scdo-agent-tools
Python and LangChain tools that give an agent an SCDO per-agent x402 wallet (USDC on Base, plus SCDO on the Agent Ledger), signed heartbeats and booked income. Free, MIT licence.
Quickstart
curl -fsSL https://scdo.com.au/downloads/wallet/linux/install.sh | sh -s -- --user # 1. install scdo-agent (https://scdo.com.au/linux-agent/)
pip install "scdo-agent-tools[langchain]" # 2. add the tools
python -c "from scdo_agent_tools import get_tools; print([t.name for t in get_tools()])" # 3. pass get_tools() to your agent
Until it is on PyPI: pip install "scdo-agent-tools[langchain] @ https://github.com/SCDOLAB/scdo-agent-plugins/releases/download/v0.1.0/scdo_agent_tools-0.1.0-py3-none-any.whl"
Full guide: https://scdo.com.au/linux-agent/
Tools: register_agent (bookkeeping node identity plus signed heartbeats), create_wallet, get_balance, pay_x402, book_income. Without LangChain, use scdo_agent_tools.ScdoAgent directly.
- Default network is Base mainnet; pass
network="base-sepolia"(orSCDO_AGENT_NETWORK=base-sepolia) for the test network. - Caps: 0.001 to 1 USDC per payment, 100 payments and 20 USDC per day. Mainnet payments to SCDO paywalls settle through
https://scdo.com.au/x402-base/; the facilitator pays gas. - Keys are kept by
scdo-agentin the local data dir and are never sent or printed.
Bulk onboarding (0.2.0)
pip install "scdo-agent-tools[bulk]", then run scdo-agent-bulk bots.csv --out out.csv. The scdo-agent CLI must be in ~/.scdo-agent/bin; the one-liner below installs it.
Or do everything in one step: curl -fsSL https://scdo.com.au/agent/install.sh | sh -s -- --bulk bots.csv.
name,operator,platform,label,email
rack-a,0xYourOperatorAddress,x,Support bot on X,
rack-b,,telegram,Telegram helper,
Each bot gets a local key (mode 0600, never printed), a signed Agent Ledger registration and a Base USDC x402 wallet. The output CSV has name, agent address, Base wallet, operator, platform, profile URL and status, and no secrets. Re-runs are idempotent and resume where they stopped.
Metadata
Release files for scdo-agent-tools 0.2.0
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 | |
|---|---|---|---|---|
| scdo_agent_tools-0.2.0.tar.gz | 13.6 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| scdo_agent_tools-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 27.9 kB
Release files / scdo_agent_tools-0.2.0.tar.gz
| Download URL | scdo_agent_tools-0.2.0.tar.gz |
|---|---|
| Size | 13.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8dd23b9e8bab9c2fdbd6ebf931664d1f4c43586d03c74a9ea53207ef2c135e56
|
|
BLAKE2b-256 checksum How to use checksums |
d7e1cfc9fe3b820523e26ba0ab277d79a5d643802989af9006129e87c5edb151
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.5
|
Release files / scdo_agent_tools-0.2.0-py3-none-any.whl
| Download URL | scdo_agent_tools-0.2.0-py3-none-any.whl |
|---|---|
| Size | 14.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
df7b381e2f671692db3e8ba08d9d275cc98f6d092d88bf526f38a730598287fb
|
|
BLAKE2b-256 checksum How to use checksums |
56efb52a17110ba94efc58df59e93f1bd926a3631229ee5bd92c7716657fa7d1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.5
|
Security for scdo-agent-tools 0.2.0
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.
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.