Back to directory

InitRunner

A tool for defining an AI agent's role in a single YAML file and running it as a CLI chat, an API server, or an autonomous daemon reacting to schedules, file changes and webhooks.

InitRunner

InitRunner lets a developer define an agent's role in one YAML file, chat with it while prototyping, then run the same file autonomously as a daemon that reacts to cron schedules, file changes, webhooks and Telegram messages. A catalog of starter agents covers a personal memory assistant, a documentation question-answering agent, a multi-agent research team and a code reviewer.

A build command can generate a new agent from a plain-language description, and the model is auto-detected from the configured API key. Agents can also be shared and installed from a community catalog called InitHub. InitRunner installs via a shell script, pip or Docker, and is available in English, Chinese and Japanese.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.