ManintheCrowds (Andre Schu) · GitHub
Skip to content
View ManintheCrowds's full-sized avatar
👀
👀
24 followers · 31 following

Achievements

Achievement: QuickdrawAchievement: Pair Extraordinairex3Achievement: YOLOAchievement: Pull Sharkx2

Achievements

Achievement: QuickdrawAchievement: Pair Extraordinairex3Achievement: YOLOAchievement: Pull Sharkx2

Block or report ManintheCrowds

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ManintheCrowds/README.md

Backend & Systems Engineer | AI Systems | Defensive Security | Agent Infrastructure

I build tools that help humans stay in control of AI systems: clear handoffs, input safety, defensive monitoring, and production backends you can inspect.

What → who → why

What I ship Who it is for Why it exists
Agent harnesses & context graphs Operators running multi-session AI work Intent gets lost across chats; humans need gates and memory
Content safety + shared threat patterns Anyone putting untrusted text near an LLM Prompt injection is real; local nodes need shared signatures without sharing raw prompts
Blue-team / observability platforms Defenders watching agent networks Autonomous attackers need autonomous (human-gated) defense
Caption + homelab platform APIs Production media / ops Real pipelines need SSO, gateway, and metrics—not demos

Projects (plain language)

Stay in control of agents

Project One line
OpenHarness Portable harness: handoffs, context, and intent alignment
OpenGrimoire Local-first context graph and Sync Session workspace
arc-forge-wiki Public sterile LLM-Wiki + vault scripts extract

Keep untrusted content out of the model

Project One line
SCP Inspect, sanitize, contain, quarantine LLM inputs (OWASP LLM01/LLM06)
scp-mycelium-registry Shared anonymized threat-pattern snapshots for SCP nodes (data only)

Defend and watch

Project One line
T3MP3ST_BLU3H4T Autonomous blue team — D3FEND operators, AI red-team detection, governance gates
moltbook_watchtower Read-only observability for agent networks (leak / injection / behavior)

Ship production backends

Project One line
media-ops-platform CaptionPipeline + Platform API — captions, SSO, gateway, observability

Experiments (EEG / visual I/O)

Project One line
ENTHEA Fork of Pliny’s visualizer — our focus is Muse EEG as I/O (features-only seam; live hardware still commissioning)
eeg-connection-hub LAN-first multi-stream EEG feature broker — LSL in, derived features out, multi-app WebSocket fan-out (synthetic-tested beta)

How they connect

flowchart TB
  Intent[Human intent]
  OH[OpenHarness]
  SCP[SCP]
  Reg[mycelium registry]
  T3[T3MP3ST]
  WT[watchtower]
  MOP[media-ops]
  OG[OpenGrimoire]

  Intent --> OH
  OH --> SCP
  Reg -.->|signed snapshots| SCP
  SCP -->|gates tools| MOP
  SCP -->|gates tools| OG
  SCP -->|gates agents| T3
  T3 -.-> WT
  WT -.-> SCP
Loading

Evidence (as-of dates)

  • CaptionPipeline (2025-12): 256+ caption files, 330+ content hours, <1% pipeline errors across 9 feeds — operational metrics, not WER → portfolio kit
  • SCP (2026-06): 16/16 promptfoo tier probes (OWASP LLM01/LLM06)
  • OpenHarness (2026-06): pin-able by commit SHA; autoresearch Tier B 5/5 on foam-pkm + frontend-a2ui
  • T3MP3ST_BLU3H4T (2026-07): 8 D3FEND operator archetypes; 17-technique AI red-team detection playbook

Metrics SSOT: metrics.json

Evaluate in ~10 minutes

Step Repo Try
1 OpenHarness python scripts/verify_script_index.py
2 SCP npx promptfoo eval (README § Testing)
3 scp-mycelium-registry Fetch latest.json
4 media-ops-platform README Quick start
5 OpenGrimoire npm install && npm run dev (default branch: master)

GitHub pins (UI)

Live pins (6): OpenHarness · moltbook_watchtower · media-ops-platform · OpenGrimoire · SCP · scp-mycelium-registry

Pin action closed: docs/PIN_ACTION.md.

Project One line CI
OpenHarness Portable harness: handoffs, context, intent alignment CI
SCP MCP guardrail for LLM inputs CI
scp-mycelium-registry Shared anonymized threat-pattern snapshots (data) data + validators
moltbook_watchtower Read-only agent-network observability Tests
media-ops-platform CaptionPipeline + Platform API tests
OpenGrimoire Local-first context graph / Sync Session CI

Also in the proof narrative (not all pinned in the UI): T3MP3ST_BLU3H4T, arc-forge-wiki.

Other projects

Project One line
LangChainChatBot Local-first RAG over YouTube transcripts
PrusaXL_Monitor 3D printing observability (Flask, PrusaLink, Grafana)
ENTHEA Fork of elder-plinius/ENTHEA — EEG headset as I/O experiment
eeg-connection-hub LAN-first multi-stream EEG feature broker — LSL in, derived features out, multi-app WebSocket fan-out

Stack

Python TypeScript Node.js Next.js FastAPI PostgreSQL Docker Nginx Redis MCP Prometheus Grafana

Open an issue on any repo for collaboration. Audit evidence: PUBLIC_REPO_AUDIT_RESULTS §8 (2026-07-18).

Pinned Loading

  1. OpenHarness OpenHarness Public

    Handoffs, Context & Intent Engineering. Compliant to Autonomous Cognitive Entities Framework.

    Python

  2. moltbook_watchtower moltbook_watchtower Public

    Passive monitoring for the Moltbook agent network. Read-only observability; leak, injection, and behavior analysis; local-first, no writes to the network.

    Python

  3. media-ops-platform media-ops-platform Public

    FastAPI homelab Platform API — JWT dashboard, gateway, compose apps. CaptionPipeline is a dated portfolio case study (docs/portfolio), not workers in this clone.

    Python

  4. OpenGrimoire OpenGrimoire Public

    Local-first context graph and Sync Session platform for human-agent alignment. RESTful API, D3/Three.js visualizations, static JSON contract.

    TypeScript 1

  5. SCP SCP Public

    Content safety for AI: inspect, sanitize, contain, quarantine. MCP server. OWASP LLM01/LLM06.

    Python

  6. scp-mycelium-registry scp-mycelium-registry Public

    Shared anonymized threat-pattern snapshots for SCP nodes — immutable tagged JSON, human-gated merge. Market making P2P data commodities for AI security. Runs on L402 and NOSTR