Skip to main content

A protocol for autonomous LLM agents to navigate complex toolsets via semantic landmarks.

Project description

🌌 Elemm (Element Mapping) v2

Autonomous. Efficient. Reliable.

Elemm is a next-generation protocol for AI agents, designed to bridge the gap between static tool definitions and autonomous complex reasoning. It optimizes token consumption, reduces execution latency, and provides a robust self-healing framework for agentic workflows.


🚀 Key Features

  • Semantic Landmarks: Group tools into logical namespaces for better discovery.
  • High-Performance Sequencing: Execute multi-step chains in a single LLM turn.
  • SmartRepair Engine: Provide agents with actionable remedies for protocol errors.
  • Variable Piping: Seamless data flow between tools with zero-latency resolution.
  • Python-First Workflow: Define tools via decorators and Pydantic models with automatic schema generation.
  • Benchmark Proven: Up to 90% token savings and 70% fewer turns compared to standard MCP.

📚 Documentation


🏎️ Quick Start (The Easy Way)

  1. Install: pip install elemm
  2. Connect: Add mcp.py to your Claude Desktop config:
"elemm": {
  "command": "python3",
  "args": ["/path/to/elemm/examples/mcp.py", "http://localhost:8000"]
}

Note: Make sure your Elemm-powered site is running on port 8000.

⚖️ License

Copyright (C) 2026 Marc Stöcker. GPLv3 License. See LICENSE for details.

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

elemm-1.0.0.tar.gz (43.1 kB view details)

Uploaded Source

Built Distribution

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

elemm-1.0.0-py3-none-any.whl (48.1 kB view details)

Uploaded Python 3

File details

Details for the file elemm-1.0.0.tar.gz.

File metadata

  • Download URL: elemm-1.0.0.tar.gz
  • Upload date:
  • Size: 43.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for elemm-1.0.0.tar.gz
Algorithm Hash digest
SHA256 242c96febc6480c4265136c3283c67aa756f372c7c760f3757094d611f613cc2
MD5 4b8d9c90f01cace4140e7b48f545789d
BLAKE2b-256 27c641a1897c201448d9cde78df3cab429c2124903431288cd09265009525858

See more details on using hashes here.

Provenance

The following attestation bundles were made for elemm-1.0.0.tar.gz:

Publisher: workflow.yml on v3rm1ll1on/elemm

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file elemm-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: elemm-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 48.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for elemm-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d288a8984c61931a9df1212475ca9e9de713ff27645edaf9f58928c007053972
MD5 059b9bc86df8bc521d3455e6a80a5ef6
BLAKE2b-256 d33ebac3603fa1e57e756ca20e5da7b0a0927107140e3cf0b151412f85d5ebd6

See more details on using hashes here.

Provenance

The following attestation bundles were made for elemm-1.0.0-py3-none-any.whl:

Publisher: workflow.yml on v3rm1ll1on/elemm

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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