AgentWrap
Wrap agents, ship APIs - Turn agent CLIs into libraries and OpenAI-compatible servers
Prerequisites
CodexAgent requires the OpenAI Codex CLI to be installed:
npm install -g @openai/codex
Note: Unlike the TypeScript package which bundles Codex as a dependency, Python cannot auto-install Node.js CLI tools. You must install Codex globally.
📚 Detailed installation guide: See docs/codex-installation-guide.md for platform-specific instructions, Docker setup, and troubleshooting.
Installation
pip install agentwrap
Quick Start
from agentwrap import CodexAgent, OpenAICompatibleServer
# Create and configure agent
agent = CodexAgent()
agent.configure({
"agent_config": {"type": "codex-agent", "api_key": "OPENA_API_KEY"},
"skills": [
{"type": "anthropic-skill", "path": "./skills/random"}
]
})
# Use as library
for event in agent.run("Generate a random number for me"):
print(event)
# Or start as OpenAI-compatible API server
server = OpenAICompatibleServer(agent)
await server.start_http_server({"port": 8000})
Features
- 🤖 Wrap agent CLIs as Python libraries
- 🔌 OpenAI-compatible API server
- 🛠️ Function calling support
- 📦 MCP (Model Context Protocol) integration
- 🔄 Streaming responses
Documentation
For full documentation, visit: https://github.com/dashi0/agentwrap
License
MIT
Metadata
Release files for agentwrap 0.1.1
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 | Actions |
|---|---|---|---|---|
| agentwrap-0.1.1.tar.gz | 40.1 kB | Without provenance | Details for agentwrap-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentwrap-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for agentwrap-0.1.1-py3-none-any.whl |
Total release size: 78.1 kB
Release files / agentwrap-0.1.1.tar.gz
| Download URL | agentwrap-0.1.1.tar.gz |
|---|---|
| Size | 40.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
65b22e1ab6884e6a815c2b43ee6883b600d627af4e90cc9150ef13480bcd6159
|
|
BLAKE2b-256 checksum How to use checksums |
648ed16b7839959d61178e3a33e4757b84e790d5ca3f677f2332ec2257b0bb84
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / agentwrap-0.1.1-py3-none-any.whl
| Download URL | agentwrap-0.1.1-py3-none-any.whl |
|---|---|
| Size | 38.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5cbfc97a285364ede9a9b78a6d66f43d60b06a1f0c80a89ca94f31a0ff0d24bc
|
|
BLAKE2b-256 checksum How to use checksums |
bd4759bca20b28b652266f375bcd1773be86cc94273ff2a0ea661992316aab4a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Security for agentwrap 0.1.1
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.