Skip to main content
Glama

FPF Skill Stack

This repository implements an Agent Stack based on the First Principles Framework (FPF). It is organized by Bounded Contexts to strictly separate semantic domains while maintaining a clear link between Design (Text) and Runtime (Code).

📄 Authoritative Specification

The "real origin content" and authoritative definition of the First Principles Framework (FPF) is located here:

👉 governance/constitution/FPF_SPEC.md

All architectural decisions, role definitions, and interaction patterns in this repository are derived from this core specification.

Related MCP server: mneme-ai

📂 Repository Structure

The project follows the FPF Holonic Architecture (A.1) and Bounded Contexts (A.1.1):

  • contexts/: Contains the core logic, partitioned by semantic boundaries.

    • SkillRuntime/: The core runtime system (formerly fpf-agent-stack).

    • Skills/: Skill definitions and implementations.

    • SharedSchema/: Shared data contracts.

  • governance/: Project-wide rules, the FPF Constitution, and Decision Records (DRR).

    • constitution/: Contains the FPF_SPEC.md.

🛠 Usage

Requirements: Bun

# Install dependencies
bun install

# Run the skills validator
bun run validate

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to operate through a local, signed boundary that blocks prompt injection and secret leakage, verifies outputs, preserves cross-session memory, and provides offline-verifiable receipts. It also exposes 900+ MCP tools for discoverable agent actions.
    7
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    A cross-platform local AI-agent runtime and MCP gateway that exposes 279 tool definitions (267 advertised by default) for local files, Git, processes, Windows automation, WSL, browser control, Office semantic automation, and extensibility. It enables durable goal continuation, Engineering Harness workflows, context capsules, indexing, and resource-aware concurrent agent tasks through a single governed MCP connection.
    MIT