Use DeepSeek Harness with OpenLLM
Add the OpenLLM bundle to a DeepSeek Harness profile and route it through your local gateway, fallback chains included.
dsh plugin --profile web add github:openllmsh/dshHow it works
The bundle is a Cordis patch that points the harness at your daemon's local gateway. It is added from the harness side, per profile.
- Add it to the
webprofile for the browser UI, orheadlessfor CLI-only - Restart the profile after adding the bundle
Fallback chains when a model is rate-limited
Define an ordered chain per model alias. When a hop returns a rate limit, an overload or a provider error, the request moves to the next hop instead of failing your session.
- Chains are configured once and shared by every client and device
- Each hop resolves its own model settings, so a fallback never inherits the wrong parameters
- Every hop that ran is visible in your request history
Code search and memory over MCP
The same binary ships one MCP server: semantic search over your indexed repositories and documentation, plus memory that persists across sessions and clients.
See where the tokens go
Requests, tokens, latency and API-equivalent cost per model and provider, with charts you can export or share.
Provider keys encrypted at rest
API keys are encrypted in your browser with AES-256-GCM under a key derived from your recovery phrase, and stored as ciphertext. They are decrypted in memory only while a request is being served, then discarded. Subscription credentials never reach the hosted service.
Questions
Something else? Contact us