Skip to main content

Recursive multi-agent swarm for long-horizon work

Project description

maverick-core

The Maverick agent kernel. A recursive multi-agent swarm with persistent world model, shared blackboard, hard budget caps, and closed-loop skill learning.

See the top-level README and ARCHITECTURE.md for the full picture.

This package is installable on its own:

pip install maverick
export ANTHROPIC_API_KEY=sk-ant-...
maverick start "your goal"

But you probably want pipx install maverick + maverick init instead, which also pulls in the safety layer and configures per-role model choice.

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

maverick_agent-0.1.2.tar.gz (637.6 kB view details)

Uploaded Source

Built Distribution

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

maverick_agent-0.1.2-py3-none-any.whl (587.5 kB view details)

Uploaded Python 3

File details

Details for the file maverick_agent-0.1.2.tar.gz.

File metadata

  • Download URL: maverick_agent-0.1.2.tar.gz
  • Upload date:
  • Size: 637.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for maverick_agent-0.1.2.tar.gz
Algorithm Hash digest
SHA256 f734cc0158589181b8da147ad9a777f92ba44228e5471ff1d44f05db1b0e3832
MD5 ed4a941ef1f4e978627eb36ea1cdb1a9
BLAKE2b-256 e95ac831d7bebd6990aa3960c8d2d7996f31114f444504d4cfc324bec3e7b629

See more details on using hashes here.

Provenance

The following attestation bundles were made for maverick_agent-0.1.2.tar.gz:

Publisher: publish.yml on cdayAI/Maverick

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

File details

Details for the file maverick_agent-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: maverick_agent-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 587.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for maverick_agent-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 1e262d9ec65d36372e258ef3a8ac8466f37ea3b4dd9684778884d39bc0007c93
MD5 cbf2a67845d080ea80b47c4ae23dfc10
BLAKE2b-256 201a5e579fa4a187619471e3afaa92d9b168e65c4b9d0e749b996ae8423d0fb5

See more details on using hashes here.

Provenance

The following attestation bundles were made for maverick_agent-0.1.2-py3-none-any.whl:

Publisher: publish.yml on cdayAI/Maverick

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