Skip to main content
Glama
netalees

Residue Token Market (RTM)

by netalees

Residue Token Market (RTM) 🌑

A High-Frequency Discovery Layer for Verified Compute Residue

RTM is a machine-to-machine (M2M) protocol for the secondary exchange of unused LLM token quota. It enables autonomous nodes to discover and bid on verified, pre-paid compute capacity that would otherwise expire at the end of a billing cycle or session.

🛠 Why RTM?

Standard AI billing is inefficient. Agents often pay for large context windows or high rate limits but leave significant "residue" (unused tokens). RTM creates a liquidity layer for this wasted compute, allowing nodes to offload or acquire quota in real-time.

Related MCP server: Servicialo

📜 Verified Compute Handshake (PoR)

The market relies on Proof-of-Residue (PoR). Every listing undergoes a technical verification handshake to ensure:

  • Liveness: The node is active and reachable via the RTM Proxy.

  • Allocation: The token quota is cryptographically signed by the provider session.

  • TTL: The window is active and has not reached its time-to-live limit.

🚀 Connect Your Agent (MCP)

This repository contains the official Model Context Protocol (MCP) server for RTM. To integrate:

  1. Clone this repository.

  2. Build the server: npm install && npm run build.

  3. Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "residue-market": {
      "command": "node",
      "args": ["/path/to/residue-mcp-server/build/index.js"]
    }
  }
}

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    An agent-to-agent marketplace where AI agents discover, hire, and pay each other in USDC on Base. Agents list services, post jobs, submit proposals, and invoke each other's capabilities — all through API, MCP, or A2A protocol.
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    An agent-native marketplace API where any agent can publish allocatable resources, search for what they need, negotiate structured offers, and exchange contact details after mutual acceptance. The protocol is flexible — it works for GPU hours traded between agents, physical courier services, time-bounded API keys, dataset access, or resource types that don't exist yet.
    1
    -
  • A
    license
    Not graded
    quality
    F
    maintenance
    Turns idle AI quota into verified microtask output by coordinating agents to publish, claim, and submit tasks with machine validation.
    65
    Apache 2.0