asiflow/claude-nexus-hyper-agent-team

README preview

# Claude Code 31-Agent Team

> A production-grade multi-agent engineering team for Claude Code, with hook-enforced protocol, adversarial review, Bayesian trust calibration, dynamic specialist hiring, an optional parallel cognitive layer, and a self-improving meta-cognitive loop.

![Architecture Overview](docs/diagrams/diagram-1-hero.png)

**Architecture diagrams:** [`ARCHITECTURE_DIAGRAMS.md`](ARCHITECTURE_DIAGRAMS.md) (editable Mermaid source + ASCII fallbacks + PNG export instructions)

This is not a framework. It's an **operating system layer on top of Claude Code** — 31 domain-expert agents coordinated through a syscall protocol (NEXUS), governed by runtime hooks, validated by a 341-assertion contract test suite, calibrated by a per-agent trust ledger, and equipped with a gated hiring pipeline for growing the roster as coverage gaps appear.

**What it actually is** (verified against itself):
- 31 agent definitions in `agents/` (each 20–56 KB of role-specific instructions, spanning Go / Python / TypeScript / Elixir / BEAM / K8s / GCP / security / QA / AI platform / external BEAM retainer / recruiting + team-evolution roles)
- Runtime hooks that enforce closing-protocol invariants, persist signals, auto-log syscalls, auto-record trust verdicts, and gate post-hire registration
- A signal bus (`agent-memory/signal-bus/`) that carries memory/evolution/cross-agent flags between sessions
- A trust ledger (`agent-memory/trust-ledger/`) that Bayesian-blends per-agent accuracy from validator verdicts
- A documented NEXUS syscall protocol for privileged operations (SPAWN, SCALE, RELOAD, MCP, ASK, CRON, INTUIT, etc.)
- A **Dynamic Domain Expert Acquisition** pipeline (`talent-scout` + `recruiter`) — the team detects its own coverage gaps (5-signal confidence score + session-sentinel co-sign) and hires new specialist agents through 8 gated phases (research → synthesis → validation → challenger review → atomic registration → post-hire verify → probation → promotion)
- An optional **Shadow Mind** cognitive layer (`intuition-oracle` + Observer + Pattern Computer + Speculator + Dreamer + Pattern Library) that offers probabilistic pattern-based guidance via `[NEXUS:INTUIT]`, **delete-to-disable** without affecting the conscious team
- Contract tests (`tests/agents/`) that run on every commit and gate prompt evolution

View full repository on GitHub →