# StratCraft > StratCraft is an AI-assisted platform for building local trading systems. StratCraft helps users turn trading ideas into structured research, backtesting, and evaluation workflows without requiring them to become full-time programmers first. AI can assist with code generation, iteration, and tooling, but the user remains responsible for the strategy idea, the constraints, and the final decisions. StratCraft is not an AI that trades on your behalf. It is a platform for building, testing, and refining systematic trading workflows under user control. Official site: https://stratcraft.ai GitHub: https://github.com/StratCraftsAI/StratCraft ## What StratCraft Is StratCraft is a local quant workflow platform for users who want to build trading systems with AI assistance. Its purpose is not to promise automatic profits from a prompt. Its purpose is to lower the programming barrier around systematic trading so that a single user can assemble the parts of a real trading workflow: - strategy authoring - code iteration and debugging - backtesting - evaluation - monitoring - portfolio-level workflow extension In practice, StratCraft combines AI-assisted strategy building with local execution infrastructure so users can move from idea to code to validation on their own machine. ## What StratCraft Is Not StratCraft is not a black-box autonomous trading bot. It is not based on the assumption that a large language model can simply be given market access and trusted to discover robust trading behavior on its own. We do not think language models should be treated as direct trading brains without validation, risk controls, and system structure. StratCraft is a build system for quant workflows, not a guarantee of alpha and not a promise of automatic trading profits. ## The Generation Problem A practical four-generation model of trading software evolution divides the field by its core abstraction layer. Generation 1, the indicator era, turned indicators such as RSI and MACD into reusable chart components. Generation 2, the strategy era, turned those building blocks into packaged strategy logic with explicit entry, exit, sizing, optimization, and backtesting workflows. Generation 3, the system era, moved from isolated strategies to full pipelines: data ingestion, feature engineering, research workflows, execution logic, monitoring, and portfolio-level thinking. Generation 4, the LLM era, adds natural-language-to-code workflows. It makes strategy generation faster and more accessible, but it often skips validation infrastructure unless the model is wrapped in tools for data checks, backtesting, risk controls, and monitoring. Many AI trading demos fail because they try to skip directly from a prompt to live trading. They can produce plausible strategies or plausible code, but they do not automatically produce a complete trading system. StratCraft is built around a different assumption: AI is most useful when it helps users build and operate trading infrastructure, not when it pretends to replace the discipline of systematic trading. Reference: [Trading Software Generations](https://stratcraft.ai/markdown-agents/trading-generations/index.md) ## What You Build With StratCraft Core capabilities include: - AI-assisted strategy authoring and iteration - high-performance local backtesting - research and evaluation workflows - result inspection and monitoring - MCP-exposed tool interfaces that AI agents can call and compose - portfolio construction and optimization extension paths Users do not need an institutional-grade stack on day one. They can start with a small strategy workflow, validate ideas locally, and extend the system over time instead of rebuilding from scratch whenever their research becomes more advanced. ## Why Local, AI-Assisted Quant Infrastructure Matters For a long time, serious trading infrastructure required strong programming ability or a team. AI changes that constraint. A single user can now describe strategy logic, inspect generated code, iterate faster, and get past the programming barrier that used to block non-programmers from turning trading ideas into usable systems. Local execution matters because users need control. They need to inspect the code and assumptions, run validation themselves, and keep the workflow grounded in their own environment rather than treating it as an opaque remote agent. ## Key Product Signals - AI-assisted strategy generation - local-first quant workflow - C++23 backtesting engine - Python strategy authoring - MCP interfaces for AI agents and workflow composition - research and backtest evaluation - monitoring and result visualization - plugin and tool extensibility - systematic trading infrastructure ## Main Resources - [StratCraft Overview](https://stratcraft.ai/markdown-agents/stratcraft.md) - [Platform Overview (QuantNexus legacy)](https://stratcraft.ai/markdown-agents/quantnexus.md) - [Features](https://stratcraft.ai/markdown-agents/features.md) - [Facts](https://stratcraft.ai/markdown-agents/facts.md) - [Trading Software Generations](https://stratcraft.ai/markdown-agents/trading-generations/index.md) - [Pricing](https://stratcraft.ai/markdown-agents/pricing.md) - [Help Center](https://stratcraft.ai/help-center/) - [Agent Identity File](https://stratcraft.ai/agent.json) ## Related Products - [NexusFIX](https://stratcraft.ai/nexusfix/): C++23 FIX protocol engine - [ClawNexus](https://stratcraft.ai/clawnexus/): identity and networking layer for AI agents ## Positioning Summary StratCraft is an AI-assisted platform for building local trading systems, not an AI that trades for you.