JSPM

  • Created
  • Published
  • Downloads 689
  • Score
    100M100P100Q115622F
  • License MIT

AI agent orchestrator that gives existing agents the drive to persist — set a goal, and PulSeed observes, delegates, verifies, and loops until done.

Package Exports

  • pulseed

Readme

Seedy - PulSeed mascot

PulSeed

Keep a goal moving until it is actually done.

Website npm Downloads CI Publish Node.js >=20 MIT License

PulSeed is an AI orchestrator for work that does not finish in one chat turn. Tell it the outcome you want, and it keeps observing, delegating, verifying, and looping until the goal is reached or the plan needs to change.

The primary entry point is pulseed. The normal flow is natural language, not a menu of subcommands.

Why PulSeed

  • Goal-first orchestration for long-running work
  • Honest goal negotiation when a target is not realistic as stated
  • Bounded agent execution with verification around delegated work
  • Local persistent state under ~/.pulseed/
  • Multiple runtime surfaces: CLI, chat, TUI, daemon, and cron
  • Support for OpenAI, Anthropic, Ollama, and adapter-based execution paths

Start Here

PulSeed requires Node.js 20 or newer.

npm install -g pulseed
pulseed

Then describe the goal in natural language:

  • Increase test coverage to 90%.
  • Show me the current progress.
  • Keep this goal moving in the background.

PulSeed will guide provider and adapter setup when needed. The recommended default for most users is agent_loop with OpenAI or Anthropic.

What It Does

  • CoreLoop keeps a goal moving and decides whether to continue, refine, verify, or stop
  • AgentLoop handles bounded tool-using work for task execution, chat, and selected runtime phases
  • State, reports, schedules, and local memory live under ~/.pulseed/
  • Software-level approval and verification gates protect delegated work

Common Surfaces

  • pulseed for the primary interactive workflow
  • pulseed tui for the terminal UI
  • pulseed start and pulseed stop for daemon control
  • pulseed schedule ... for schedule management
  • Lower-level commands for scripting, diagnostics, and compatibility

Use Cases

PulSeed is a fit when the work is bigger than one prompt and needs follow-through:

  • keep a codebase moving toward a maintenance goal
  • track a business KPI and adjust strategy as results change
  • coordinate recurring reports, reminders, and external actions
  • observe external data sources and ask for confirmation when a human decision is required

More detailed examples live in Use Cases.

Docs and Community

Start with the public doc map:

For project participation:

Safety Boundary

PulSeed uses approval gates and verification around delegated work. Native agent_loop task execution can use isolated git worktrees, and supported CLI adapters can be wrapped with a Docker terminal backend. These reduce blast radius, but local backends and plugins still run with the user's privileges. See Security.

License

MIT