Coding¶

A self-learning experience layer for AI coding assistants

Coding wraps around your AI coding assistant to capture conversations, build knowledge, prevent mistakes, and track progress - creating a continuously improving development environment.

What is Coding?¶

Coding is an infrastructure layer that enhances AI coding assistants by:

• Capturing everything - Automatic session logging of all prompts, tool calls, and responses
• Learning from experience - Build a knowledge base from your coding history and conversations
• Preventing mistakes - Constraint system stops errors before they happen

Key Features¶

Live Session Logging (LSL)¶

Every conversation is captured automatically with intelligent 5-layer classification that routes content between projects.

• Real-time monitoring with zero data loss
• Automatic redaction of secrets and credentials
• Multi-project support with foreign session tracking
• Configurable time-based slots (hourly files)

Learn more about LSL

Knowledge Management (UKB/VKB)¶

A 14-agent AI system extracts insights from your git history and conversation logs, building a searchable knowledge graph.

Update Knowledge Base (UKB):

ukb           # Incremental update from last checkpoint
ukb full      # Full analysis from first commit
ukb debug     # Single-stepping with mocked LLM

View Knowledge Base (VKB):

vkb           # Opens http://localhost:8080

Learn more about Knowledge Management

Constraint System¶

20+ configurable constraints enforce code quality via PreToolUse hooks - preventing mistakes before they happen.

• Real-time violation detection and blocking
• Web dashboard for monitoring and configuration
• Per-project constraint configuration
• Auto-correction suggestions

Learn more about Constraints

Health Monitoring¶

3-layer supervision architecture ensures system reliability with automatic recovery.

• Process health monitoring with automatic restart
• Service lifecycle management
• Multi-agent workflow visualization
• LLM call tracing (tokens, duration, costs)

Learn more about Health Monitoring

Status Line¶

Real-time feedback via the unified tmux status bar showing system health, costs, and development state. All coding agents (Claude, Copilot, OpenCode, Mastracode) are wrapped in tmux sessions with a shared status line rendered by combined-status-line.js.

Learn more about Status Line

Multi-Agent Support¶

While Claude Code is the primary and default agent, coding is fully agent-agnostic. Any coding assistant can be integrated with a single config file — no changes to shared code needed.

All agents share the same infrastructure: tmux session wrapping, status line, health monitoring, LSL session logging, knowledge management, and constraint enforcement. Missing agent CLIs are auto-installed on first launch.

Agent Integration Guide

Quick Start¶

# Clone and install
git clone --recurse-submodules https://github.com/fwornle/coding ~/Agentic/coding
cd ~/Agentic/coding && ./install.sh

# Reload shell
source ~/.bashrc  # or ~/.zshrc

# Start coding with all features
coding

# View your knowledge graph
vkb

Full Installation Guide

Design Principles¶

Feature Status¶

MCP Integrations¶

Coding provides several MCP (Model Context Protocol) servers:

Documentation¶