How it works

Neo4j + a 6,200-line CLI + a skill file.

Components

Neo4j Community (free) — the graph database, runs in Docker
sys_edge.py — CLI for all graph operations, 50+ commands
sys_edge_viz.py — local web visualiser, drill-down navigation
feature-graph skill — Claude Code skill file, governs all session behaviour
Seed JSON — your project's module and feature definitions

Safety model

Sessions use MERGE (never DELETE)
Graph reset is a separate shell script — not accessible from Claude
Instance-filtered seed auto-backs up before running
VERIFIES edges snapshot before any seed — post-backup links preserved
Sessions only write nodes within their declared instance scope

Session start in 30 seconds

Three commands replace ten minutes of file reading.

$ python3 cli/sys_edge.py briefing --instance manage ══════════════════════════════════════════════════════════ SYSTEM GRAPH BRIEFING — manage (2026-05-22) ══════════════════════════════════════════════════════════ MOD-delegation Delegation 12/12 ✓ ✓cmp 12/12 ✓int 12/12 ~uc 8/12 ✗e2e 0/12 MOD-succession Succession 9/9 ✓ ✓cmp 9/9 ✓int 9/9 ✓uc 9/9 ✗e2e 0/9 ENHANCEMENTS (3) PROPOSED (3) ENH-330 [Must] Delegation inbox API endpoint → F-DLG-003 ENH-331 [Should] Bulk reassign on offboarding → F-DLG-008 $ python3 cli/sys_edge.py worklog --instance manage ★★★ ENH-330 [Must] Delegation inbox API endpoint — GET /manage/delegation/inbox Feature : F-DLG-003 Delegation inbox view Module : MOD-delegation backend/internal/p8/delegation/ $ python3 cli/sys_edge.py start-enhancement --id ENH-330 --instance manage ✓ ENH-330 in-progress — Delegation inbox API endpoint Other sessions can now see this is being built.

Zero-config setup

The biggest adoption barrier is the initial seed JSON. The /init-sysedge skill solves this in one command.

/init-sysedge Scanning working directory... Detected: Go backend (backend/internal/) — 12 packages Detected: TypeScript frontend (src/features/) — 8 feature modules Detected: Python tests (tests/) — 47 test files ✓ 20 SysModule nodes derived from package structure ✓ 89 SysFeature nodes derived from exported symbols ✓ 3 SysTestPackage groups (component / integration / e2e) ✓ seed written to data/sys-init-YYYY-MM-DD.json Next: python3 scripts/sys_edge.py seed data/sys-init-YYYY-MM-DD.json

Language support

Full scan: functions, handlers, test files

TypeScript

Full scan: components, hooks, exports

Python

Full scan: classes, functions, pytest files

Java

Full scan: public classes and methods

Rust / other

Graph features work · manual symbol linking

Adding a new language scanner is one Python function (~20 lines). See INSTALL.md for the plugin interface.

Installation — 4 steps

# 1. Start Neo4j (requires Docker) docker run -d --name sysedge-neo4j \ -e NEO4J_AUTH=neo4j/yourpassword \ -p 7688:7687 neo4j:5.26 # 2. Install Python dependencies pip install neo4j python-dotenv pyyaml # 3. Configure echo "SYSEDGE_NEO4J_URI=bolt://localhost:7688 SYSEDGE_NEO4J_USER=neo4j SYSEDGE_NEO4J_PASSWORD=yourpassword" > .env # 4. Initialise and load your project python3 cli/sys_edge.py init python3 cli/sys_edge.py seed examples/seed-example.json ✓ Ready. Add the feature-graph skill to your Claude Code sessions.

The bootstrap kit includes a Docker Compose file and a setup wizard that generates your initial seed JSON from your working directory.

Instance model

SysEdge uses instances to scope work across parallel sessions. Each session declares an instance name and only writes nodes within that scope. A typical team of 12 might use: master (shared patterns, e2e tests), core (P2-P4 features), framework (auth, shell), manage (delegation, succession), plan (strategy, compliance), and 7 more domain instances. Sessions query across all instances but write only to their own.

Get SysEdge →