Registry › Compare › Guardrails AI vs open-kritt

Guardrails AI vs open-kritt

Guardrails AI leads on trust: 76.7/100 (Grade B) against 57.7/100 (Grade C), a 19.0-point gap. Guardrails AI leads on supply-chain integrity and adoption, and rests on broader evidence; open-kritt leads on maintenance.

B Guardrails AI 76.7

Adding guardrails to large language models.

guardrails-ai/guardrails · #190 overall · #3 Security & Guardrails · coverage A (4/5)

Choose Guardrails AI if supply-chain integrity and adoption matter most.

+11.5Safety / Integrity: 100% of recent commits signed, against 51%
+7.3Adoption: 7.5k GitHub stars against 2.2k
+7.2Identity / Provenance: package provenance attested, against none
+1.0Transparency: OSSF Scorecard 6.0 against 4.8

C open-kritt 57.7

Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.

Kritt-ai/open-kritt · #704 overall · #8 Security & Guardrails · coverage C (2/5)

Choose open-kritt if maintenance matters most.

+6.0Maintenance: last push today, against 3d ago

Where they differ

20.0

Safety / IntegrityGuardrails AI +11.5

8.5

18.0

Identity / ProvenanceGuardrails AI +7.2

10.8

13.6

TransparencyGuardrails AI +1.0

12.6

11.8

Maintenanceopen-kritt +6.0

17.8

15.3

AdoptionGuardrails AI +7.3

8.0

-2.0

Runtime calibrationopen-kritt +2.0

+0.0

Full evidence table

An independent, evidence-based trust comparison of Guardrails AI and open-kritt, two Security & Guardrails projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal	Guardrails AIguardrails-ai/guardrails	open-krittKritt-ai/open-kritt
HVTrust score	76.7	57.7
Evidence grade	B	C
Coverage grade	A	C
Overall rank	#190	#704
Rank in Security & Guardrails	#3	#8
GitHub stars	7.5k	2.2k
Last updated	3d ago	today
Build provenance	Yes	No
OSSF Scorecard	6.0 / 10	4.8 / 10
License	Apache-2.0	AGPL-3.0
Downloads	31k/wk	—
Trust dimensions (points earned)
Safety / integrity / 25	20.0	8.5
Identity & provenance / 18	18.0	10.8
Transparency / 17	13.6	12.6
Maintenance / 20	11.8	17.8
Adoption / 20	15.3	8.0
Runtime capability surface (full matrix)
MCP server	—	—
External providers	3 — Anthropic, Multi-provider (LiteLLM), OpenAI	—
Requires API keys	Yes	No
Plugin surface	—	—
Provenance drift	Unknown	—

Open in the live compare tool → Guardrails AI profile open-kritt profile More Security & Guardrails →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.3 →