Integrations
Capability that plugs into the stack you already run.
Each integration attaches to a native seam in your framework, evaluates the decoded tool payload before it executes, and halts the call on a blocked verdict. That checkpoint is what lets your agents take actions you would otherwise keep off limits. No model to retrain, no rewrite of your agent.
Free tier — 1,000 custom-tool evaluations/month, BYOK, full Core IT Security bundle.
Official Integrations
Agents, MCP servers, models, and datasets.
Each integration verifies the Ed25519 receipt locally, so a blocked verdict is cryptographically provable at the point of enforcement — not just logged.
- latest v0.2.6 PythonAgent Templates
ramen foundry — view source on GitHub (opens in a new tab)
Open-source Python SDK for LangGraph agents. Wraps each tool in a pre-execution checkpoint and ships ready-made agents for shell access, databases, commercial lending, industrial automation, web research, resume screening, and authorization, eligibility and provenance gates.
pip install ramen-foundryRamenToolNode · DevboxShieldAgent · RamenSteerNodePython ≥ 3.10 · LangGraph - latest v0.1.4 TypeScriptTransport Proxy
mcp shield proxy — view source on GitHub (opens in a new tab)
A universal MCP stdio proxy that intercepts tools/call JSON-RPC messages at the transport layer and blocks malicious payloads before they reach the downstream server.
npx @ramen-ai/mcp-shield-proxy --helpDrop-in stdio proxy — no SDK changes requiredAny MCP server using stdio transport - PythonAgent Framework
LangChain — view source on GitHub (opens in a new tab)
A callback handler that intercepts agent tool calls pre-execution, evaluates the serialized tool definition and input, and halts the chain on a blocked verdict.
pip install -e plugins/langchain-pythonRamenSafetyCallbackHandler → raises RamenSafetyExceptionPython ≥ 3.10 · langchain-core ≥ 0.2 - PythonAgent Framework
PydanticAI — view source on GitHub (opens in a new tab)
Middleware that hooks PydanticAI's native args_validator, evaluating the tool name and resolved arguments before the tool body ever runs.
pip install -e plugins/pydantic-airamen_firewall() → @agent.tool(args_validator=…)Python ≥ 3.10 · pydantic-ai ≥ 0.0.14 - TypeScriptOrchestration
Microsoft AGT — view source on GitHub (opens in a new tab)
Adds a pre-execution checkpoint to any agent running under the Microsoft Agent Governance Toolkit, evaluating proposed tool calls and returning deterministic steering to the host agent on a block.
npm install @ramen-ai/agt-middlewareRamenFirewallBackend → GovernanceDenied@microsoft/agent-governance-sdk - PythonClassical ML / XGBoost
ramen mlflow guard — view source on GitHub (opens in a new tab)
Pre-inference checks for MLflow-served classical models, including XGBoost workflows. Evaluates feature values and available SHAP attributions for proxy bias before inference.
pip install ramen-mlflow-guardRamenGovernedModel → GovernanceDeniedExceptionPython ≥ 3.10 · MLflow ≥ 2.9 - PythonDataset Distillation
ramen data filter — view source on GitHub (opens in a new tab)
Dual-mode Pandas and CSV filtration for RAG ingestion and MLOps datasets, with strict exclusion or operator-controlled semantic imputation for blocked rows.
pip install ramen-data-filterfilter_dataframe() / filter_csv()Python ≥ 3.10 · Pandas 2.3.3
Client Libraries
Or build directly against the API.
Published to the public registries. Each client verifies the Ed25519 receipt locally, so every verdict can be verified locally.
- npm
@ramen-ai/node-core
The official Node.js client for policy evaluation, governed generation, and local V5 Ed25519 receipt verification. Requires Node.js 24 or newer.
npm install @ramen-ai/node-core - PyPI
ramen-ai-core
Agnostic Python HTTP client and Ed25519 V5 cryptographic verifier. The shared layer under the LangChain, PydanticAI and MLflow plugins. Requires Python ≥ 3.10.
pip install ramen-ai-core
Beyond the Agent Runtime
Checkpoints in the pipeline and at the attestation boundary.
GitHub Actions (opens in a new tab)
Scans pull request diffs for AI prompt modifications, evaluates the added text, and fails the build on a blocked verdict with a receipted PR comment.
cMCP + TRACE (opens in a new tab)
Officially merged upstream in the Linux Foundation's AgentTrust ecosystem, this cMCP policy adapter maps each verified V5 receipt onto a TRACE Trust Record for cross-vendor attestation.
Common Contract
Every integration follows the same three-step contract.
Intercept
The integration attaches to a native hook and captures the decoded tool name and arguments before the tool body executes.
Evaluate
The payload is scored for semantic intent against your policy bundles over POST /api/v1/paas/evaluate. Stateless — nothing is retained.
Halt or allow
A blocked verdict raises in-process and returns deterministic steering, so the agent replans instead of failing. The V5 receipt is verified locally.
Open Challenge
Can you bypass it?
Keyword filters catch syntax and fail on encoded payloads and corporate jargon. Our Red Team Guide publishes the zero-day evasion vectors we test against — including the Morse-code-encoded transfer used in the Grok/Bankr simulation. Every verdict in it was checked against the live API before publication.
Wire it up in an afternoon.
Create a free account, point an integration at your policy bundle, and watch the first blocked tool call land with a signed receipt.