← DeepSeek Harness Plugins
DeepSeek Harness PluginIndexed

LiuHe

LLM-native code operations toolkit featuring a Rust tree-sitter parser daemon and 44 deterministic MCP tools.

Terminal & TUIDeveloper ToolsSecurity & PolicySkills & WorkflowsRemote Execution
1GitHub Stars0ForksUpdated2026-10-24

Install

$ # dsh plugin --profile web add @jieai/dsh-malong-bridge

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.

source-grounded
Malong LiuHe is an LLM-native code toolkit designed specifically for AI-driven development. It pairs a fast Rust tree-sitter parsing daemon supporting 10 programming languages with an extensive suite of 44 MCP tools. The toolkit provides deterministic AST parsing, symbol indexing, blast radius impact analysis, atomic transactional edits with undo journals, and zero-LLM code quality/security gates. It integrates smoothly with DeepSeek Harness via dedicated bridge tooling and Cordis configuration.

Key Capabilities

  • Multi-language AST symbol and reference extraction via high-performance Rust daemon
  • Atomic multi-file code editing with rollback journals and optimistic concurrency locking
  • Deterministic zero-LLM quality and security reviews including injection and secret scanning
  • Fast SQLite-backed symbol indexing, repo mapping, and dependency graph analysis
  • Direct integration into DeepSeek Harness web profile with automated workspace resolution

Useful For

  • Providing AI assistants with reliable, atomic code editing and refactoring primitives
  • Running blast-radius impact analysis and call-chain tracing before making codebase changes
  • Enforcing deterministic code quality, style, and security guardrails during automated workflows
  • Accelerating codebase navigation and symbol search across large multi-language repositories

Who It Fits

  • DeepSeek Harness users requiring advanced code editing and analysis capabilities
  • AI agent developers seeking safe, transactional AST-aware code toolchains
  • Software engineers integrating MCP coding tools into LLM workflows

Documented Limitations

  • Security scanners rely on deterministic regex patterns and AST reference graphs without cross-module data-flow or taint tracking
  • Requires running the native Rust parsing daemon or prebuilt binary for full tree-sitter symbol extraction
  • Fallback sql.js WASM sandbox mode is degraded compared to native better-sqlite3

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Not Found

No root package.json was captured in the latest GitHub snapshot.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
wulun811/LiuHe
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
858f833 · 2026-10-26

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
1GitHub stars
Forks
0
Open issues
0
Last commit
2026-10-24
Last release
2026-10-24
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app