Back to overview

Automate it

Agents with tools, skills, MCP & native provider tools

Configurable AI agents that call your tools, run Anthropic-standard skills in a Docker sandbox, federate across MCP servers — and turn on each provider's own server-side tools, opt-in per agent.

  • Your tools, your logic

    Define custom tools in Groovy with first-class helpers for HTTP calls, in-process Turing search and conversation slots — hot-reloadable, testable from the admin without a restart.

  • Anthropic-standard skills in a sandbox

    Drop a skill folder (SKILL.md + scripts) and Turing runs it in an isolated Docker sandbox with progressive disclosure — the same skill format Claude uses, executed safely against a per-conversation workspace.

  • MCP — both directions

    Connect agents to Model Context Protocol servers (with cross-vendor federation), and expose Turing's own search itself as an MCP server so any MCP-aware client can query your content.

  • Built-in code interpreter & chat flows

    Run Python in a hardened sandbox (native or Docker), and orchestrate multi-step conversations with a declarative flow DSL — slots, form capture, A/B testing and human handoff included.

Scaffold, run and deploy an agent with the CLI
npx @viglet/turing-cli init my-search
cd my-search
npx @viglet/turing-cli dev      # local stack
npx @viglet/turing-cli deploy   # push agents, flows, tools & skills
Native provider tools

Turn on the tools your model already has

OpenAI, Anthropic and Gemini ship powerful tools that run in their own infrastructure. Turing wires them straight into the agent loop — opt-in per agent, no glue code, no extra crawler — and routes their citations into the same source-chip UI as your own search.

Web search & grounding

The model searches the live web (and Google grounding on Gemini) and grounds its answer — citations flow into the same source-chip UI as your own RAG.

OpenAIAnthropicGemini

Code execution

A managed Python sandbox runs alongside your own code interpreter — charts, data wrangling and computed answers, rendered inline.

OpenAIAnthropicGemini

Computer use

A multi-turn screenshot/action loop behind a pluggable driver seam — browse and operate a UI to complete a task, the same contract across all three vendors.

OpenAIAnthropicGemini

URL / web fetch

The model pulls a URL or PDF named in the prompt directly in the provider's infrastructure — no Turing crawler in the path.

AnthropicGemini

Image generation

Generate images inline in the answer as self-contained data URIs — no separate artifact endpoint to host.

OpenAIGemini

File search

Retrieval over a provider-hosted vector store, available as a built-in tool right next to Turing's own search.

OpenAI

Strictly opt-in via a two-level capability gate — your existing agents stay byte-for-byte unchanged. Provider availability as of 2026.3.