Library
87,246 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Phocinae-Largha-150M-v1
Modelstext classification model by Phocinae
Phocinae/Phocinae-Largha-150M-v1 -
guardrails
MCP serversAI Agent Guardrails MCP server - security layer
guardrails-mcp-server@1.0.1 -
awesome-jev
Agents & frameworksA curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.
git clone https://github.com/cobanov/awesome-jev.git -
traced-claude-format-guard
MCP serversTraced Claude Format Guard
-
guardian-mcp-server
MCP serversGuardian Open Platform: search and retrieve full article text from The Guardian archive.
@cyanheads/guardian-mcp-server@0.3.0 -
Guard Core
MCP serversGuard Core security MCP: SecurityConfig validation, docs search, live threat detection.
guard-core-mcp@1.7.0 -
ai-guardrails
MCP serversCloudflare Workers MCP server: ai-guardrails
-
The Guardian
MCP serversThe Guardian Open Platform MCP.
@pipeworx/mcp-the-guardian@0.2.1 -
agent-guard
MCP serversConstitutional guardrails and loop detection for AI agents
agent-guard-mcp@0.1.3 -
The Guardian
Public APIsAccess all the content the Guardian creates, categorised by tags and section
-
Execute deepvoice-guard-mcp
MCP serversPremium agentic endpoint for deepvoice-guard-mcp.
-
guardian-mcp
MCP serversNews and article search from The Guardian. No key required.
@mrfentmen/guardian-mcp@1.0.0 -
joey-1
Modelstext classification model by baselabs · transformers
baselabs/joey-1 -
GuardMarket
MCP serversMCP client for commerce/data skills; requires a configured GuardMarket backend.
https://github.com/zma-petterzhang/guardmarket/releases/download/v0.3.0/guardmarket-mcp-0.3.0.mcpb -
OpenWorkProof
MCP serversVerifiable agent evidence; opt-in Codex guard and reference SOC alert review.
openworkproof@1.6.1 -
chainloop
Agents & frameworksAgentic SDLC infrastructure. Define guardrails. Collect signals. Enforce continuously. Signed records of what your AI coding agents and CI/CD pipelines did, checked against policies as code, with the loop closed in CI/CD. AI sessions, SBOMs, VEX, SARIF and SLSA provenance, built on Sigstore and in-toto. Apache 2.0.
git clone https://github.com/chainloop-dev/chainloop.git -
AI Guard
MCP serversGuardrails for AI-written JS/TS: scans, weakened-test checks, package checks, verify before done.
eslint-plugin-ai-guard@1.4.7 -
javelin-guardrails-mcp-server
MCP serversAn MCP server that provides Javelin Standalone Guardrails
-
guard
MCP serversLocal-first architecture guardrails and project context for JS/TS AI coding agents.
@codapult/guard@0.14.1 -
Vizier Guard
MCP serversDeterministic authorization and security guard for AI agent actions with signed receipts.
vizier-guard@0.3.4 -
guardian-mcp
MCP serversRoutes agent tool calls through Guardian for ALLOW/ASK/DENY before execution.
@odingard/guardian-mcp@0.5.0 -
guardfile
MCP serversExtract a repo's guardrails — DCO, CLA, changesets, sign-off — into one checkable report.
@reneturcios/guardfile@0.1.0 -
CoWork-OS
MCP serversRent the model. Own everything else. Free, open-source AI app for real work.
git clone https://github.com/CoWork-OS/CoWork-OS.git -
Tracekit
Agents & frameworksTamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
git clone https://github.com/Cygnux-Labs/Tracekit.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.