dsh-vlm-bridge
A DeepSeek Harness bundle that adds image analysis to text-only agents through a configurable VLM API.
Install
$ dsh plugin --profile web add github:me9rez/dsh-vlm-bridgeRepository Intelligence
AI-assisted, source-grounded explanation based on the public repository snapshot. It does not replace compatibility or security verification.
Key Capabilities
- Adds the `vision_analyze` tool to DeepSeek Harness.
- Analyzes image files with a VLM API; the documented default is ModelScope `Qwen/Qwen3-VL-8B-Instruct`.
- Supports a `question` parameter for image-detail follow-up questions.
- Configures endpoint, model, caching, request timeout, token limit, and log-file path through plugin configuration.
- Reads the required `VLM_API_KEY` only from DSH credentials.
- Provides a verification script covering module resolution, configuration schema, tool registration, and optional VLM end-to-end testing.
Useful For
- Give a text-only DSH model a textual description of a local image.
- Ask targeted questions about image contents.
- Use an alternative configured VLM endpoint or model for image understanding.
Who It Fits
- DeepSeek Harness users running models without image input support.
- Developers configuring DSH bundle plugins and VLM credentials.
Documented Limitations
- Requires a `VLM_API_KEY` in `~/.dsh/.credentials.yaml` for VLM requests.
- Image analysis depends on the configured external VLM API endpoint and model.
- A DSH process restart is required after installation so the bundle layer is read.
- Local linked development installations may require a junction for resolving `@deepseek-ai/*` dependencies.
- The documented end-to-end verification skips VLM testing when no API key is available.
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 2 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub did not report an SPDX license for this repository snapshot.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Traceable source and registry metadata for this entry, kept separate from runtime verification.
- Source repository
- me9rez/dsh-vlm-bridge
- Registry source
- Public GitHub repository
- Source snapshot
- c98f72eeaf85
- Artifact type
- plugin-bundle
- AI enrichment
- gpt-5.6-terra · 2026-08-14
- Prompt version
- dsh-plugin-enrichment-v3
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
- 0
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-14
- Last release
- —
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Adds an OpenAI-compatible vision bridge to DeepSeek Harness, forwarding images to a configured vision model and displaying descriptions in a web panel.
View plugin →DeepSeek Harness vision-routing plugin with provider fallback chains and pixel-level image tools.
View plugin →Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
View plugin →DeepSeek Harness plugin that generates, runs, and iteratively fixes unit tests through a /testgen command and generate_tests tool.
View plugin →