Skip to main content

A research-backed CLI for human-mediated multi-agent coordination via structured file-based memos.

Project description

interagent

A research-backed CLI for human-mediated multi-agent coordination via structured file-based memos.

Status: Planning. This package is under active development. The protocol design is being validated through manual experimentation before the CLI is built.

What this will be

interagent (ia on the command line) manages the communication layer for workflows where a human operator coordinates multiple LLM agents across separate chat interfaces using structured markdown memos with YAML frontmatter.

CLI command: ia

ia new {workstream}       # Create a new memo from template
ia inbox {entity_id}      # List active memos for an entity
ia reply {memo_id}        # Scaffold a reply memo
ia resolve {memo_id...}   # Create a decision memo closing a thread
ia archive-thread {id}    # Archive all memos in a thread
ia onboard {entity_id}    # Create an entity folder and profile
ia entities               # List all entities with status
ia activate {entity_id}   # Activate an entity
ia deactivate {entity_id} # Deactivate an entity
ia lint {memo_id}         # Validate memo schema
ia index                  # Regenerate the memo registry

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

interagent-0.0.1.tar.gz (2.3 kB view details)

Uploaded Source

Built Distribution

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

interagent-0.0.1-py3-none-any.whl (3.3 kB view details)

Uploaded Python 3

File details

Details for the file interagent-0.0.1.tar.gz.

File metadata

  • Download URL: interagent-0.0.1.tar.gz
  • Upload date:
  • Size: 2.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.14

File hashes

Hashes for interagent-0.0.1.tar.gz
Algorithm Hash digest
SHA256 af45155759bd1c3adac8530a77563ac2ed7e10e3142b58de3f8581f9fec8499f
MD5 eb785775e4caaca2cde25f24c82fda15
BLAKE2b-256 3afbd6a1324ef2ff2de521c8b26c3eb3ef4c9c76ede381ba81f506ad1f27a805

See more details on using hashes here.

File details

Details for the file interagent-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: interagent-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 3.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.14

File hashes

Hashes for interagent-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 368e7f550dc8a9dd0064222cf503d6eebec9164c448d7d7feb5df893be9a1cc4
MD5 115fcd4d816377a708f4939a0e80a44d
BLAKE2b-256 7c3c771e26c2a532f8fee0187b714ecbca31790a3c9b02d18a1daa537c6111af

See more details on using hashes here.

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