Skip to main content

Mirror Frame Protocol — symmetric frame envelope for LLM agent communication

Project description

Mirror Frame Protocol (MFP)

Symmetric frame envelope for LLM agent communication

MFP is a protocol and runtime for secure, peer-to-peer communication between autonomous agents. It provides end-to-end encrypted channels, federated message transport, and a minimal API for agent lifecycle management.

Features

  • Symmetric design — no client/server distinction, all agents are peers
  • End-to-end encryption — ChaCha20-Poly1305 AEAD with X25519 key exchange
  • Federation-ready — bilateral channels, recovery protocols, TCP transport
  • Production hardening — circuit breakers, timeouts, health checks, metrics
  • High performance — Merkle tree for O(log N) global state updates
  • Library-first — runtime embeds in any Python process
  • Standalone server — YAML-configured process for managing agents
  • Type-safe — full type annotations with py.typed marker

Installation

pip install pymfp

Or install from source:

git clone https://github.com/Madahub-dev/MFP.git
cd MFP
pip install -e .

Quickstart

5-minute hello world between two agents:

from mfp import Runtime, RuntimeConfig, bind, mfp_send, mfp_channels

# Create a runtime
config = RuntimeConfig()
runtime = Runtime(config)

# Define two simple agent callables
def alice(channel_id, message):
    print(f"Alice received: {message.decode()}")
    return {"status": "ok"}

def bob(channel_id, message):
    print(f"Bob received: {message.decode()}")
    return {"status": "ok"}

# Bind agents to the runtime
alice_handle = bind(runtime, alice)
bob_handle = bind(runtime, bob)

# Establish a channel between them
alice_handle.establish_channel(bob_handle.agent_id, symmetric_key=None)

# Send a message from Alice to Bob
channels = mfp_channels(alice_handle)
channel_id = channels[0].channel_id

receipt = mfp_send(
    alice_handle,
    channel_id=channel_id,
    plaintext=b"Hello from Alice!"
)

print(f"Message sent, receipt: {receipt.message_id.hex()[:16]}...")

# Shutdown
runtime.shutdown()

Run this script to see agents communicate through MFP channels.

Architecture

┌─────────────────────────────────────────────────────────────┐
│                        Application                          │
└─────────────────────────────────────────────────────────────┘
                            │
                            ▼
┌─────────────────────────────────────────────────────────────┐
│  Public API: Runtime, bind/unbind, mfp_send/channels/status │
└─────────────────────────────────────────────────────────────┘
                            │
        ┌───────────────────┼───────────────────┐
        ▼                   ▼                   ▼
   ┌─────────┐         ┌─────────┐        ┌──────────┐
   │ Runtime │◄────────┤  Agent  │◄───────┤ Storage  │
   │ Pipeline│         │Lifecycle│        │  Engine  │
   └─────────┘         └─────────┘        └──────────┘
        │                                       │
        ▼                                       ▼
   ┌─────────┐                            ┌──────────┐
   │  Core:  │                            │Federation│
   │ Crypto, │                            │Transport │
   │ Frames  │                            └──────────┘
   └─────────┘

Layers:

  • Core — cryptographic primitives, frame construction/validation
  • Runtime — agent callable pipeline, hooks, error handling
  • Agent — lifecycle management (bind/unbind), tool interface
  • Storage — persistent state, message queues, channel records
  • Federation — bilateral channels, recovery, wire protocol, TCP server

Documentation

CLI Usage

Launch the standalone server:

mfp-server --config runtime.yaml

Or using Python module syntax:

python -m mfp --config runtime.yaml

Development

Set up development environment:

# Clone and install with dev dependencies
git clone https://github.com/Madahub-dev/MFP.git
cd MFP
pip install -e ".[dev]"

# Run tests
pytest

# Run tests with coverage
pytest --cov=mfp --cov-report=term-missing

Project Status

Version: 0.4.0 (Production Ready)

All implementation phases complete including production hardening:

  • ✅ P0: Critical Security
  • ✅ P1: Operational Robustness (logging, health checks, metrics, limits)
  • ✅ P2: Performance Optimization (Merkle tree, circuit breakers, timeouts, pooling)
  • ✅ P3: Advanced Hardening (frame caching, key rotation, deduplication)

Test Coverage: 813 tests passing (591 unit, 191 integration, 27 E2E, 4 benchmark)

License

Apache License 2.0 — see LICENSE for details.

Credits

MFP — authored by Akil Abderrahim and Claude Sonnet 4.5


For protocol design documentation, see design/.

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

pymfp-0.1.0.tar.gz (92.7 kB view details)

Uploaded Source

Built Distribution

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

pymfp-0.1.0-py3-none-any.whl (79.9 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: pymfp-0.1.0.tar.gz
  • Upload date:
  • Size: 92.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.9

File hashes

Hashes for pymfp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 9cff83739bbc70ae1c418c428e2d57115e504bcba9ba374715c4fce688a334e5
MD5 92d59b1b6875c796d4ef87dd750871ba
BLAKE2b-256 ea960c128ef4516ca02f43b6b488f8bdeb48ab1ce446b9ddd63184ce9161a807

See more details on using hashes here.

File details

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

File metadata

  • Download URL: pymfp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 79.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.9

File hashes

Hashes for pymfp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 076bc23a82257aba3c44d7390f809f0f274991c5e22ad7c2447bf8ea4e4f7bba
MD5 f3ab0b286dfa97ff5ab7682bbc2b4427
BLAKE2b-256 c61c1563abd20e23cb18d6e701bc73131efa3a4fdd6d9c9597b9647a3fc29922

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