Skip to main content
Agent skill

Krun agent skill

  • The official Krun agent skill teaches Claude Code, Codex and other coding agents to design Krun integrations: primitive selection, uncertainty handling, multimodal inputs and latency. Install it with claude plugin marketplace add krun-ai/skills and claude plugin install krun@krun-ai, or with npx skills add krun-ai/skills --skill krun.
  • No API or SDK changes.
Krun One V1

Krun One V1: multimodal inputs and multi

  • Krun One V1 (krun-one-v1) is the new default model. Requests that pin krun-one-v0 or krun-one-v0.3 keep working: both ids are aliases of krun-one-v1. See Models.
  • Multimodal inputs. context can be a string, as before, or a list of content parts: text, image, document and audio. Media parts reference files uploaded with the new /v1/assets endpoints, kept for 24 hours.
  • multi, a fourth question type that selects every option that applies, with an independent probability per option.
  • Pricing is unchanged. Media inputs are counted as input tokens, like text.
  • Cold starts can take up to about 2 minutes. The API now waits up to 150 seconds for the model. Set client timeouts of at least 180 seconds, the default in SDK 0.3.0, and retry 504 UPSTREAM_TIMEOUT. See Timeouts and cold starts.
  • Python SDK 0.3.0 (pip install -U krun-ai) adds content parts, multi, client.assets and the 180-second default timeout.
  • TypeScript SDK: @krun-ai/sdk is on npm (npm install @krun-ai/sdk). V1 multimodal support requires 0.3.0 or later.
Data controls

Data controls and typed feedback in the Console

  • Data controls. Organization owners can choose whether Krun may retain selected requests and feedback to improve its models. Off by default.
  • Console usage shows decisions by primitive (choice, noul, score), API latency percentiles and errors by code.
  • Playground feedback asks for the expected option (choice), true / false (noul) or the expected level (score).
  • No API or SDK changes.
Decision primitives

Krun One v0.3: choice, noul and score

  • Decision primitives. Besides choice, questions can now be noul (the probability that a yes/no proposition holds) and score (an expected level and a distribution over ordered levels). Types can be mixed in one call. See Decision primitives.
  • Krun One v0.3 (krun-one-v0.3) is the new default model. choice answers keep v0’s accuracy and format; requests that pin krun-one-v0 keep working.
  • Feedback accepts a typed expected value (choice option, noul true/false, score level). expected_decision still works. See Feedback.
  • Pricing is unchanged: one question is one decision, whatever its type, and usage still reports input tokens only.
  • Python SDK 0.2.0 adds NoulQuestion / ScoreQuestion, typed NoulAnswer / ScoreAnswer and result.choice() / .noul() / .score(). The TypeScript SDK (coming soon) will ship with the same types.
Closed beta

Krun One v0

  • Krun One v0 (krun-one-v0), the first Krun decision model, for intent and tool routing. See Models and Benchmarks.
  • POST /v1/decide with the questions and answers contract: one context, 1 to 16 named choice questions, one answer per question with choice, probabilities, confidence, abstain and abstention_status. See Questions and answers.
  • POST /v1/feedback to report whether an answer was correct, per question. See Feedback.
  • GET /v1/models to list available models.
  • Python SDK 0.1.0: krun-ai on PyPI, with Krun and AsyncKrun clients. See Python SDK.
  • TypeScript SDK: coming soon. See TypeScript SDK.