ramen ai

Latest ecosystem updates

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 Python
    Agent 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-foundry
    RamenToolNode · DevboxShieldAgent · RamenSteerNode
    Python ≥ 3.10 · LangGraph
  • latest v0.1.4 TypeScript
    Transport 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 --help
    Drop-in stdio proxy — no SDK changes required
    Any MCP server using stdio transport
  • Python
    Agent 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-python
    RamenSafetyCallbackHandler → raises RamenSafetyException
    Python ≥ 3.10 · langchain-core ≥ 0.2
  • Python
    Agent 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-ai
    ramen_firewall() → @agent.tool(args_validator=…)
    Python ≥ 3.10 · pydantic-ai ≥ 0.0.14
  • TypeScript
    Orchestration

    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-middleware
    RamenFirewallBackend → GovernanceDenied
    @microsoft/agent-governance-sdk
  • Python
    Classical 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-guard
    RamenGovernedModel → GovernanceDeniedException
    Python ≥ 3.10 · MLflow ≥ 2.9
  • Python
    Dataset 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-filter
    filter_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.

Common Contract

Every integration follows the same three-step contract.

1

Intercept

The integration attaches to a native hook and captures the decoded tool name and arguments before the tool body executes.

2

Evaluate

The payload is scored for semantic intent against your policy bundles over POST /api/v1/paas/evaluate. Stateless — nothing is retained.

3

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.

Read the Red Team Guide (opens in a new tab)

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.