Skip to content

plasmallm

KDE Plasma 6 assistant widget for many LLM providers, with a Decisions adapter that answers each message with a Jev verdict and confidence.

ServicebetaGPL-2.0

Overview

PlasmaLLM is a system-aware AI assistant widget for the KDE Plasma 6 desktop. It connects to Ollama, LM Studio, OpenAI, Anthropic, Google Gemini, OpenCode Zen/Go and any OpenAI-compatible API, can gather system information, call tools for files, shell commands and web data with user approval, run commands in tmux or screen, search the web, accept images and voice input, store keys in KWallet and compact context.

Its Decisions (TypeSafe / Jev) adapter, using TypeSafe directly or via OpenRouter, is for decision models: instead of chatting, each message is evaluated once and answered with a verdict and confidence of Yes, No or Uncertain. The run_command tool can also optionally verify each command with a second model profile before execution. It is GPL-2.0 licensed.

What the decision model decides

TypeQuestionAnswers
ChoiceVerdict on the user's messageYes · No · Uncertain

How it works

  1. Select a Decisions profile in the widget.
  2. Type a question.
  3. Jev evaluates it once and returns a verdict and confidence.
  4. Display the structured judgment.

Strengths

  • Desktop-native access to decision models.
  • Works via TypeSafe or OpenRouter.
  • Part of a broader local assistant.

Caveats

  • Decisions mode is a small feature of a general assistant.
  • KDE Plasma 6 only.

At a glance

Type
Service
Status
beta
Language
QML/JavaScript
Runtime
KDE Plasma 6 widget
Has code
yes
License
GPL-2.0

Use cases and integrations

How curated lists describe it

Frequently asked questions

How does the Decisions adapter answer?

With a single verdict of Yes, No or Uncertain plus confidence.

Which providers can reach Jev?

TypeSafe directly or OpenRouter.

Which desktop does it need?

KDE Plasma 6.

Related projects

  • Hack Club's lightweight LLM proxy, listed for adding a Jev forwarding endpoint behind its auth, limits and usage logging.

    MCP serverproductionTypeScript
  • Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.

    PluginproductionTypeScript
  • Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.

    ProjectproductionTypeScript
  • PHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.

    ProjectproductionPHP
  • Go MCP server giving any client typed Jev decisions via OpenRouter or TypeSafe, with validated answers and no paid retries.

    MCP serverproductionGo
  • Simon Willison's LLM plugin that adds Jev as a model for yes/no, choice and score questions from the command line.

    PluginproductionPython