Skip to content
View nessos666's full-sized avatar
🏠
Working from home
🏠
Working from home
7 followers · 25 following

Block or report nessos666

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
nessos666/README.md

David

Hey, I'm David 👋

AI Safety Engineer • Quantitative Developer • Open Source Builder
I build systems that think, learn, and protect.

🦑 Featured Project: Coding Tentacle

The world's first Safety-First Guardian Layer for LLM code-fixing agents.

OpenCode writes fixes. Coding Tentacle analyzes, blocks dangerous changes, requires human approval, and learns from every run. Safety VETO + SkepticBrain + Bayesian Trust + 18 bug types. 68 Python modules. 100% open source.

→ github.com/nessos666/coding-tentacle

🔬 Featured Open-Source Tools

Three production-ready tools — no API keys required, MIT licensed, CI-tested on Python 3.10/3.11/3.12.

🔬 Wissenschaft

148 key-free academic sources searched in parallel.

Give it a topic, get a PRISMA dossier with ranked, verified papers.

  • 4-agent pipeline (Researcher → Verifier → Synthesis → Reviewer)
  • Citation snowballing
  • Zero API keys

→ Repo

🔍 SUCHER-1000

40+ sources in parallel — web and academic.

Keeps working when every other search tool fails.

  • Multi-engine fallback chain
  • Key-free
  • Built-in FTS5 archive

→ Repo

🧠 Extraktor

Turn AI conversations into durable memory.

Quality gates decide what is worth keeping — and what is noise.

  • 5 gates, 2 mandatory
  • Dedup at 0.85 similarity
  • Qdrant-backed

→ Repo

🧠 How I Work

I don't just write code. I build systems with intelligence.

🔬 Research FirstDeep literature review before architecture. 12-layer research sweeps. I read the papers. Then I build.
🛡️ Safety-FirstEvery system I build has a VETO layer. Nothing executes unless it's safe. No exceptions.
🧠 Self-LearningMy systems learn from every run. Bayesian trust calibration. Experience consolidation. Memory bridges.
🔧 Full StackFrom kernel-level monitoring to AI agent orchestration. Python, Rust, Bash, C++, Go, Ruby, JS/TS, Java.
📊 Evidence-DrivenI benchmark everything. If it can't be measured, it can't be improved. 100-issue reality tests as standard.
📦 Open SourceEverything I build is public. MIT license. No paywalls. No black boxes.

📂 Projects (15 repositories)

🦑 AI Safety & Code Quality

Project Description Stars
coding-tentacle Safety-first guardian layer for LLM code fixing. VETO + SkepticBrain + Bayesian Trust. ★0
context-bench Self-learning Claude Code hook that auto-injects project context into every session. ★0
multi-rep-set Multi-language code checker. Bash, Python, JS, JSON, YAML, Markdown + System. Zero dependencies. ★0

📡 Infrastructure & Monitoring

Project Description
topstepx-api-health-monitor 9 automated checks → Trust Score 0-100. Contract rollover, token expiry, bar quality, latency trending.
rithmic-api-health-monitor File-based health monitoring for Rithmic API — 10 checks, no own connection.
api-health-trust-system Generic weighted Trust Score for any REST API. Pluggable checks, Telegram alerts, atomic JSON export.

🔬 Quantitative Research

Project Description
nq-strategy-builder IS/OOS/Holdout backtesting with NLP-driven strategy composition. 158 files, 60 tests.
quant-tools Ornstein-Uhlenbeck MLE fitting, simulation, bias correction, volatility estimation.
baustein-tester Isolate and rank signal concepts (FVG, OB, Sweep, Breaker) before strategy building.

🛠 Tools

Project Description
chart-vision-mcp Local TradingView chart analysis via OpenCV + Tesseract OCR.
tv-watch-agent Automated TradingView chart watcher — CDP-based screenshot agent.
wissenschaft 148 key-free academic sources in parallel → PRISMA dossier. Citation snowballing.
sucher-1000 40+ web & academic sources in parallel. Multi-engine fallback, FTS5 archive.
extraktor Extract durable knowledge from AI chats into Qdrant. 5 quality gates.
graveyard Archived experimental projects.

📊 What I Build

AI Safety     ██████████  Coding Tentacle, Context-Bench
Infra/Monitor ████████    API Health Trust System, TopstepX, Rithmic
Quant/Finance ███████     NQ Strategy Builder, Quant Tools, Baustein Tester
Tools/Utils   ██████      Multi-Rep-Set, Chart-Vision, TV Watch Agent

🦑 Built with curiosity, shipped with care. Hungary → Germany. Bilingual DE/HU. Open to AI Safety & Infrastructure roles in Budapest.

Pinned Loading

  1. coding-tentacle coding-tentacle Public

    🦑 CT 11 — Secure Self-Learning Repair Agent. Droste Fusion. 4 Engines. Reflection Engine. 9/10 Benchmark.

    Python 2

  2. topstepx-api-health-monitor topstepx-api-health-monitor Public

    Real-time health monitoring for TopStepX/ProjectX futures trading API. 9 checks, Trust Score 0-100, JSON output for alerting.

    Python 5

  3. api-health-trust-system api-health-trust-system Public

    Weighted Trust Score monitoring for any REST API. Pluggable checks, composite 0-100 score, Telegram alerts, atomic JSON export.

    Python 3

  4. multi-rep-set multi-rep-set Public

    MULTI REP SET — Multi-Language Code Checker. Prüft Bash, Python, JS, JSON, YAML, Markdown + System. 0 Dependencies, 0 Token-Kosten.

    Python 1

  5. wissenschaft wissenschaft Public

    🔬 148 key-freie wissenschaftliche Quellen parallel durchsuchen — Dedup, Ranking, Verifier, PRISMA-Dossier. Ohne API-Keys. /wissenschaft für Hermes.

    Python 1

  6. extraktor extraktor Public

    Session-Wissen-Extraktor: holt Erkenntnisse aus einem KI-Chat und legt sie dauerhaft in Qdrant ab — mit Qualitaetspruefung vor dem Schreiben. Lokal, ohne Cloud.

    Python