Code Craft AI Agent Kit
The codecraftai-agent-kit is a Python SDK for building cross-platform AI agents. It provides a unified framework for agent development that works across cloud providers (AWS, Azure, GCP) and local environments. The SDK covers the full agent development lifecycle — from agent identity and state management through LLM integration, tool invocation, workflow orchestration, observability, and cross-platform deployment.
Highlights
Agent lifecycle management, identity, and a state machine with hierarchical composition under agentkit/.
Cross-platform runtime with platform adapters (AWS, Azure, GCP, local) under agentkit/platform/.
Pluggable transports (HTTP, WebSocket, gRPC, message queues) and agent-to-agent messaging under agentkit/transports/.
Tool registration, built-in tools, and custom tool development API under agentkit/builtins/ and agentkit/steps/.
Multi-provider LLM integration with prompt templates, structured-output parsing, and streaming support.
Memory and context management, workflow orchestration (DAG-based), observability, and security primitives.
Repository Structure
development/ - Runtime environment scripts.
repository-setup/ - Repository homing and setup scripts.
source/packages/ - Package source code.
source/testroots/ccai/ - TestBase test roots.
source/examples/ - Example agent definitions.
specs/ - Requirements, design, and task documentation organised by feature area.
userguide/ - Standards, conventions, and documentation.
Environment Setup
When working in a Codex container:
./development/setup-agent-containerFor local development:
./repository-setup/rehome-repository
./development/setup-envrionmentRunning Tests
Activate the virtual environment:
source .venv/bin/activateRun the single-host test suite:
testbase testing run --root source/testroots/ccai --includes=ccai.tests.singlehost.agentkit --output=./.outputStandards and Conventions
Naming conventions: userguide/10-02-naming-conventions.rst
Code organization: userguide/10-01-code-organization.rst
Coding standards: userguide/10-00-coding-standards.rst
Additional Resources
User guide entry point: userguide/userguide.rst
Specifications: specs/core-agent-framework/, specs/llm-integration/, specs/communication-messaging/
1 maintainer
Metadata
1 maintainer
Release files for codecraftai-agent-kit 1.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| codecraftai_agent_kit-1.3.0.tar.gz | 276.4 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| codecraftai_agent_kit-1.3.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 688.2 kB
Release files / codecraftai_agent_kit-1.3.0.tar.gz
| Download URL | codecraftai_agent_kit-1.3.0.tar.gz |
|---|---|
| Size | 276.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7d2aa6929d91ff63f3e1846c57260b03bc8ddf3212507a5b5bb838de9fe54851
|
|
BLAKE2b-256 checksum How to use checksums |
cc0f2a1248767c2b8e985960a9d9cb39711678fbee1450475c3a65cb3a08aa89
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / codecraftai_agent_kit-1.3.0-py3-none-any.whl
| Download URL | codecraftai_agent_kit-1.3.0-py3-none-any.whl |
|---|---|
| Size | 411.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7a937b4b312da048c1117592e1a722437647b011707b1a2b68c549a8c3c6c08d
|
|
BLAKE2b-256 checksum How to use checksums |
1aa39c6f56e520d27e3414a07ca4f5a3601833c41ee79196850a475701b4715e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logSecurity for codecraftai-agent-kit 1.3.0
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for codecraftai_agent_kit-1.3.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logA 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.
