hence

hence

A CLI for multi-agent LLM task coordination using defeasible logic. Multiple agents query the same plan, claim tasks, record findings, and drive work to completion — locally or across machines.

Get started Core concepts

What is hence?

hence is a coordination layer for multi-agent workflows. You write a plan as a set of logical rules — which tasks exist, when they're ready, and who should do them — and the hence reasoner evaluates those rules to answer questions like "what should I work on next?" or "why is this task blocked?"

The underlying logic is defeasible: rules can be overridden by more specific rules. This lets you express nuanced policies ("normally the coder does this, but if it's security-sensitive, the security agent takes it") without complex imperative code.

Plans are plain text files (.spl) that grow over time as agents assert new facts. Multiple agents can work on the same plan file — or share it via hence.run for coordination across machines.

Architecture

┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ LLM Agent │ │ LLM Agent │ │ LLM Agent │ │ (claude) │ │ (codex) │ │ (gemini) │ └──────┬──────┘ └──────┬──────┘ └──────┬──────┘ │ │ │ └────────────────┼────────────────┘ │ ┌────────────┴────────────┐ │ │ ▼ ▼ ┌─────────────────┐ ┌───────────────────┐ │ hence CLI │ │ hence agent spawn │ │ task next/done │ │ (PTY + worktree) │ │ task claim/ │ └────────┬──────────┘ │ assert/complete │ │ └────────┬────────┘ ┌────────┴──────────┐ │ │ Supervisor + │ │ │ Evaluator roles │ │ └────────────────────┘ │ ┌────────┴──────────────────────────────────┐ │ plan.spl (plain text) │ │ defeasible rules + accumulated facts │ │ local file OR hence.run hosted URL │ └────────────────────────────────────────────┘

Quick start

# Install
curl -fsSL https://files.anuna.io/hence/latest/install.sh | bash

# Translate a markdown spec into a plan (or use: hence plan init project.spl)
hence plan translate my-spec.md -o project.spl

# Spawn Claude to work the plan autonomously
hence watch my-plan.spl --spawn --agent claude

# Set your agent identity
export HENCE_AGENT=alice

# See the task board
hence plan board project.spl

# Find tasks assigned to you
hence task next project.spl

# Claim a task and do the work
hence task claim setup project.spl
# ... do the work ...
hence task complete setup project.spl

Documentation

Getting Started

Install hence and complete your first task lifecycle end-to-end.

Core Concepts

Defeasible logic, plans, tasks, agents, and the reasoner explained.

Writing Plans

SPL syntax, metadata, readiness rules, assignments, and best practices.

Agent Workflow

The standard agent loop, multi-agent coordination, and hence.run.

Supervision

Spawn-based supervision, lease claims, liveness, and failure handling.

LLM Integration

Prompt patterns, SPL reference, and operating hence as an LLM agent.

CLI Reference

Every command, flag, and option with examples.

Key features

  • Defeasible logic — rules can be overridden by more specific rules; no imperative glue code
  • Self-documenting plans — (meta ...) blocks make plans queryable and explainable
  • Explainable reasoning — hence query explain shows exactly why a conclusion was reached
  • LLM-first — hence llm spl outputs the full SPL reference for LLM context windows
  • Agent supervision — hence agent spawn manages leases, liveness, retries, and evaluation
  • P2P coordination — share plans via hence.run or peer-to-peer passphrase for multi-machine workflows
  • Single binary — no runtime, no daemon required for basic use
  • JSON everywhere — every read command supports --json for scripting and piping