Skip to main content

a2o-cortex

The Cortex CLI: governed coding-agent sessions from your terminal.

pip install a2o-cortex
cortex code

cortex code wraps a coding harness (OMP by default; Claude Code, Codex and OpenCode are also supported) in a Cortex governance session: every tool call is routed through a local policy bridge that gates shell, file-write, network and package-install actions against the session's policy, keeps writes inside the workspace, and audits what the agent did.

  • cortex code — launch a governed session in the current directory (default omp, main anthropic/claude-opus-5-5, advisor openai-codex/gpt-6.1-sol, both high).
  • cortex code --harness claude|codex|opencode --model <id> — pick a harness and model.
  • cortex setup — save your preferred harness, model and policy so a bare cortex code uses them.
  • cortex code --dry-run — print the resolved launch without starting the harness.
  • cortex code --effort medium|high|xhigh — override reasoning for the main and advisor.
  • cortex code --create my-app "Build ..." — unpack the owned template, run make setup, then adapt it.
  • /create in an OMP session — interactive project-creation wizard or /create name goal.

The bundled template includes pinned engineering/design skills and general video/animation guidance. Task-specific skills and MCPs are selected and verified during adaptation, not installed as a dormant catalog. Project setup requires Git and make; a compatible Node/npm runtime is provisioned when missing. Model inference requires your authenticated provider accounts. Existing directories are never overwritten by --create, and setup/adaptation failures are reported rather than labeled complete.

Requires Python 3.12+ and the harness binary you want to wrap on PATH. The wheels ship compiled bytecode only.

Metadata

Release files for a2o-cortex 0.5.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for a2o-cortex 0.5.1
File Interpreter ABI Platform Actions
a2o_cortex-0.5.1-cp314-none-any.whl CPython 3.14 none any Details for a2o_cortex-0.5.1-cp314-none-any.whl
a2o_cortex-0.5.1-cp313-none-any.whl CPython 3.13 none any Details for a2o_cortex-0.5.1-cp313-none-any.whl
a2o_cortex-0.5.1-cp312-none-any.whl CPython 3.12 none any Details for a2o_cortex-0.5.1-cp312-none-any.whl

Total release size: 3.4 MB

Release files / a2o_cortex-0.5.1-cp314-none-any.whl

Download URL a2o_cortex-0.5.1-cp314-none-any.whl
Size 1.2 MB
Tags CPython 3.14
SHA-256 checksum
How to use checksums
bc5d5ebedd232343b05ed30e52e99169ab1b38dd32b8f6178168c7e52dbc89b3
BLAKE2b-256 checksum
How to use checksums
85ed08fbad51df4842f11aba522f1fc30453db62859fbc49865f50a9e738e96d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Release files / a2o_cortex-0.5.1-cp313-none-any.whl

Download URL a2o_cortex-0.5.1-cp313-none-any.whl
Size 1.1 MB
Tags CPython 3.13
SHA-256 checksum
How to use checksums
e155a5323024fd1223805cdb276a539ac2f36b574f133f562fd823f73890b033
BLAKE2b-256 checksum
How to use checksums
55a6d451be33dad37089b09b9b64463ebb8049f17a241bc9b8b2df9675423cbb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Release files / a2o_cortex-0.5.1-cp312-none-any.whl

Download URL a2o_cortex-0.5.1-cp312-none-any.whl
Size 1.1 MB
Tags CPython 3.12
SHA-256 checksum
How to use checksums
14a88e55affd9839fd83fbde510dad439f8c19a28db361ff0bb3a48b226c3c97
BLAKE2b-256 checksum
How to use checksums
0312875f26c46b8ba6d749d87851a3d6413a5377334a365cedf35b218398c2c9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Security for a2o-cortex 0.5.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page