DSH Plugins Marketplace

DSH Plugins

Plugins

/

Tools & Capabilities

/

@aalvsz/dsh-hermes-bridge

a

@aalvsz/dsh-hermes-bridge

Manifest valid★ 3

Native adaptive intelligence layer for DeepSeek Harness: memory, skills, /learn, background review, and curator — no Hermes or Python dependency.

hasBundlePatch

dsh-hermes-bridge

CI License: MIT

Native adaptive intelligence for DeepSeek Harness — no Hermes or Python dependency.

dsh-hermes-bridge reimplements Hermes's adaptive intelligence layer as a standalone DSH plugin in JavaScript. It provides what Hermes provides on top of the base agent loop — persistent memory, reusable skills, skill authoring, background review, and curator — without requiring a separate Hermes installation.

What appears in DSH

CapabilityDSH surface
Persistent memory (MEMORY.md / USER.md)hermes_memory + frozen system-prompt snapshot
Reusable skills (SKILL.md catalog)hermes_skills_list, hermes_skill_view, hermes_skill_manage
Skill authoring/hermes-learn
Background memory/skill reviewoptional DSH subagent fork
Curatoroptional due-checked integration
RL trajectory capturehermes_trajectory_save + automatic turn/end capture
Trajectory compressionhermes_trajectory_compress (protected regions + LLM summarization)
Capability diagnosticshermes_status

DSH already provides the agent loop, tool calling, providers, subagents, sessions, approvals, file/bash/web tools, and model routing. This plugin adds the adaptive layer that DSH lacks natively — including the RL trajectory collection and compression pipeline for generating fine-tuning data.

Differences from v0.1.0 (bridge)

v0.1.0 was a bridge that connected to a real Hermes Python installation. v0.2.0 is a native reimplementation — no Hermes, no Python, no subprocess. Memory and skills are pure JavaScript with standard fs operations.

Install

dsh plugin --profile web add github:aalvsz/dsh-hermes-bridge

Configure

Override the package row in your profile's cordis.patch.yml:

- id: dsh/hermes-bridge
  config:
    enabled: true
    namespace: hermes
    backgroundReview: false
    curator: false
    memoryCharLimit: 2200
    userCharLimit: 1375
    memoryNudgeInterval: 10
    skillNudgeInterval: 10
    saveTrajectories: false
    model: null
    trajectoryTargetMaxTokens: 15250
    trajectorySummaryTargetTokens: 750

Defaults

  • backgroundReview, curator, and saveTrajectories are off until explicitly enabled.
  • Memory and skill files use mode 0600; directories use 0700.
  • All tools are namespaced hermes_* to avoid collisions with native DSH tools.

RL trajectory pipeline

When saveTrajectories: true, every completed conversation is converted to ShareGPT trajectory format ({from, value} with <execute>, <result>, and <think> XML tags) and appended to trajectory_samples.jsonl.

Use hermes_trajectory_compress to compress trajectories within a token budget:

  1. Protected head turns (system, human, first gpt+tool) are preserved
  2. Protected tail turns (last N turns) are preserved
  3. Middle turns are accumulated until enough savings are achieved
  4. Compressed turns are replaced with a single summary message
  5. Boundary snapping prevents splitting gpt/tool pairs

This mirrors Hermes's trajectory_compressor.py for generating SFT/DPO-ready data.

Development

npm install
npm test
npm run verify

License

MIT.

Comments

Loading…

Similar plugins

dsh-harness-mcp-server

by chushixixin

Expose DeepSeek Harness agent capabilities as an MCP server (brain=Hermes, arms=Harness)

Tools & CapabilitiesManifest valid

★ 10

↓ 99/wk

MIT

TypeScript

Aug 15, 2026

dsh plugin --profile web add @chushixixin/dsh-harness-mcp-server

by Dogtiti

Subagent-shaped bridge between Codex and DeepSeek Harness: Codex spawns DSH workers over a loopback MCP endpoint and gets final answers back; DSH agents can dispatch to Codex in return.

Sessions & MessagesManifest valid

★ 5

↓ 804/wk

MIT

JavaScript

Nov 1, 2026

dsh plugin --profile web add dsh-plugin-subagent-bridge

by Bear0117

Recursive Harness for DeepSeek Harness: evolves the agent's system prompt, guardrails, tool guidance, memory and skills with Propose, Probe, Compose loops and a cross-task experience library (Harness², arXiv:2610.14224). Experimental.

Tools & CapabilitiesManifest valid

★ 0

MIT

JavaScript

Oct 22, 2026

dsh plugin --profile web add dsh-plugin-recursive-harness

by helibeiqi

Universal bridge adapter for DeepSeek Harness: consume external MCP servers & Agent Plugins 1.0 packages, and expose DSH native tools back as a standard MCP server. Host composition layer, bidirection

Tools & CapabilitiesManifest valid

★ 0

MIT

TypeScript

Aug 28, 2026

dsh plugin --profile web add @helibeiqi/dsh-cordis-universal-adapter

by Socialist-Sister

Multi-agent collaboration suite for DeepSeek Harness: specialist roster with on-demand dispatch, roundtable, model comparison and a multimodal vision bridge — models via the official provider flow.

Workflow & AutomationManifest valid

★ 4

MIT

TypeScript

Aug 19, 2026

dsh plugin --profile web add dsh-collaboration

by dsh-pulse

Task-queue execution endpoint for DSH: requires a separately self-deployed Hermes Agent gateway plus your own WeChat inbound script; verified on a single environment — expect to adapt it.

Tools & CapabilitiesNotifications & IntegrationsManifest valid

★ 0

↓ 93/wk

MIT

JavaScript

Aug 24, 2026

dsh plugin --profile web add @dsh-pulse/dsh-hermes-bridge