Skip to content

ELF provides persistent memory, pattern tracking, and multi-agent coordination for Claude Code sessions without the need for an api key

Notifications You must be signed in to change notification settings

Spacehunterz/Emergent-Learning-Framework_ELF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Emergent Learning Framework

Emergent Learning Framework

Persistent memory and pattern tracking for Claude Code sessions.

Claude Code learns from your failures and successes, building institutional knowledge that persists across sessions. Patterns strengthen automatically. Install once, watch knowledge compound over weeks.

Install

./install.sh              # Mac/Linux
./install.ps1             # Windows

New to ELF? See the Getting Started Guide for detailed step-by-step instructions including prerequisites and troubleshooting.

First Use: Say "check in"

Every session, start with check in. This is the most important habit:

You: check in

Claude: [Queries building, starts dashboard, returns golden rules + heuristics]

Auto-Setup on First Check-In:

  • New user: Everything installs automatically - config, commands, hooks
  • Existing CLAUDE.md: Selection boxes to choose merge/replace/skip
  • Already configured: Proceeds normally

What "check in" does:

  • First time ever: Auto-installs config, hooks, /search, /checkin, /swarm commands
  • Start of session: Loads knowledge, starts dashboard at http://localhost:3001 (Ctrl+click to open)
  • When stuck: Searches for relevant patterns that might help
  • Before closing: Ensures learnings are captured (CYA - cover your ass)

When to check in:

Moment Why
Start of every session Load context, start dashboard, prevent repeating mistakes
When you hit a problem See if building knows about this issue
Before closing session Ensure learnings are captured

Core Features

Feature What It Does
Persistent Learning Failures and successes recorded to SQLite, survive across sessions
Heuristics Patterns gain confidence through validation (0.0 -> 1.0)
Golden Rules High-confidence heuristics promoted to constitutional principles
Pheromone Trails Files touched by tasks tracked for hotspot analysis
Coordinated Swarms Multi-agent workflows with specialized personas
Local Dashboard Visual monitoring at http://localhost:3001 (no API tokens used)
Session History Browse all Claude Code sessions in dashboard - search, filter by project/date, expand to see full conversations
Cross-Session Continuity Pick up where you left off - search what you asked in previous sessions. Lightweight retrieval (~500 tokens), or ~20k for heavy users reviewing full day
Async Watcher Background Haiku monitors your work, escalates to Opus only when needed. 95% cheaper than constant Opus monitoring

Hotspots

Hotspots Treemap of file activity - see which files get touched most and spot anomalies at a glance.

Graph

Graph Interactive knowledge graph showing how heuristics connect across domains.

Analytics

Analytics Track learning velocity, success rates, and confidence trends over time.

Cross-Session Continuity

Ever close a session and forget what you were working on? Use /search with natural language:

/search what was my last prompt?
/search what was I working on yesterday?
/search find prompts about git
/search when did I last check in?

Just type /search followed by your question in plain English. Pick up where you left off instantly.

Token Usage: ~500 tokens for quick lookups, scales with how much history you request.

Session History (Dashboard)

Browse your Claude Code session history visually in the dashboard's Sessions tab:

  • Search - Filter sessions by prompt text
  • Project Filter - Focus on specific projects
  • Date Range - Today, 7 days, 30 days, or all time
  • Expandable Cards - Click to see full conversation with user/assistant messages
  • Tool Usage - See what tools Claude used in each response

No tokens consumed - reads directly from ~/.claude/projects/ JSONL files.

Async Watcher

A background Haiku agent monitors coordination state every 30 seconds. When it detects something that needs attention, it escalates to Opus automatically.

┌─────────────────┐     exit 1      ┌─────────────────┐
│  Haiku (Tier 1) │ ──────────────► │  Opus (Tier 2)  │
│  Fast checks    │   "need help"   │  Deep analysis  │
│  ~$0.001/check  │                 │  ~$0.10/call    │
└─────────────────┘                 └─────────────────┘

Runs automatically - no user interaction required. See watcher/README.md for configuration and details.

How It Works

+---------------------------------------------------+
|              The Learning Loop                    |
+---------------------------------------------------+
|  QUERY   ->  Check building for knowledge         |
|  APPLY   ->  Use heuristics during task           |
|  RECORD  ->  Capture outcome (success/failure)    |
|  PERSIST ->  Update confidence scores             |
|                    |                              |
|         (cycle repeats, patterns strengthen)      |
+---------------------------------------------------+

Key Phrases

Say This What Happens
check in Start dashboard, query building, show golden rules + heuristics
query the building Same as check in
what does the building know about X Search for topic X
record this failure: [lesson] Create failure log
record this success: [pattern] Document what worked
/search [question] Search session history with natural language

Quick Commands

# Check what has been learned
python ~/.claude/emergent-learning/query/query.py --stats

# Start dashboard manually (if needed)
cd ~/.claude/emergent-learning/dashboard-app && ./run-dashboard.sh

# Multi-agent swarm (Pro/Max plans)
/swarm investigate the authentication system

Swarm Agents

Agent Role
Researcher Deep investigation, gather evidence
Architect System design, big picture
Skeptic Break things, find edge cases
Creative Novel solutions, lateral thinking

Documentation

Quick Start: Getting Started Guide - Step-by-step setup from zero to running

Full documentation in the Wiki:

Plan Compatibility

Plan Core + Dashboard Swarm
Free Yes No
Pro ($20) Yes Yes
Max ($100+) Yes Yes

Troubleshooting

Dashboard fails on Windows with Git Bash (Issue #11)

If you see Cannot find module @rollup/rollup-win32-x64-msvc when starting the dashboard:

Cause: Git Bash makes npm think it's running on Linux, so it installs Linux-specific binaries instead of Windows binaries.

Fix Option 1: Use PowerShell or CMD for npm install:

cd ~/.claude/emergent-learning/dashboard-app/frontend
rm -rf node_modules package-lock.json
npm install

Fix Option 2: Use Bun (handles platform detection correctly):

bun install

The run-dashboard.sh script will now detect this issue and warn you before failing.

Links

License

MIT License

Buy Me A Coffee

Development Status

ELF is under heavy active development. Rapid commits reflect live experimentation, architectural refinement, and real-world usage. The main branch represents active research and may change frequently. Stable checkpoints will be published as versioned GitHub releases; users who prefer stability should rely on tagged releases rather than the latest commit.

About

ELF provides persistent memory, pattern tracking, and multi-agent coordination for Claude Code sessions without the need for an api key

Resources

Stars

Watchers

Forks

Sponsor this project

Packages

No packages published