{
  "markdown": "## Vantio Optics (Open Core)\nFree, local-first observability for AI agent egress. See what your agents call out to —\nwithout ever reading the conversation.\n\n```\nnpm install -g @vantio/cli\nvantio run node agent.js\n```\n\nThat's the integration. Optics intercepts outbound calls to known LLM providers and reports\ndestination, process, size, and timing — never prompts or completions.\n\nPython: `pip install vantio-agent-sdk`, then wrap your agent with `@shield`.\n\nOptics is Tier 1 of Vantio's architecture — Observe. [Gate](https://vantio.ai/gate) (Enforce)\nand [Phantom Engine](https://vantio.ai/phantom-engine) (Control) extend this to policy\nenforcement and host-level runtime protection on enrolled Linux systems. Full docs:\nvantio.ai/docs.\n\n---\n\n## Supported runtimes\n\nThat's the only install step. Works on macOS, Linux, and Windows (WSL).\n\nOn Node: fetch, undici, http/https, http2, net/tls, WebSocket, and spawned curl or wget.\n\n`vantio run` only injects the Node interceptor (`NODE_OPTIONS --require`) for `node` / `npx` / `tsx` / `ts-node`.\n\nPython support requires vantio-agent-sdk. Follow the current Python SDK example and verify that a supported outbound event appears before relying on the coverage state. Prefixing `vantio run python` does not intercept by itself.\n\nBrowser paths stay outside this wrap.\n\n---\n\n## What is recorded\n\nOptics records connection and process metadata from supported wrapped agent paths. Does not block actions or retain prompts or completions.\n\nVantio records *that* a call was made, *when*, *to which provider*, and *how many bytes* — nothing more.\n\n---\n\n## What is never recorded\n\n- The content of your prompts\n- Model completions or responses\n- Any personally identifiable information\n\n---\n\n## Present coverage boundaries\n\n`vantio run` intercepts LLM calls by patching `globalThis.fetch` in the Node.js\nruntime (via `NODE_OPTIONS --require`). This covers the vast majority of real agents\n— every OpenAI SDK call, every LangChain.js call, every Vercel AI SDK call — without\nany code changes.\n\n**It can be bypassed.** A process can:\n- Call an LLM endpoint directly through a native socket without using `fetch`\n- Spawn a subprocess that isn't started with `vantio run`\n- Use a language runtime other than Node without installing the Python SDK\n\n**This is intentional, not a bug.** Vantio Optics surfaces your governance gap honestly.\n\nWithout the SDK, `vantio run python` does not intercept. Browser paths, or processes not started with `vantio run` / `shield()`, never hit Optics — and Optics does not invent a record for them.\n\n---\n\n## License and telemetry\n\nMIT License.\n\nAnonymous, opt-out usage analytics. No prompts, completions, API keys, or emails. Opt out at any time:\n\n```\nexport VANTIO_TELEMETRY_DISABLED=1   # or\nexport DO_NOT_TRACK=1\n```\n\n---\n\n## Upgrade path to Gate and Phantom Engine\n\nFree Optics needs **no account and no API key**. `vantio login` is optional and later, for dashboard sync only, never a required step before running.\n\nOptics is Tier 1 of Vantio's architecture — Observe. [Gate](https://vantio.ai/gate) (Enforce)\nand [Phantom Engine](https://vantio.ai/phantom-engine) (Control) extend this to policy\nenforcement and host-level runtime protection on enrolled Linux systems.\n\nResidual risk closes with **Vantio Gate**, then **Vantio Phantom Engine** — see [vantio.ai/pricing](https://vantio.ai/pricing).\n",
  "bytes": 3375,
  "sha": "54b2b72bc949270252829dc7a5a6c02e4c29829905df24d474e13fb4e2835608",
  "repo_slug": "vantioai/vantio-open-core",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_vantioai_vantio_gate_b920609d/readme"
}