aimarket-orchestrator
Documentation
| Document | Description |
|---|---|
| User guide | Install, configure, verify plugin is loaded |
| User cases | Personas and cross-plugin workflows |
| SDK integration | Code examples and hook behavior |
The planner IS a capability. Priced at 1% of total spend. External agents send NL tasks. Orchestrator selects the capability chain, negotiates prices, executes, and returns a signed Bill of Materials. You sell the brain, not just the muscles.
When to Use
- External agents with "empty head" — just send NL task, get result + BOM
- Complex multi-step workflows requiring capability chaining
- Consumer who doesn't know which capabilities exist — orchestrator plans for them
- Monetization: orchestrator earns 1% of every routed dollar in the ecosystem
Installation
pip install aimarket-orchestrator
Example
from aimarket_orchestrator.orchestrator_capability import Orchestrator
orch = Orchestrator(orchestration_fee_pct=0.01)
caps = [
{"capability_id": "translate.multi@v2", "product_id": "p1", "name": "translate",
"price_per_call_usd": 0.40, "p50_latency_ms": 8100},
{"capability_id": "legal.review@v1", "product_id": "p2", "name": "legal",
"price_per_call_usd": 1.20, "p50_latency_ms": 11400},
]
plan = orch.plan("translate contract to French then legal review", budget_usd=3.0,
available_capabilities=caps)
print(f"Steps: {len(plan.steps)}, Est: ${plan.estimated_total_usd:.2f}")
print(f"Orchestration fee: ${plan.orchestration_fee_usd:.4f} (1%)")
def mock_invoke(pid, cid, inp):
return {"success": True, "result": {"output": f"done {cid}"}, "price_usd": 0.40}
result = orch.execute_plan(plan, mock_invoke)
print(result["bill_of_materials"])
print(f"Tasks completed: {orch.stats()['tasks_completed']}")
print(f"Total fees earned: ${orch.stats()['total_fees_earned_usd']:.4f}")
Pricing
Default 1% of total invocation spend. Configurable at init: Orchestrator(orchestration_fee_pct=0.02) for 2%.
License
MIT · Maintained by AI-Factory
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file aimarket_orchestrator-2.0.0.tar.gz.
File metadata
- Download URL: aimarket_orchestrator-2.0.0.tar.gz
- Upload date:
- Size: 4.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
520c355ca5b556184b52da5991930e172c818c50c6e5f29f6993457089994061
|
|
| MD5 |
792073a053895c2d724087ea3653ef0f
|
|
| BLAKE2b-256 |
3732d3acc3b87eaa1b2fb9a39d395c635d70f0b23d24f3ba2d370b81b361fcbb
|
File details
Details for the file aimarket_orchestrator-2.0.0-py3-none-any.whl.
File metadata
- Download URL: aimarket_orchestrator-2.0.0-py3-none-any.whl
- Upload date:
- Size: 5.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2e7ccc383e9e0066c41dc2de33961ef70cc4eb353b1e70e02cd73942dbb41dd8
|
|
| MD5 |
ff120f71313bbb4d0a175f43b058ab10
|
|
| BLAKE2b-256 |
41cecc1ee3fe78077798559774b9ccdc38aa0afa94bce4a6fbb0149d2be9cdc6
|