Skip to main content

🛡️ ProofCore Protocol

The Cryptographic Notarization & Evidence Layer for the AI & M2M Economy

TON Blockchain Python OpenAPI 3.1 llms.txt License: MIT

"Don't trust ProofCore. Verify the proof yourself."

🌐 Website • 📖 OpenAPI Spec • 🤖 llms.txt • 📱 Telegram Bot


⚡ The Problem & The Solution

In the era of autonomous AI agents, digital trust is broken:

  • Denial of Generation: AI outputs can be secretly altered or deleted.
  • Fabricated Hallucinations: Screenshots of LLM predictions and contract audits can easily be faked.
  • Centralized Vulnerability: Traditional notarization APIs require manual API keys, subscriptions, and trusting a single server's timestamp.

ProofCore is a high-throughput, Zero-Auth M2M Protocol that cryptographically commits digital outputs into The Open Network (TON) Blockchain via Merkle Tree batching. It delivers mathematical Proof-of-Existence (PoE) and verifiable provenance without storing private user keys.

┌────────────────┐     POST /api/v0.1/seal     ┌────────────────┐
│ Autonomous AI  │ ──────────────────────────> │   ProofCore    │
│ Agent / LLM    │ <────────────────────────── │   API Gateway  │
└────────────────┘    Instant Citation Badge   └───────┬────────┘
                                                       │
                                            SHA-256 Merkle Batching
                                                       │
                                                       ▼
                                            ┌────────────────────┐
                                            │   TON Blockchain   │
                                            │ (Immutable Anchor) │
                                            └────────────────────┘

🚀 Developer Integrations & SDK

Zero-Auth Cryptographic Notarization API for AI Agents & Autonomous Systems The easiest way to interact with the TON Blockchain and seal your data is to use our official Python package.

📦 Installation

pip install proofcore

(For specific AI frameworks, use pip install proofcore[langchain] or pip install proofcore[crewai])


🤖 1. LangChain Agent Integration

from langchain_openai import ChatOpenAI
from langchain.agents import initialize_agent, AgentType
from proofcore.langchain import ProofCoreSealerTool

# 1. Init LLM and our official drop-in tool
llm = ChatOpenAI(model="gpt-4o")
tools = [ProofCoreSealerTool()]

# 2. Run the agent
agent = initialize_agent(tools, llm, agent=AgentType.OPENAI_FUNCTIONS, verbose=True)

# The agent will write the audit, call the tool, and give you the verification link!
response = agent.run("Write a short security audit for an ERC-20 token and notarize it.")
print(response)

🕵️ 2. CrewAI Integration

from crewai import Agent, Task, Crew
from proofcore.crewai import ProofCoreCrewTool

notary_tool = ProofCoreCrewTool()

auditor = Agent(
    role="Smart Contract Security Auditor",
    goal="Audit contract code and cryptographically seal the final verdict on-chain.",
    backstory="You are an autonomous auditor specializing in Web3 security.",
    tools=[notary_tool]
)

# CrewAI agent will automatically use the tool to anchor the report

🐍 3. Pure Python (The Lazy Way)

No frameworks? No problem. ProofCore is a Zero-Auth API. You don't need API keys or registration.

import proofcore
import time

# Step 1: Create a Proof
print("Sealing data...")
deal = proofcore.seal(
    content="Autonomous System Prediction: BTC > $150k before Q4 2026.",
    agent_id="python-script-v1",
    title="Market Forecast"
)

print(f"Deal ID: {deal['deal_id']}")
print(f"Badge: {deal['citation']}")

# Step 2: Check Blockchain Status
while True:
    status_data = proofcore.get_proof(deal['deal_id'])

    if status_data.get("status") == "anchored_onchain":
        print("✅ SUCCESS! Anchored to TON Blockchain.")
        print(f"Merkle Root: {status_data['merkle_root']}")
        print(f"TON TX Hash: {status_data['ton_tx_hash']}")
        break

    print("⏳ Still in queue. Checking again in 60 seconds...")
    time.sleep(60)

🛡️ How to Verify the Proof Offline?

ProofCore is built on the philosophy: "Don't trust us. Verify it yourself."

The get_proof() method returns all the data required for independent verification. You can easily reconstruct the Merkle Tree and compare the resulting root against the public TON Blockchain without ever trusting our servers.

Check out the full OpenAPI Specification and Mathematical Algorithm at proofcore.org/openapi.json.

Metadata

Release files for proofcore 0.1.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for proofcore 0.1.3
File Size Uploaded Provenance Actions
proofcore-0.1.3.tar.gz 5.4 kB Without provenance Details for proofcore-0.1.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for proofcore 0.1.3
File Interpreter ABI Platform Actions
proofcore-0.1.3-py3-none-any.whl Python 3 none any Details for proofcore-0.1.3-py3-none-any.whl

Total release size: 11.9 kB

Release files / proofcore-0.1.3.tar.gz

Download URL proofcore-0.1.3.tar.gz
Size 5.4 kB
Tags Source
SHA-256 checksum
How to use checksums
2fa23db16f8fa148e2bbea413876f996c48d1fcd7aa24afffcf21b9dc45d39c7
BLAKE2b-256 checksum
How to use checksums
fb83eabde3461b0647bd80c1acc1e65a2dc8c98acfffb85add41c1849950bf13
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.6

Release files / proofcore-0.1.3-py3-none-any.whl

Download URL proofcore-0.1.3-py3-none-any.whl
Size 6.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c384b35a4e2a1ce84580dd0116777620e86864e845ab7b809ebd2e60458b65f2
BLAKE2b-256 checksum
How to use checksums
f27cc633baf4e6fc425752a85ef40769d1dc69577545257267d5de6cdcb1e38e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.6

Security for proofcore 0.1.3

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.

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