Skip to main content

LangChain tools for ENACT Protocol — trustless escrow for AI agents on TON

Project description

enact-langchain

LangChain tools for ENACT Protocol — trustless escrow for AI agents on TON. Wraps every method of enact-protocol as a langchain_core.tools.BaseTool.

Install

pip install enact-langchain

enact-protocol is pulled in automatically.

Quick Start (read-only explorer agent)

import asyncio
from enact_protocol import EnactClient
from enact_langchain import get_enact_tools
from langchain_anthropic import ChatAnthropic
from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_core.prompts import ChatPromptTemplate

async def main():
    client = EnactClient(api_key="YOUR_TONCENTER_KEY")

    tools = get_enact_tools(client)          # read-only (safe default)

    llm = ChatAnthropic(model="claude-haiku-4-5-20251001")
    prompt = ChatPromptTemplate.from_messages([
        ("system", "You are an explorer for ENACT Protocol on TON."),
        ("human", "{input}"),
        ("placeholder", "{agent_scratchpad}"),
    ])
    agent = create_tool_calling_agent(llm, tools, prompt)
    executor = AgentExecutor(agent=agent, tools=tools)

    result = await executor.ainvoke({"input": "How many TON jobs are on ENACT?"})
    print(result["output"])

    await client.close()

asyncio.run(main())

Enabling write tools

Every write tool broadcasts a real TON transaction — burning real TON (and, for jetton jobs, real USDT) on every call. Enable them explicitly:

client = EnactClient(
    mnemonic="word1 word2 ... word24",
    pinata_jwt="YOUR_PINATA_JWT",
    api_key="YOUR_TONCENTER_KEY",
)
tools = get_enact_tools(client, include_write=True)   # opt-in

Put a human-in-the-loop check in front of any write tool in production.

Tool catalog

Read (9): enact_get_wallet_address, enact_get_job_count, enact_get_jetton_job_count, enact_get_job_address, enact_list_jobs, enact_list_jetton_jobs, enact_get_job_status, enact_get_wallet_public_key, enact_decrypt_job_result.

Write TON (10): enact_create_job, enact_fund_job, enact_take_job, enact_submit_result, enact_submit_encrypted_result, enact_evaluate_job, enact_cancel_job, enact_claim_job, enact_quit_job, enact_set_budget.

Write USDT (3): enact_create_jetton_job, enact_set_jetton_wallet, enact_fund_jetton_job.

Links

License

MIT

Project details


Download files

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

Source Distribution

enact_langchain-0.1.0.tar.gz (7.7 kB view details)

Uploaded Source

Built Distribution

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

enact_langchain-0.1.0-py3-none-any.whl (9.2 kB view details)

Uploaded Python 3

File details

Details for the file enact_langchain-0.1.0.tar.gz.

File metadata

  • Download URL: enact_langchain-0.1.0.tar.gz
  • Upload date:
  • Size: 7.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for enact_langchain-0.1.0.tar.gz
Algorithm Hash digest
SHA256 7561249106a75516628aa8adf21e692805db005db3f0be22f428f1dc5af3f443
MD5 d98797f7c566e677601b4d657de46ef2
BLAKE2b-256 15bbb13fc68142b9354a7b35d8aadcc1bf9047fb61f103cf92ce8db876b1ded5

See more details on using hashes here.

File details

Details for the file enact_langchain-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for enact_langchain-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 47515783f5174a8e3114cf590fe9c17a6a9eb12073e424ac96756e71e8428333
MD5 84fd99aa3fd2c7a3a1c8c6d2c95c36b4
BLAKE2b-256 190071a965831d274a4c77da1873fd0202f424b258dd88eeaf79cb469c0b8da8

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page