Vibe-Mathematics
Multi-agent mathematical problem solving and formal verification framework bundle for DeepSeek Harness.
Install
$ dsh plugin --profile <你的 profile> add dsh-vibe-math@<版本>Plugin 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
- Bundles four agent presets into DeepSeek Harness: vibe-math-v2, vibe-math-v3, vibe-math-v4, and vibe-math-v5
- Provides multi-agent verification pipelines with independent reviewers, structured debate, and quorum/consensus mechanics
- Supports Lean 4 formal verification integration with asynchronous compilation and fidelity checks
- Offers mathematical computation tool integration across multiple engines (Python, R, Julia, Octave, etc.)
- Automatically compiles comprehensive research papers in Markdown, LaTeX, and PDF formats upon problem completion
- Maintains checkpointed state and resumable continuable sessions for interrupted workflows and manual interventions
Useful For
- Automated collaborative mathematical theorem proving and conjecture exploration
- Formal verification of mathematical claims using Lean alongside LLM agents
- Multi-agent academic research simulation with role-based coordination and peer review
- Automated generation and LaTeX typesetting of research papers from multi-agent reasoning logs
Who It Fits
- Mathematicians and researchers exploring automated formal mathematics
- AI developers building collaborative multi-agent reasoning workflows
- DeepSeek Harness users requiring advanced mathematical computation and theorem verification
Documented Limitations
- Lean toolchains and compilers are not bundled; formal execution requires Lean installed on the host system
- Compiling PDF research papers requires a host-installed LaTeX engine such as xelatex or pdflatex
- Agent consensus and formal proof checks only verify syntax and kernel conformance, requiring human review for faithfulness to the original proposition
- Plugin installation and updates require pnpm to be preinstalled on the host system
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.
package.json declares 0 runtime, 0 development, 1 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- ChongCyrus/Vibe-Mathematics
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- fc18e32 · 2026-10-25
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
- 43GitHub stars
- Forks
- 3
- Open issues
- 9
- Last commit
- 2026-10-25
- Last release
- 2026-10-05
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed security.
View plugin →LLM-supervised persistent memory and graph-based recall integration bundle for DeepSeek Harness.
View plugin →