venikman

FPF Agent Stack

Community venikman
Updated

AI-Powered Observability with .NET Aspire + MCP

FPF Agent Stack

Bounded Context: Offline AI Agent Runtime

1. Context

Problem. Cloud LLM APIs leak private data, incur per-token costs, and require network connectivity.

Solution. An embedded, offline agent runtime with auditable execution and tri-state safety guards.

Scope. Local development, private automation, air-gapped environments.

2. Intent (L-PROJ-*)

L-PROJ-01: Core Capabilities

Capability Description
Embedded Model Qwen 2.5 0.5B Instruct via Transformers.js — no API keys, no network
MCP Server Exposes skills as tools via Model Context Protocol (Stdio)
AgentFS Copy-on-write sandbox for safe, auditable file operations
Guard Tri-state validation: pass / degrade / abstain
Skills Dynamic loading from core/skills/ with L/A/D/E contracts

L-PROJ-02: Project Structure (FPF E.4 Compliant)

fpf-agent-stack/
├── core/                # CANON: Normative contracts
│   └── skills/          # L/A/D/E skill definitions
│       ├── file-ops/
│       └── repo-search/
├── src/                 # TOOLING: Implementation
│   ├── cli.ts
│   ├── mcp-server.ts
│   ├── model-gateway.ts
│   ├── guard.ts
│   └── agent-fs.ts
├── test/                # TOOLING: Verification
│   └── bdd/
│       └── features/
└── docs/                # PEDAGOGY: Rationale & tutorials
    └── *.md

3. Archetypal Grounding

U.System Example: AgentFS Session

# Start isolated session
node dist/src/cli.js start-session ./my-project

# All writes go to session layer, host untouched
node dist/src/cli.js write <session> file.txt "content"

# Audit trail available
node dist/src/cli.js audit <session>

U.Episteme Example: Skill Contract

# core/skills/file-ops/SKILL.md

## L-TOOL-01: write_file
Write text content to a file path within workspace.

## A-TOOL-01: Admissibility
- Predicate: Active AgentFS session required
- Evidence: session_id

## D-TOOL-01: Duties
- Writes isolated to session layer
- Text content only (no binary)

## E-TOOL-01: Evidence
- Logged in AgentFS audit log

4. Getting Started

Prerequisites

  • Node.js 20+ (LTS)
  • 8GB RAM minimum

Setup

npm install
npm run build

Run

# Start MCP server
npm start

# Run tests
npm test

5. Conformance Checklist

ID Requirement Verification
CC-PROJ-01 Runs without network npm start succeeds offline
CC-PROJ-02 Model loads <30s Manual timing on 8GB machine
CC-PROJ-03 File writes sandboxed npm test — @agentfs green
CC-PROJ-04 Unknown tools abstain npm test — @guard green

6. Relations

Builds on. FPF L/A/D/E pattern, MCP specification, Transformers.js.

Constrains. All skill implementations must follow SKILL.md template.

Coordinates with. Technical-Choices.md, Development-Plan.md, Architecture-Comparison.md.

MCP Server · Populars

MCP Server · New

    TalkToHumans

    LinkedIn MCP Server

    Safe LinkedIn MCP server for Claude, ChatGPT, Cursor & Codex. Your Agents read LinkedIn DMs, search your network, enrich profiles and draft messages you send.

    Community TalkToHumans
    bex-co

    Beancount.io Backend

    💰 Double-entry bookkeeping made easy — plain-text accounting for humans and AI agents. Polished iOS & Android app built with React Native + Expo.

    Community bex-co
    nkapila6

    mcpsurfr

    Local web search MCP server, formerly mcp-local-rag. Multi-engine deep research with on-device re-ranking. ✨ no API keys ✨

    Community nkapila6
    convex

    mcp.ts

    The open-source reactive database for app developers

    Community convex
    convex

    convex-backend

    The open-source reactive database for app developers

    Community convex