ReNoUn — Crypto Regime Classification

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/98lukehall-renoun

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

8 read · 0 write · 0 delete · 1 not yet classified

Secrets

1 (API keys, tokens or passwords)

Install scripts

Nothing to install (hosted)

Runs as

Hosted (remote endpoint)

Tools (9)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• renoun_agent_monitor

  Real-time structural health monitoring for AI agent sessions. Feed agent trace events incrementally and receive alerts when structural pathologies are detected (stuck loops, oversight loss, scattering, cascading errors). Supports per-agent and per-swarm monitoring.

• renoun_alignment_classify

  Structural alignment classification using the Life as Ground + ReNoUn bridge. Classifies conversations as INTEGRATIVELY_COHERENT, SUPPRESSIVELY_COHERENT, FRAGMENTED, or RIGID. Adds corrigibility scoring, challenge detection, and revision trace analysis on top of base ReNoUn analysis.

• renoun_analyze

  Deep structural analysis of a conversation. Detects loops, stuck states, breakthroughs, and convergence patterns across 17 channels — without reading the content. Returns a health score (0-1), pattern classifications (8 types including CLOSED_LOOP, PATTERN_BREAK, CONVERGENCE, SURFACE_VARIATION), breakthrough moments, and actionable next steps. Use this to understand why a conversation succeeded or failed structurally. Minimum 10 turns for reliable results.

• renoun_compare

  Structural A/B test between two conversations. Did the second session improve over the first? Which channels shifted? Did the pattern change from stuck to converging? Use for prompt iteration testing, session-over-session tracking, or comparing different agent strategies. Provide either pre-analyzed results or raw turns.

• renoun_finance_analyze

  Structural analysis of OHLCV financial data with regime classification and stability estimation. Returns DHS, constellation patterns, stress levels, and exposure scalar. 100% bounded regime accuracy across 265+ graded predictions. Use as a risk overlay — reduces exposure during structural disorder.

• renoun_health_check

  Fast structural triage. Is this conversation stuck, healthy, or falling apart? Returns one score, one pattern, one summary. Use this for quick checks before deciding whether to run full analysis. Sub-50ms.

• renoun_pattern_query

  Query structural patterns across sessions over time. How has conversation health trended this month? Which sessions were stuck? When did convergence patterns start appearing? Supports save, list, filtered queries, and trend computation against locally stored history.

• renoun_recovery_analyze

  Adaptive Recovery Analysis — measures how systems RESPOND to structural perturbation. The dynamic complement to static DHS. Detects perturbation events in a DHS trajectory, classifies outcomes (RECOVERED, REORGANIZED, COLLAPSED, STAGNATED, ONGOING), and computes an Adaptive Capacity Score (0-1). Works on any windowed analysis output: feed it the 'windows' from sequential renoun_analyze or renoun_finance_analyze calls. Key metrics: recovery rate, recovery surplus (positive = antifragile), recovery time, constellation sequences during perturbation-recovery cycles. Validated on financial crash da…

• renoun_steer

  Real-time inference steering. Monitor a live conversation and get actionable signals when the model should change strategy. Maintains rolling window buffers per session, runs structural analysis on each window, and emits SteeringSignals when thresholds are crossed (DHS drop, loop persistence, scattering). Use add_turns to feed conversation data incrementally; signals are emitted automatically when windows fill.

Signals

Stars

2

Forks

1

Open issues

0

Last commit

Mar 22, 2026 (7 months ago)

Last release

Mar 17, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.github.98lukehall/renoun

Version

1.4.0

Auth

Bearer token

License

License unknown

Repository

github.com/98lukehall/renoun-mcp

First seen

Oct 24, 2026

Last checked

Oct 25, 2026

Source

Official MCP Registrygithub-graphql