dsh-llm-vision-bridge
Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.
Install
dsh plugin --profile web add dsh-llm-vision-bridge
For reproducible installs, append #commit to pin a specific revision.
Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.
No highlight list provided; see the repository README.
- Install and start DeepSeek Harness:
npx @deepseek-ai/dsh web - Run the install command above (the CLI resolves the plugin and verifies its source)
- Confirm with dsh plugins list; restart Harness if required
Plugins run with your dsh process permissions and may execute code during installation. Read the repository source and license first, and check for destructive commands or excessive access. This site only indexes; it does not vouch for third-party plugins.
| Repository | github.com/Einskyle/dsh-llm-vision-bridge |
| License | Not declared (see repo) |
| Primary language | — |
| Downloads | 327 |
| GitHub stars | 3 |
| Last push | — |
| Cataloged | 2026-08-14 |
| Category | Vision & Multimodal |
Facts come from a public catalog snapshot (2026-09-16); descriptions are rewritten by us.
Sources: the public DeepSeek Harness plugin catalog and each plugin's GitHub repository. This is an independent third-party directory with no affiliation to or endorsement from DeepSeek, High-Flyer, or the plugin authors.
