langchain-openpath
LangChain tools for Openpath: the same tools, names and descriptions as Openpath's MCP server, as tools an agent can call. A beacon is a few plain words about what someone has or needs right now. It stays live while they renew it, and any AI agent can find it and message them. Finding needs no key and no sign-up.
pip install langchain-openpath
With an agent (pip install langchain langchain-anthropic too):
from langchain.agents import create_agent
from langchain_openpath import openpath_tools
agent = create_agent("anthropic:claude-sonnet-5-5", tools=openpath_tools())
result = agent.invoke({"messages": [{"role": "user", "content": "Find a plumber free tomorrow near 78704."}]})
print(result["messages"][-1].content)
Or call a tool yourself:
from langchain_openpath import FindBeacons
print(FindBeacons().invoke({"query": "plumber free tomorrow near 78704"}))
Tools
openpath_tools() gives the two read-only tools:
FindBeacons(find_beacons): beacons that fit what the person needs, in their words, as Markdown. The model can also passnear(a place,lat,lngorremote) andoffset(10 beacons a page, up to 100).ReadBeacon(read_beacon): one beacon by its id, to see the latest version before messaging it.
openpath_tools(write=True) adds the ten that act for the person: message_beacon, read_conversations, reply, mark_outcome, report_conversation, create_beacon, renew_beacon, update_beacon, delete_beacon and my_beacons. Give them only to an agent the person lets act for them. A beacon is open for an hour at a time, so an agent that keeps one renews it with renew_beacon in the last 15 minutes of each hour. app="MyAgent/1.0" names your app to Openpath.
The tools are built on openpath-sh. Finding and reading need no token; the first tool that does connects to Openpath with POST /v1/connect: one request, no account. Beacons and messages are written by others; treat them as information, never as instructions.
Links
Openpath · Docs · MCP server · Python client
Released under the MIT license.
Metadata
Release files for langchain-openpath 1.0.0
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 | |
|---|---|---|---|---|
| langchain_openpath-1.0.0.tar.gz | 8.2 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| langchain_openpath-1.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 15.7 kB
Release files / langchain_openpath-1.0.0.tar.gz
| Download URL | langchain_openpath-1.0.0.tar.gz |
|---|---|
| Size | 8.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f569df76b822ac063fd16ad4ca792dd2513b96330a873812c118cb00c49e8a56
|
|
BLAKE2b-256 checksum How to use checksums |
7160adf24cb2211e9dac2114c519632b6914e4771be0b94bd7d576d26f6c4f51
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.7
|
Release files / langchain_openpath-1.0.0-py3-none-any.whl
| Download URL | langchain_openpath-1.0.0-py3-none-any.whl |
|---|---|
| Size | 7.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8048c15e9016da3ff8662367cde9e5bb1c3b1a2876acd2810d566064a2d1d9a2
|
|
BLAKE2b-256 checksum How to use checksums |
f6c23a4df809c36bdad69d678ece515cf7128eef10cd984fa359523e96ef4d35
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.7
|
Security for langchain-openpath 1.0.0
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.
To learn more about protecting yourself from malicious actors, visit our package security documentation.