Skip to main content

AFM (Agent-Flavored Markdown) interpreter using LangChain

Project description

AFM LangChain Interpreter

A LangChain-based reference implementation of an interpreter for Agent-Flavored Markdown (AFM) files.

Features

  • Support for all interface types:
    • Console chat (interactive CLI)
    • Web chat (HTTP API + optional UI)
    • Webhook (WebSub-based event handling)
  • Multi-interface agents - run multiple interfaces simultaneously
  • MCP support for tools (Model Context Protocol)
  • Validation - dry-run mode to validate AFM definitions

Prerequisites

  • Python 3.12 or later.
  • uv for dependency management.
  • Docker (optional, for running via containers).

Quick Start

# Set your API Key
export OPENAI_API_KEY="your-api-key-here"

# Run with an AFM file using uv
uv run afm path/to/agent.afm.md

Configuration

Configuration via environment variables or CLI options:

  • OPENAI_API_KEY, ANTHROPIC_API_KEY, etc. (Required based on provider)
  • HTTP port can be set via -p or --port (default: 8000)

Running with Docker

# Build the image
docker build -t afm-langchain-interpreter .

# Run with an AFM file mounted and API key
docker run -v $(pwd)/path/to/agent.afm.md:/app/agent.afm.md \
  -e OPENAI_API_KEY=$OPENAI_API_KEY \
  -p 8000:8000 \
  afm-langchain-interpreter afm /app/agent.afm.md

Testing

uv run pytest

Project Structure

langchain-interpreter/
├── src/afm/
│   ├── interfaces/        # Interface implementations (console, web, webhook)
│   ├── tools/             # Tool support (MCP server)
│   ├── resources/         # Static assets (web UI)
│   ├── agent.py           # Core agent logic
│   ├── cli.py             # CLI entry point
│   ├── parser.py          # AFM file parsing
│   ├── models.py          # Model configuration
│   ├── providers.py       # LLM provider handling
│   └── templates.py       # Prompt templates
├── tests/                 # Unit and integration tests
├── Dockerfile             # Container build
├── pyproject.toml         # Python project configuration
└── uv.lock                # Dependency lock file

License

Apache-2.0

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

afm_py-0.1.3.tar.gz (30.3 kB view details)

Uploaded Source

Built Distribution

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

afm_py-0.1.3-py3-none-any.whl (38.3 kB view details)

Uploaded Python 3

File details

Details for the file afm_py-0.1.3.tar.gz.

File metadata

  • Download URL: afm_py-0.1.3.tar.gz
  • Upload date:
  • Size: 30.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for afm_py-0.1.3.tar.gz
Algorithm Hash digest
SHA256 e28fcf340c0931412dddc4f9199504c71af0aebd49a1c9a7a0869ddf8af16665
MD5 cb6754b7dc9806549fd8431687a8479a
BLAKE2b-256 13db9989bedc116f2617d21909a7e6076dcae55735902a9171013b0387e48439

See more details on using hashes here.

File details

Details for the file afm_py-0.1.3-py3-none-any.whl.

File metadata

  • Download URL: afm_py-0.1.3-py3-none-any.whl
  • Upload date:
  • Size: 38.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for afm_py-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 a6a45a6d350f2b558fa525d4696a280e302844320af8aad7ca76df8866a48647
MD5 c6ddf05304a8e847a8f08d914f789358
BLAKE2b-256 14301f19a646bcc87115b5a16a459d6b117d48080c731fc314583bba51d6aac0

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