dsh-llm-friendli

Automated evidence available

FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support

Author: Lee-Si-Yoon · Tools & Capabilities · Catalog snapshot: 2026-09-19

Canonical semantic path

Models & AI CapabilitiesModel Provider Access & AuthenticationModel Catalog Discovery & Sync

One primary path; alternate capabilities remain separate.

What it may solve

FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support

Imported third-party catalog description; not a Registry verification conclusion.

Sources and public signals

Lee-Si-Yoon/dsh-llm-friendli

— stars · 724 downloads

Signals were provided by the source catalog and do not imply quality or safety. 2026-09-19

What can currently be confirmed

Active analysis coverage 5/5. Historical chains are retained but do not count toward current coverage.

Analysis complete

Source structure

Conclusion: The source structure check completed without finding a structural issue.

Analysis complete

Repository health

Conclusion: The GitHub repository is reachable and not archived. Public data: 1 stars, 16 commits, 0 forks, and 0 watches; latest commit 2026-09-07.

Analysis complete

npm release

Conclusion: Resolved npm release 0.1.6, published 2026-09-07, license MIT.

Not analyzed

DSH compatibility

Installation and startup verification has not been run.

Not analyzed

Dependency audit

Dependency audit has not been run.

Not analyzed

Functional verification

The plugin’s advertised feature has not been automatically verified. Passing installation and startup does not prove that feature works.

Not analyzed

Static risk scan

Static risk scanning has not been run.

Not analyzed

Package integrity

Package structure and integrity have not been analyzed.

Automated evidence is scoped to the named artifact, DSH target and profile. It is not a blanket safety or feature-completeness claim.

Continue with the latest plugin manager

Describe your task in a DSH conversation and mention dsh-llm-friendli. After installing or updating the manager from npm latest, it can find this candidate through Registry, then inspect its actual source and version locally.

Install or update the plugin manager (latest)