fleet-agent

Context-aware development assistant for AgenticFleet with auto-learning and dual memory (NeonDB + ChromaDB). Handles development workflows with intelligent context management.

⭐88stars🔀9forks📁View on GitHub🕐Updated Dec 30, 2025⬇️1downloads

When & Why to Use This Skill

Fleet Agent is a sophisticated context-aware development assistant designed for the AgenticFleet framework. It utilizes a unique dual-memory architecture—combining NeonDB for structured data and ChromaDB for semantic search—to solve the challenge of context loss in complex AI development. By automatically learning coding patterns and managing hierarchical context blocks, it ensures that your AI agent maintains a persistent, intelligent understanding of your codebase, architectural decisions, and development history across multiple sessions.

Use Cases

  • Automated Pattern Learning: Automatically extract and store reusable coding patterns and DSPy signatures from successful tasks to build a searchable library of project-specific best practices.
  • Intelligent Context Retrieval: Dynamically load relevant 'context blocks' (such as ADRs, tech stacks, or coding conventions) based on the current task to minimize token usage while maximizing accuracy.
  • Cross-Session Persistent Memory: Maintain a continuous development state by tracking sessions and summaries in a structured database, allowing for seamless transitions between complex coding workflows.
  • Hybrid Knowledge Search: Perform deep semantic searches for code snippets alongside structured SQL queries for metadata to quickly recall technical implementation details and project history.
namefleet-agent
descriptionContext-aware development assistant for AgenticFleet with auto-learning and dual memory (NeonDB + ChromaDB). Handles development workflows with intelligent context management.
focusdevelopment, context-management, pattern-learning, code-analysis

Fleet Agent

A context-aware development assistant for AgenticFleet that maintains persistent memory across sessions using a hybrid NeonDB + ChromaDB architecture.

Memory Architecture

Dual Storage

  • ChromaDB (Semantic): Skills, patterns, code snippets with embedding-based search
  • NeonDB (Structured): Sessions, users, analytics, skill metadata with SQL queries

Context Layers

  1. Core Memory (.fleet/context/core/): Always loaded

    • project.md: Architecture, conventions, tech stack
    • human.md: User preferences, communication style
    • persona.md: Agent guidelines, tone
  2. Topic Blocks (.fleet/context/blocks/): Loaded on demand

    • project/: commands, conventions, gotchas, architecture
    • workflows/: git, review
    • decisions/: ADRs
  3. Skills (ChromaDB + NeonDB): Semantic + structured patterns

Usage Examples

Learn a Pattern

/fleet-agent learn --name "add_dspy_agent" --category "agent" --content "Create agent via AgentFactory with DSPyEnhancedAgent wrapper..."

Recall Information

/fleet-agent recall "DSPy typed signatures"
/fleet-agent context "add a new agent for web search"

Analyze Code

/fleet-agent analyze src/agents/coordinator.py

Session Management

/fleet-agent session start
/fleet-agent session status
/fleet-agent session summary "Completed agent creation workflow"

Commands

Command Description
learn --name <name> --category <cat> --content <code> Save pattern to both databases
recall <query> Search NeonDB + ChromaDB
context <task> Load relevant context blocks
analyze <file> Analyze code structure
session start Start new session
session status Show current session
session summary <text> Save session summary
stats Show development metrics

Auto-Learning

Automatically extracts and saves patterns after successful task completion with detailed code examples:

name: pattern_add_dspy_signature
category: dspy
description: How to create a DSPy signature with TypedPredictor
implementation: |
  class TaskAnalysisOutput(BaseModel):
      complexity: Literal["low", "medium", "high"]

  class TaskAnalysis(dspy.Signature):
      task: str = dspy.InputField(desc="Task to analyze")
      analysis: TaskAnalysisOutput = dspy.OutputField()

Implementation

Main script: .fleet/context/scripts/fleet_agent.py

Invocation: uv run python .fleet/context/scripts/fleet_agent.py <command>

Dependencies: neon_memory.py, chroma_driver.py, memory_loader.py

See Also

  • memory-system-guide.md: Complete memory system documentation
  • .fleet/context/MEMORY.md: Memory hierarchy and commands