A bundle is the sandbox’s world: your project, Agentix, integration packages, transitive Python dependencies, and optional system binaries in one bundle. agentix build [path] takes a normal Python project and produces a deploy-ready Docker image. 
agentix build ./my-rollout -o my-rollout:0.1.0

​
What Goes In

Agentix does not maintain a separate plugin manifest. The project’s pyproject.toml is the manifest. 
[project]
name = "my-rollout"
version = "0.1.0"
dependencies = [
    "agentixx>=0.1.0",
    "agentix-runtime-basic>=0.1.0",
    "agentix-claude-code>=0.1.0",
    "agentix-swebench>=0.1.0",
]
During the build, Agentix copies the project into the image and runs one install into the runtime environment: 
/nix/runtime/bin/pip install --no-cache-dir /src/project
That single install brings in user code, direct dependencies, transitive dependencies, and integration modules such as agentix.bash or agentix.swebench.

​
Runtime Layout

/nix/runtime/
├── bin/
│   ├── python
│   ├── pip
│   └── agentix-server
└── lib/python3.11/site-packages/
    ├── agentix/
    ├── agentix/bash/
    ├── agentix/swebench/
    └── app.py
The runtime server and worker use this same environment. If the worker can import a module from that environment, the host can call it with client.remote(fn, ...).

​
System Binaries

If the project root includes default.nix, agentix build adds a Nix builder stage. The derivation closure is copied into the final image, and binaries are linked under /nix/runtime/bin. Worker subprocesses inherit the runtime server’s environment, with the bundle venv and Nix runtime bins prepended to PATH: 
/nix/runtime/venv/bin:/nix/runtime/bin:${PATH}
That is how CLI wrappers can call tools by name: 
await asyncio.create_subprocess_exec("git", "status")
await asyncio.create_subprocess_exec("claude", "-p", instruction)

​
Bundles Compose Integrations

Agent wrappers, dataset scorers, sandbox primitives, and application code are all normal Python packages. A rollout bundle chooses which packages coexist in one sandbox.
Package typeExampleWhy include it
FrameworkagentixxRuntime client/server protocol and worker invocation
Primitiveagentix-runtime-basicShell and file operations in the sandbox
Agent wrapperagentix-claude-codeCLI execution behind a typed Python function
Scorer wrapperagentix-swebenchBenchmark grading behind a typed Python function
User projectmy-rolloutOrchestration-specific functions and dependencies

​
Mental Model

Bundle = what exists in the sandbox
Remote call = which installed function runs
Deployment = where the image is started
Keep those concerns separate and the same integration can move from a local smoke test to a larger rollout system without changing its Python API.