Granite Guardian
IBM model family that judges whether LLM inputs and outputs meet criteria such as jailbreak, harm and hallucination checks.
Observability tool by IBM
Get started
Setup steps are in the repository. Website · Repository
About
Use cases: security-scanning, llm-evaluation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Category
- Guardrails · safety model
- Self-host
- Yesraw.githubusercontent.com
Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.
Details
- License
- License unknown
- Repository
- github.com/ibm-granite/granite-guardian
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- README
More from IBM
- 0.742score
ContextForge MCP Gateway
IBM
Open source registry and proxy that federates MCP, A2A and REST/gRPC APIs under central governance.
InfrastructureAFreshness: A★ 4.7Kgateway - 0.636score
IBM watsonx Orchestrate ADK
IBM
Python library and CLI for building agents that run on IBM watsonx Orchestrate, with a local Developer Edition for testing.
HarnessAFreshness: A★ 177↓ 24.8K/wk - 0.577score
Granite 4.0 Micro
IBM
Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models.
ModelAFreshness: A$0.017 / $0.112131K ctxOpen weights - 0.577score
Granite 4.2 8B
IBM
Granite 4.2 8B is a dense reasoning model from IBM.
ModelAFreshness: A$0.06 / $0.25131K ctxOpen weights - 0.450score
IBM watsonx Orchestrate
IBM
IBM platform for building, orchestrating and governing AI agents from one control plane, with a 30-day trial and fixed monthly plans
BuilderCFreshness: C
Cite this page
Granite Guardian. Agent Mart. https://agentmart.dev/observability/granite-guardian (last updated 2026-10-24)