FollowAgents Insights

What 1,000+ independent AI agent reviews actually show

Every number on this page is computed live from the 1848 agents that have completed a FollowAgents Review (FARS) — not a survey, not a vendor claim, and not cached from the day this page launched.

As of 2026-10-19Recomputed on every page load from the live catalog

How the catalog scores

FARS-2.1 scores only what a source-code read can settle — no live testing, no vendor input. A low share in the top bands is a statement about the ecosystem's documentation and safety practices, not about this review's harshness (see the review method for exactly what closes the gap).

50.3%

Excellent

1467.9%

Good

44123.9%

Some gaps

125668.0%

Major gaps

Where agents most often fall short

Share of 1848 FARS-2.1-reviewed agents whose trust criterion scored 0 — absent, or contradicted by the evidence, exactly as it does on a single agent's own profile page.

rollback or recovery path

37.6%695

confirmation before acting

30.0%554

dependency security

19.3%357

sensitive-data handling

18.5%342

least-privilege scoping

15.4%284

data-flow disclosure

15.3%282

disclosed external effects

14.7%272

verifiable attribution

12.8%236

What these agents ask of your machine

Share of reviewed agents that require each capability.

Shell / CLI

94.8%1752

Network access

90.2%1667

Local filesystem

86.7%1603

MCP Server

32.3%597

License coverage

Share of reviewed agents under each declared license.

MIT

47.8%883

Apache-2.0

28.2%521

No license declared

15.9%294

AGPL-3.0

4.7%87

GPL-3.0

2.2%41

BSD-3-Clause

0.3%5

Other licenses

0.9%17

By category

Average FARS score and reviewed count per category.

Category	Reviewed	Avg. FARS score
Uncategorized	2	68.0
Dev & Engineering	1103	53.4
Productivity & Collaboration	176	52.4
Automation & Ops	314	51.9
Writing & Content	28	51.7
Data & Analysis	181	46.6
Design & Frontend	44	44.4

How these numbers are produced

Every figure above comes directly from stored FARS assessments — the same structured review shown on each agent's own profile page, aggregated rather than rewritten. Nothing here is estimated, surveyed, or carried over from a previous snapshot.