Skip to main content

CLI for building and deploying AI agents as containers

Project description

ninetrix

Build and deploy AI agents as Docker containers. Define your agent in YAML, ship it anywhere Docker runs.

pip install ninetrix

Quickstart

# Scaffold a new agent
ninetrix init --name my-agent --provider anthropic

# Build the container image
ninetrix build --file ninetrix.yaml

# Run it interactively
ninetrix run --file ninetrix.yaml

Multi-agent crews

# Start all agents on a shared Docker network
ninetrix up --file ninetrix.yaml

# Trigger the orchestrator
ninetrix invoke --agent orchestrator -m "Research Python history and write a summary"

# Stream logs from all agents
ninetrix logs --file ninetrix.yaml

# Visualize the execution trace
ninetrix trace --thread-id <id>

# Tear down
ninetrix down --file ninetrix.yaml

ninetrix.yaml

agents:
  orchestrator:
    metadata:
      role: "Research Orchestrator"
      goal: "Coordinate search and synthesis"
    runtime:
      provider: anthropic
      model: claude-sonnet-4-6
    tools:
      - { name: search, source: mcp://duckduckgo }
    collaborators: [researcher, writer]
    governance:
      max_budget_per_run: 1.00
      human_approval: true
    triggers:
      - type: webhook
        endpoint: /run

  researcher:
    runtime: { model: claude-haiku-4-5-20251001 }
    tools:
      - { name: search, source: mcp://duckduckgo }
      - { name: files,  source: mcp://filesystem }

  writer:
    runtime: { model: claude-sonnet-4-6, temperature: 0.7 }
    tools:
      - { name: files, source: mcp://filesystem }

Commands

Command Description
ninetrix init Scaffold a new ninetrix.yaml
ninetrix build Build container images
ninetrix run Run a single agent interactively
ninetrix up Start all agents on a Docker bridge network
ninetrix down Stop and remove all crew containers
ninetrix status Show running agent containers
ninetrix logs Stream logs from all agents
ninetrix invoke POST a message to a running agent
ninetrix trace Render a multi-agent execution tree
ninetrix mcp list List available MCP tool servers

Environment variables

Variable Description
ANTHROPIC_API_KEY Anthropic API key
OPENAI_API_KEY OpenAI API key
DATABASE_URL PostgreSQL URL for persistence
ninetrix_PROVIDER Override model provider at runtime
ninetrix_MODEL Override model at runtime

Requirements

  • Python 3.10+
  • Docker

License

MIT

Project details


Download files

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

Source Distribution

ninetrix-0.2.1.tar.gz (145.9 kB view details)

Uploaded Source

Built Distribution

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

ninetrix-0.2.1-py3-none-any.whl (179.7 kB view details)

Uploaded Python 3

File details

Details for the file ninetrix-0.2.1.tar.gz.

File metadata

  • Download URL: ninetrix-0.2.1.tar.gz
  • Upload date:
  • Size: 145.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for ninetrix-0.2.1.tar.gz
Algorithm Hash digest
SHA256 ab8f10db9681c6ca5e1cd7ac78fb5e92d8744805c29c72d72994cce634d333b3
MD5 de8c72e7d864cd3c899ec5defc6de5fb
BLAKE2b-256 ab766a854987ce0c86b1eceebdbbd2ad836585f222d7b17da79ea11cf3fe3a0e

See more details on using hashes here.

Provenance

The following attestation bundles were made for ninetrix-0.2.1.tar.gz:

Publisher: release-cli.yml on Ninetrix-ai/Ninetrix

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

File details

Details for the file ninetrix-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: ninetrix-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 179.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for ninetrix-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 819e1a87bd908106f8780ddae721d2ec57265e19d887413ae87c8ef6b50002d3
MD5 19fd674110f1315303e7f07327ae9f6b
BLAKE2b-256 13141c8b57094e20a019745c9b9bdd0e79c8dd80ca5e44f5079d09bf7752fa45

See more details on using hashes here.

Provenance

The following attestation bundles were made for ninetrix-0.2.1-py3-none-any.whl:

Publisher: release-cli.yml on Ninetrix-ai/Ninetrix

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