dsh-rigorquant
Session-scoped unattended multi-agent research lab for quantitative finance and computational mathematics in DeepSeek Harness.
Install
$ dsh plugin --profile web add dsh-rigorquantPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Context-isolated multi-agent orchestration across 6 specialized research roles (Orchestrator, Explorer, Oracle, Adversary, Literature, Document Adversary)
- Four-part pre-implementation check battery (closed-form equality, exact invariants, analytic bounds, statistical hardening)
- Dual independent ground-truth derivations for critical formulas before any numerical code is written
- Evidence-backed meta-validation (rq_check.py) verifying audit trails and study artifacts
- Role-routed model and reasoning effort configuration with fallback retry handling
- Live floating visual activity panel rendering task progress and team roster in the DSH web client
Useful For
- Rigorous quantitative finance modeling and empirical validation
- Mathematical derivation and symbolic verification prior to numerical implementation
- Simulation and portfolio optimization research with fixed-seed LLN audit standards
Who It Fits
- Quantitative researchers and computational finance practitioners
- Mathematical and algorithmic modelers using DeepSeek Harness
- Data scientists requiring formal derivation and verification workflows
Documented Limitations
- Runs unattended only within a single live session boundary (human confirmation required across restarts)
- Requires DeepSeek Harness >= 0.1.2-alpha.1 for native agentOptions.reasoningEffort support
- Jacobian/Lean proof escalation lanes require explicit MCP enabling and provisioning
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- linxichen/dsh-rigorquant
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- fbdd80e · 2026-09-13
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 5GitHub stars
- Forks
- 1
- Open issues
- 1
- Last commit
- 2026-09-10
- Last release
- 2026-08-21
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Multi-agent team collaboration plugin for DeepSeek Harness with DAG task scheduling, mailbox messaging, and an interactive Web UI monitor.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Native SQLite-backed local project taskboard plugin and UI for DeepSeek Harness with Agent claim and review flows.
View plugin →