Skip to main content

Portable governance tooling for Statement-of-Work (SOW) corpora. Install the package, point it at a corpus, and use the zeo CLI (the zeo command is retained as a permanent alias).

Portable, deterministic governance tooling and AI agent orchestration for Statement-of-Work (SOW) corpora.

PyPI version Python Version License: MIT Code style: ruff

WebsiteDocumentationIssues


Overview

zero-employee (zeo) is the governance layer and linter for multi-agent software organizations. It enforces deterministic schema validation, cost tracking, state board generation, and IDE/agent bridge synchronization across your entire repository fleet.

              ┌─────────────────────────────────┐
              │       GOVERNANCE DOCTRINE       │
              │       (CLAUDE.md / Rulings)     │
              └────────────────┬────────────────┘
                               │
           RULINGS             │  ▲  SOWs
        (Top-to-Bottom)        │  │ (Bottom-to-Top)
        Mandates & Precedents  │  │ Status & Deliverables
                               ▼  │
              ┌────────────────┴────────────────┐
              │       PROJECT WORKSTREAMS       │
              │    (projects/<repo>/sow/...)    │
              └─────────────────────────────────┘

Key Features

  • Deterministic SOW Linting: Enforces strict frontmatter schemas (sow:, n:, status:, restaufwand:, done_when:).
  • Zero-Clutter Scaffolding: Clean-by-default repository and workstream generation with opt-in IDE bridges (--cursor, --gemini, --claude, --agents).
  • Cost & Token Proxies: Real-time token tracking (--session-cost, --repo-cost) with live rate cards.
  • Fleet State Board (STATE.md): Local navigation board of active streams, open questions, and held workstreams (gitignored — regenerate with zeo --board, never commit).

Installation

Install globally via uv (recommended) or pip:

# Recommended (isolated global executable):
uv tool install zero-employee

# Standard pip install:
pip install zero-employee

Requirements: Python 3.11 or higher.


Quick Start

zeo discovers a corpus by walking up from the current directory looking for claude-md/CLAUDE.md. You can also set ZEO_SOWS_ROOT or pass an explicit path.

# From inside a corpus (or with ZEO_SOWS_ROOT set):
zeo --board
zeo --triage
zeo --help

# Target a specific corpus path from anywhere:
zeo --board /path/to/corpus
ZEO_SOWS_ROOT=/path/to/corpus zeo --triage

If no corpus is found, zeo exits non-zero with a clear error message—it never hallucinates or invents a board.


Command Reference

Command / Flag Purpose
zeo init [path] Scaffold corpus marker + CLAUDE.md (@import). Bridges are opt-in.
zeo sow new <project> <stream> --title "..." Create a valid Rev-17 SOW without writing YAML.
zeo sow set / add / remove Mutate frontmatter fields safely (ZEO re-serializes YAML).
zeo sow draft ... Ollama collaborative body draft; ZEO owns frontmatter.
zeo doctor PATH / --changed Actionable readiness check for one SOW (or git-changed files).
zeo scaffold <project> <stream> Greenfield wrapper: project CLAUDE.md + sow new.
zeo bridges [flags] Install/resync IDE and agent bridges into an existing repository.
zeo --board Regenerate the local fleet state board (STATE.md, gitignored).
zeo --stream-index Regenerate local stream-index.md (gitignored).
zeo --triage Display operator worklist (open questions, held streams, unread rulings).
zeo --digest Generate session commit digest and tree status.
zeo --repo-cost / --session-cost Calculate USD cost proxies for LLM model token usage.
zeo --resync-check / --resync-apply Check and apply inherited doctrine updates across projects.
zeo hooks install Install thin git/session hook stubs + gitignore board files.
zeo hooks pre-commit Pre-commit gate (unstage boards, regen locally, lint staged SOWs).
zeo <path> Lint a single SOW, ruling, or skill file against strict schema rules.

zeo accepts the same arguments as zeo.


Modular IDE & Agent Scaffolding

Scaffolding commands stay clean by default to avoid polluting repositories with unused tool directories. You explicitly pass flags to generate tool-specific bridges:

# Clean SOW creation (no IDE clutter):
zeo sow new ducktyper render-pipeline --title "Render pipeline"

# Greenfield project+stream (also creates project CLAUDE.md):
zeo scaffold ducktyper render-pipeline

# Add Cursor MDC rules and .cursorrules symlink:
zeo scaffold ducktyper render-pipeline --cursor

# Add Gemini support:
zeo scaffold ducktyper render-pipeline --gemini

# Install the full agent & IDE bridge suite:
zeo scaffold ducktyper render-pipeline --all

Supported bridge flags: --cursor, --gemini, --claude, --agents, --all.


Local Development & Testing

We use uv and make for deterministic, hermetic local builds:

# Clone repository
git clone https://github.com/zeroemployeeorg/zero-employee.git
cd zero-employee

# Setup virtualenv and install dependencies
make setup

# Run linting and test suite
make verify

Documentation & Resources


License & Community

Distributed under the terms of the MIT License.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

zero_employee-0.1.5.tar.gz (201.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

zero_employee-0.1.5-py3-none-any.whl (138.4 kB view details)

Uploaded Python 3

File details

Details for the file zero_employee-0.1.5.tar.gz.

File metadata

  • Download URL: zero_employee-0.1.5.tar.gz
  • Upload date:
  • Size: 201.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for zero_employee-0.1.5.tar.gz
Algorithm Hash digest
SHA256 a437d4737bb381b612023492f384c951485ff62abbc0d6e2ca9b51b96f0792db
MD5 a72c2317f9f1b236579b3fde638ef56d
BLAKE2b-256 37b60a4676b88e67c6e38a2b4d5214a2c641c69cbafff3d91753192637057ce4

See more details on using hashes here.

Provenance

The following attestation bundles were made for zero_employee-0.1.5.tar.gz:

Publisher: publish.yml on zeroemployeeorg/zero-employee

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file zero_employee-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: zero_employee-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 138.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for zero_employee-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 6bc98abc6a6c96a1d1a3f79d8a42a2b16a2a7f0d24a4aa5280134807e10b599a
MD5 d462486d92c304fc951a35c6ad4da5c2
BLAKE2b-256 9919ddcf8cd2cf0a62e08cac34524431421f9902b654c2af68a0a90c28f26446

See more details on using hashes here.

Provenance

The following attestation bundles were made for zero_employee-0.1.5-py3-none-any.whl:

Publisher: publish.yml on zeroemployeeorg/zero-employee

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page