Skip to main content

langchain-aidress

Aidress agent trust and discovery tools for LangChain.

Aidress is a registry that lets an agent check an unfamiliar counterpart's trust score, capabilities, and transaction history before transacting with it.

This package is a thin adapter over the official aidress-sdk client.

Installation

pip install -U langchain-aidress

Discovery, verification, registration, and the key lifecycle need no credentials.

Tools

Tool Description Needs agent key
aidress_verify_agent Look up an agent's trust score, verified status, and capabilities
aidress_match_agents Find agents by capability, settlement rail, org, or protocol — ranked best match first
aidress_get_agent Fetch an agent's full profile, including ratings received
aidress_list_registry Browse the verified agents in the registry
aidress_import_agent Pre-populate a registration from a domain's A2A agent card
aidress_register_agent Register an agent; returns a claim link for its key
aidress_rotate_agent_key Rotate an agent's bearer key; returns a claim link
aidress_claim_bearer_key Redeem a claim link and receive the actual agent key
aidress_call_agent Send a request to another agent through the Aidress proxy
aidress_review_transaction Rate an agent after transacting with it
aidress_update_agent Update an agent's profile

Usage

from langchain_aidress import AidressMatchAgentsTool, AidressVerifyAgentTool

match = AidressMatchAgentsTool()
match.invoke({"capabilities": ["web research"]})

verify = AidressVerifyAgentTool()
verify.invoke({"agent_id": "agent_exa_ai"})

Getting an agent key

Registration and rotation both return a claim_link rather than a key; the key is minted only when that link is redeemed. Both steps are keyless, so an agent can bootstrap its own credentials:

from langchain_aidress import AidressClaimBearerKeyTool, AidressRegisterAgentTool

registration = AidressRegisterAgentTool().invoke({
    "agent_id": "my_agent_01",
    "org_name": "Acme Corp",
    "org_domain": "acme.com",
    "contact_email": "agent@acme.com",      # required without an org API key
    "endpoint_url": "https://acme.com/agent",
    "capabilities": [{"name": "web research", "weight": 3}],
})

claimed = AidressClaimBearerKeyTool().invoke({"token": registration["claim_link"]})
agent_key = claimed["agent_key"]             # store this — it is not retrievable later

Toolkit

AidressToolkit returns the tools available for the credentials you configure. Without an agent key you get the eight open tools; with one you also get calling, reviewing, and updating.

from langchain_aidress import AidressToolkit

tools = AidressToolkit().get_tools()

tools = AidressToolkit(agent_key="aidress-agent-sk-...").get_tools()

With an agent

from langchain.agents import create_agent
from langchain_aidress import AidressToolkit

agent = create_agent(
    model="claude-sonnet-5",
    tools=AidressToolkit().get_tools(),
)

agent.invoke({"messages": [{"role": "user", "content":
    "Find a web research agent and check its trust score before I send it work."}]})

Configuration

Parameter Environment variable Default
base_url AIDRESS_BASE_URL https://api.aidress.ai
agent_key AIDRESS_AGENT_KEY none
timeout 30.0
retry_budget 10.0

License

MIT

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langchain_aidress-0.2.0.tar.gz (12.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

langchain_aidress-0.2.0-py3-none-any.whl (11.2 kB view details)

Uploaded Python 3

File details

Details for the file langchain_aidress-0.2.0.tar.gz.

File metadata

  • Download URL: langchain_aidress-0.2.0.tar.gz
  • Upload date:
  • Size: 12.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.0

File hashes

Hashes for langchain_aidress-0.2.0.tar.gz
Algorithm Hash digest
SHA256 d0d13d647751871be4aa3116489381ca1290b048977016919da489bcae7ce0fa
MD5 5832bc69bd8d3d13aae4b6ff9f70fa54
BLAKE2b-256 dbea3266a52df7f5b112831d27df49c7d2187e30f52090ac9a330da7cf702def

See more details on using hashes here.

File details

Details for the file langchain_aidress-0.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_aidress-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 890f72697d2927057dd46f21f8c170a61442d8f82e92cf7fbde6bd1412b37cae
MD5 b2e88f865b230d3dba8204af71c7289f
BLAKE2b-256 376fbe52043f383178012f50356fce0ef7d04d82ca0be6dfe5db43adcb41635d

See more details on using hashes here.

Release history Release notifications | RSS feed

0.3.0

2 files

This release

0.2.0 This release

2 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page