taco-agent
The Python SDK for TACO — The A2A Construction Open-standard: an open vocabulary that lets construction AI agents hand work to each other. TACO adds typed task types, typed data schemas and discovery by trade and CSI division on top of the A2A protocol (Linux Foundation). Every TACO agent is a standard A2A agent.
pip install taco-agent[all]
Expose an agent
from taco import ConstructionAgentCard, ConstructionSkill
card = ConstructionAgentCard(
name="My Mechanical Takeoff Agent",
trade="mechanical",
csi_divisions=["22", "23"],
skills=[
ConstructionSkill(
id="generate-bom",
task_type="takeoff",
output_schema="bom-v1",
)
],
)
# Serve the agent card for discovery
card.serve(host="0.0.0.0", port=8080)
Discover and call agents
from taco import TacoClient, AgentRegistry, extract_structured_data
registry = AgentRegistry()
await registry.register("http://estimator:8001")
agents = registry.find(trade="mechanical", task_type="estimate")
async with TacoClient(agent_url=agents[0].url) as client:
task = await client.send_message("estimate", bom_data)
estimate = extract_structured_data(task.artifacts[0].parts[0])
Learn more
- Documentation: https://taco-protocol.com
- Specification, schemas and task types: https://github.com/pelles-ai/taco/tree/main/spec
- Source and issues: https://github.com/pelles-ai/taco
- Changelog: https://github.com/pelles-ai/taco/blob/main/CHANGELOG.md
Apache 2.0. Initiated by Pelles.
1 maintainer
Release files for taco-agent 0.3.17
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| taco_agent-0.3.17.tar.gz | 39.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| taco_agent-0.3.17-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 88.4 kB
Release files / taco_agent-0.3.17.tar.gz
| Download URL | taco_agent-0.3.17.tar.gz |
|---|---|
| Size | 39.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
57513204de16895ec45ed8baf497106458f62e7e77ea69dd387b3b0742a570ab
|
|
BLAKE2b-256 checksum How to use checksums |
4091c1a33ac204047e8289b1c27e9914a937e4ff97663f0b4fef64d875cc0e45
|
| 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 Sep 23, 2026.
Transparency logRelease files / taco_agent-0.3.17-py3-none-any.whl
| Download URL | taco_agent-0.3.17-py3-none-any.whl |
|---|---|
| Size | 48.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6c8f154f7cd5b81e7db4308067b9c21ba1f3d0a2795762e57410a0d7011c9149
|
|
BLAKE2b-256 checksum How to use checksums |
44a6ca5244e6f73e2265608146399a58e9faa9ede3f7f1ab4877c4827c9e8917
|
| 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 Sep 23, 2026.
Transparency log
