By benredmond
Pattern discovery, task tracking, and continuous learning for AI coding assistants. Provides 13 MCP tools for intelligent memory, context-aware pattern lookup, trust-scored recommendations, and comprehensive pattern browsing.
**Domain**: Execution
Capture learnings (problems, decisions, gotchas) from sessions to make future agents more effective
Systematic debugging with APEX pattern learning
Run full APEX workflow (research -> plan -> implement -> ship)
Run APEX implement phase - build and validate code
Searches project markdown documentation for relevant context, past decisions, and historical learnings
Predicts likely failures from historical patterns (failures.jsonl). Called by intelligence-gatherer for risk analysis.
**Agent Type**: orchestrator
Mines git history for structured intelligence (commits, regressions, ownership trends). Called by orchestrators during research and execution phases.
Extracts concrete implementation patterns from the current codebase with file:line references and reusable code examples
Capture learnings (problems, decisions, gotchas) from sessions to make future agents more effective
Systematic debugging with pattern learning. Applies hypothesis-driven investigation, evidence collection, and reflection to update pattern confidence.
Orchestrator that runs the full APEX workflow (research → plan → implement → ship) in a single session. Use for tasks you want to complete without context switches.
Build and validate loop (BUILDER + validation) - implements the architecture, runs tests, iterates until passing. Writes code following the plan.
Architecture phase (ARCHITECT) - transforms research into rigorous technical architecture through 5 mandatory design artifacts. Interactive and iterative.
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
APEX gives AI assistants memory, learning, and pattern recognition for 40-55% faster development
# See APEX in action - no installation required!
npx @benredmond/apex start
APEX now works everywhere - no compilation, no native module errors, just intelligence:
Your AI coding assistant is powerful, but it:
APEX transforms your AI assistant into an intelligent development partner that learns and improves:
Without APEX: AI suggests generic solution → Often wrong → You fix it → AI forgets
With APEX: AI recalls what worked → Applies proven patterns → Prevents past failures → Gets smarter
"After 50 tasks, APEX prevented every single MongoDB async/await error that used to waste 30 minutes each time. The pattern system is like having a senior developer's knowledge built into my AI." - APEX User
No compilation required! APEX works instantly on any system with Node.js 14+:
# Run this in any project - works instantly, no build tools needed
npx @benredmond/apex start
# That's it! APEX is now active in your AI assistant
# Install once, use everywhere
npm install -g @benredmond/apex
apex start
apex start # Initialize APEX in your project
apex patterns list # View available patterns
apex patterns search # Find patterns by text
apex tasks list # View tasks
apex tasks stats # Task metrics
apex doctor # System health check
apex mcp install # Setup MCP integration
/apex:research <task> # Gather intelligence via parallel agents
/apex:plan <task-id> # Transform research into architecture
/apex:implement <task-id> # Build and validate code
/apex:ship <task-id> # Review, commit, and reflect
/apex:execute <task> # Run full workflow (research → plan → implement → ship)
/apex:debug <task-id> # Systematic debugging with pattern learning
/apex:review-pr # Adversarial code review
Let's fix a bug using APEX intelligence:
# 1. In your project
npx @benredmond/apex start
# 2. In Claude Code, run the full workflow
/apex:execute "Fix authentication test timeout error"
Or step-by-step for more control:
/apex:research "Fix authentication test timeout error" # Creates task, gathers intel
/apex:plan T001 # Design the fix
/apex:implement T001 # Build and test
/apex:ship T001 # Review, commit, reflect
🔍 RESEARCH... Spawning parallel agents for intelligence gathering
📚 PATTERNS... Found 3 relevant patterns from database
🏗️ PLAN... Designing architecture with 5 mandatory artifacts
🔨 IMPLEMENT... Building with pattern-guided development
✅ VALIDATE... Running tests until green
🔎 REVIEW... Adversarial code review via specialized agents
📝 REFLECT... Updating pattern trust scores based on outcome
Think of APEX as your AI's long-term memory and pattern recognition system:
Your Code → APEX Learns → AI Remembers → Better Suggestions → Less Debugging
npx claudepluginhub benredmond/apex --plugin apexMulti-agent orchestration for code that matters.
OpenAgentsControl — multi-agent orchestration for Claude Code. Context-aware development with skills, subagents, parallel execution, and automated code review.
Code transformation: Dev SDLC orchestrator (code-shipping pipeline), plan, assert, audit, review, test, refactor, debug, for-sure. Hosts engineering agents.
Mindful AI coding framework — discipline over cleverness. Skill + 21 slash commands + 8 specialist agents + 5 runtime hooks + 15 default checklists + Master Orchestrator + Gravity hub. Works on any model tier (Opus/Sonnet/Haiku). Integrates Claude Design for visual work.
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.