-CAT-00847Catalog 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
57±27
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?

OpenHands Cloud GET /api/organizations/{org_id}/conversations/usage-stats (estimated_spend, by day/user/model/agent; Admin/Owner) and GET /api/organizations/{org_id}/members/financial (spend per member)
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?

SDK · Cloud Agent SDK and MCP support; self-hosted so route model spend through a gateway
64±27
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: Not scoped · Revoke: Console only · SSO: SSO only
70±27
Desk research 78 · 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 research61%Neutral starting point39%

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 keysNot scoped
Audit logNot known
RevokeConsole only
SSOSSO only
PricesPublished

OpenHands Cloud orgs: alerts at 80/90/100% of org budget and new conversations 'may be blocked' at 100% until the next cycle or a raise; per-member (lifetime) budgets. API keys are named, unscoped (optional expires_at/not_before) and deleted in Settings > API Keys. Teams ($499/mo, public) lists SSO/SAML, RBAC and budgeting controls; SAML SSO docs cover OpenHands Enterprise. No SCIM or audit-log docs. Self-hosted open source has none of these controls.

History

11-11 B 6011-12 B 6011-13 B 6011-14 B 6011-15 B 6011-16 B 6011-17 B 6011-18 B 60
First rated 2026-10-02 at 45 (C). Now 60. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-25.

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
medium confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Prices published
Cost
Yes Declared
medium confidence
2026-10-25
2 earlier
[1][2][3][4] Correct
Usage API
Usage
OpenHands Cloud GET /api/organizations/{org_id}/conversations/usage-stats (estimated_spend, by day/user/model/agent; Admin/Owner) and GET /api/organizations/{org_id}/members/financial (spend per member) Declared
medium confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Cost per agent
Per agent
partial Declared
medium confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
How an agent reports out
Reports out
SDK Declared
medium confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Per-agent keys
Controls
Not scoped Declared
medium confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Revoke access
Controls
Console only Declared
medium confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Spend cap
Controls
Hard cap Declared
medium confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
SSO
Controls
SSO only Declared
medium confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Small plans get the data
Small plans
No Declared
medium confidence
2026-10-25
1 earlier
[1][2][3][4] Correct

Prices · Agent Canvas open source (MIT) free, own LLM key; Teams $499/mo up to 10 users + $50/mo per extra seat (5,000 sessions/mo); Enterprise custom

Notes · Self-hosted Agent Canvas cost is whatever LLM you plug in, so route model spend through a gateway. Pricing page now lists Agent Canvas (free), Teams ($499/mo, 30-day trial) and Enterprise (custom); the old 'Individual SaaS free, 10 daily conversations, LLM at cost' tier is no longer listed. OpenHands Cloud org usage-stats API returns estimated spend with per-agent (agent_name) cost and per-model cost, hence partial attribution; no invoice-grade cost API documented.

Scored with the rubric for Agents and agent platforms (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

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

Run agents on OpenHands?

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.