Skip to content

Could QuantDinger retain durable research context across strategy workflows? #244

Description

@memcodeoff

Hi, I’m Vivek Gupta, Founder & CEO at MemCode. QuantDinger brings research, strategy building, backtesting, paper/live workflows, monitoring, and MCP into one AI workspace. Those workflows generate context that should survive a single chat or run: explicit research assumptions, strategy constraints, confirmed findings, rejected hypotheses, dataset notes, and review decisions. A durable memory layer could preserve that context while leaving market data, backtest results, and execution records authoritative.

MemCode provides state-of-the-art semantic retrieval and durable updates with provenance, retention, export, and deletion controls. QuantDinger could retrieve narrowly scoped research context before an agent runs and write back only explicit, user-approved conclusions or verified workflow outcomes through MemCode’s MCP server or SDK. MemCode supports local memory and self-hosted deployment in concrete terms: the engine/API can run in the operator’s own Docker/VM or as a local process behind a private base URL, keeping records, embeddings, credentials, and logs inside that deployment with no mandatory hosted endpoint or telemetry. MCP + SDK support makes this an optional adapter without core-code changes.

I’d value the maintainers’ perspective on whether durable research context fits QuantDinger’s roadmap. If useful, I can open a small PR or discuss the cleanest boundary between source data, execution records, and memory. The short overview is here: MemCode Leviathan.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions