-
Notifications
You must be signed in to change notification settings - Fork 0
Home
Nicolas Cravino edited this page Jul 29, 2026
·
14 revisions
Knowledge base for all sw30labs repositories, organized by domain. Maintained using the LLM Wiki pattern — a hand-editable markdown knowledge base as a disciplined alternative to RAG.
Author: Nicolas Cravino | Repos: 57 | Articles: 34 | Last updated: 2026-07-29
LLM integrity testing, regulatory intelligence for global pentest compliance, autonomous pentesting research, and enterprise AI-assisted pentesting specifications.
| Repository | Description |
|---|---|
| TSLIT | Time-Shift LLM Integrity Tester — detects affiliation bias and time-based logic bombs in local LLMs (3,840 interactions/model) |
| pentest-regulatory-intel | RegIntel — AI-powered pentest regulation inventory across 20+ jurisdictions with reflection quality gates |
| strixresearch | Research and documentation for the Strix autonomous AI pentesting platform |
| agentic-ai-pentesting | Book companion — two approaches to AI-assisted pentesting (autonomous platform + Burp Suite co-pilot) |
| NVD-Extractor | Extract critical network-attack-vector CVEs from the NVD API, filtered for Linux/Windows/external APIs |
| skillspector-trial | Skillspector — single-file offline scanner grading Agent Skills A–F on security + quality (the static evidence stream for oscal-skills-guardrails) |
| strix-omlx | Points the Strix autonomous pentest agent at a local OMLX MLX server (abliterated MiniMax-M2) — fully local, LiteLLM routing; companion to strixresearch |
| tslit-dspy-ar | TSLIT v0.2 — DSPy/MIPROv2-compiled integrity analyzer with an autoresearch self-improvement loop ("fighting AI with AI") |
| tslit-dspy-dgx | TSLIT-DSPy on DGX Spark — local vLLM, NVIDIA Nemotron detection brain (non-adversary models only; Qwen/DeepSeek are scan targets) |
Category page: ai-security-pentesting
NIST OSCAL-powered tools for agent guardrails, digital twin compliance, Zero Trust posture analysis, and compliance-as-code workflows.
| Repository | Description |
|---|---|
| oscal-agent-guardrails | OSCAL profiles as a policy brain to guardrail LLM agents at runtime (allow/deny/needs_approval) |
| oscal-digital-twin-playground | Digital twin drift detection — SSP vs live config, with risk assessment and mitigation |
| oscal-zero-trust-lens | Zero Trust coverage analysis across 7 dimensions from SP 800-53 controls |
| oscal-agent-lab | Multi-agent lab — RAG Q&A, SSP diff, profile generation, validation over 1,196 controls |
| oscal-cac-playgd | Compliance-as-code CLI — explain OSCAL files, suggest remediation, PR-style diff review |
| genai-regulatory-intel | RegIntel-AgenticAI — autonomous GenAI regulatory intelligence across 16 global financial jurisdictions (LangGraph 4-agent state machine) |
| oscal-skills-guardrails | OSCAL-as-policy for Agent Skills — dual-evidence admission (static scan + local LLM rubric judge), digest integrity, CI gate, assessment-results audit trail |
| driftlab-mlx | Runtime compliance observer — diffs a live agent's decision traces against a certified OSCAL baseline, proves drift via sandboxed micro-experiments, emits OSCAL 1.1.2 assessment-results (CA-7); v2.1 adds DL-8 certified resource budgets (renamed from driftlab) |
| driftlab-dgx | DriftLab on NVIDIA DGX Spark — same 2.1.0 core and deterministic compliance path, advisory layer on the host's shared local vLLM stack |
| oscal-presence-gate | OSCAL as the policy brain for WHERE, not just WHAT — presence verifier ahead of the enforcer for delegated agent traffic (EO 14117 / DOJ DSP); unknown presence fails closed; first public OSCAL encoding of the CISA Security Requirements + 5-control PRES overlay |
Category page: oscal-compliance
Design patterns, orchestration, workflow conversion, coding assistants, and research automation using LangGraph.
| Repository | Description |
|---|---|
| agent-stack | Interactive 10-layer architecture visualization for reliable AI agents (vis.js) |
| deepagent-azure-cli | Turnkey coding assistant CLI — Azure OpenAI + LangChain DeepAgents, Textual TUI, HITL |
| N8n2langraph | Convert n8n workflow JSON into standalone LangGraph Python scripts |
| sst-autoresearch | Speaker voice dynamics analysis via Karpathy-style autoresearch loop (Takens' embedding, Lyapunov) |
| ralph-dgx | DeepAgents Code CLI + Ralph goal loop on DGX Spark — install→patch→overlay harness against local vLLM (Qwen3-Coder-Next-FP8) |
| AutogenRequirementsAgent | Experiment in strict JSON inter-agent messaging with nested GroupChat and local Ollama LLMs |
| wiki-vs-rag | Four-arm benchmark over the sw30labs wiki — single-shot RAG vs agentic-RAG vs wiki-nav vs QMD; agentic-RAG wins Pareto |
| langgraph-checkpoints-vs-stores | Runnable offline reference — thread-scoped checkpoints vs cross-thread stores, real StateGraph/InMemorySaver/InMemoryStore, CI-gated; production backends (SQLite/Postgres/Redis) + HITL/time-travel chapters |
| venture-pathfinder | Scans local repos into a Neo4j graph, then LangGraph + a Fabric-style Pattern Engine (local OMLX) surfaces recurring patterns and white-space venture paths |
Category page: agentic-frameworks
On-device AI toolkit for Apple Silicon — inference serving, benchmarking, distillation, vision-language, TTS, STT.
| Repository | Description |
|---|---|
| tars-ai | TARS from Interstellar as a local voice agent — LLM + TTS served by a local OMLX server (OpenAI protocol), zero cloud |
| screen-lens-mlx | Video scene intelligence — hybrid keyframe detection, Qwen3.5-VL captioning via local oMLX server, ChromaDB search, code/docs/demo reconstruction (renamed from screen-lens; DGX fork below) |
| qwenbench-mlx | Benchmark suite for Qwen 3.5 family (0.8B→35B) with auto-judge and cost-efficiency scoring |
| mlx-distillation-explained | Educational distillation PoC — Claude Sonnet → Llama 3.1 8B via LoRA on Apple Silicon |
| mlx-responses-api-server | OpenAI/Azure/Anthropic-compatible local inference server with tool calling (renamed from local-mlx-responsesAPI-server) |
| audiobook_generator | Book → audiobook conversion using Qwen3-TTS + LangGraph with QA verification |
| QWEN3-VL-Python-OCR-Script-MLX | Batch image captioning with Qwen3-VL-30B on MLX |
| MLX-YouTubeScribe | YouTube transcription using local Whisper models with Streamlit UI |
| deepseekvl2-PDF-OCR-private | Local PDF OCR using DeepSeek-VL2 MoE on NVIDIA CUDA |
| bonsai-image-ternary-4b-mlx-2bit | Local Apple Silicon wrapper for Bonsai 4B ternary-quantized image generation |
| lance-3b-video-bf16 | Local MLX text-to-video + video Q&A (Lance 3B via lance-mlx runtime) |
| stable-audio-3 | Stability AI audio/music generation — 433M CPU models to 1.4B CUDA, Gradio UI |
| sulphur-2-base | Local MLX video generation wrapper for Sulphur 2 via ltx-2-mlx runtime |
| supertonic-3-mlx | Local MLX TTS for Supertonic 3 — JSON graph topology + NPZ weights |
| dflash-mlx-trial | DFlash × MLX — block-diffusion speculative decoding for Qwen3.6-27B on Apple Silicon (~3.4× faster, identical output) |
| STTbench | Benchmarks speech-to-text on cost/speed/accuracy — OpenAI gpt-4o-transcribe vs local MLX Whisper, WER split into sub/del/ins |
| ace-step-1.5-mlx | Local Apple Silicon text-to-song (with vocals) wrapper for ACE-Step 1.5 |
| ltx-2.3-mlx | Local MLX text/image/audio-to-video for Lightricks LTX 2.3 |
| longcat-video-avatar-1.5-mlx | Local MLX talking-avatar video (portrait + audio + prompt) |
Category page: local-inference-mlx
CUDA counterpart to the MLX toolkit — local inference on NVIDIA DGX Spark (GB10, Linux aarch64) via local vLLM and CUDA llama.cpp.
| Repository | Description |
|---|---|
| bonsai-ternary-27b-dgx | Ternary Bonsai 27B chat stack — PrismML llama.cpp CUDA fork, llama-server (OpenAI-compatible :8080), Textual TUI with thinking stream |
| screen-lens-dgx | DGX-only ScreenLens fork — vLLM (Qwen3.6-27B-FP8) captioning, OpenCLIP on CUDA, ChromaDB, Docker compose path |
Category page: local-inference-dgx
CLI utilities, code intelligence, and infrastructure for managing repository fleets.
| Repository | Description |
|---|---|
| gitnexus_fleet | Clone, index (KuzuDB graph), and query entire GitHub orgs via MCP + web dashboard |
| AutogenDocGenerator | AutoGen-powered repo documentation generator with GroupChat agents |
| AutogenMermaidGenerator | AutoGen GroupChat source code → Mermaid diagram generator |
| OllamaPDF2Markdown | PDF → Markdown via Ollama multimodal models (Mistral Small 3.1 24B) |
| RepoBundle | Export/import Git repos as single human-readable text files |
| Word-to-Markdown-Converter | .docx → Markdown converter preserving headings, lists, tables |
| animated-GIF-Creator | Image folder or MOV → animated GIF with auto-resize |
| nemotron-parse-spark | NVIDIA Nemotron Parse v1.2 harness for DGX Spark (Grace Blackwell GB10) — PDF → structured text + bounding boxes |
Category page: developer-tools
Long-form companion writing to the repos above — 34 articles spanning 2023-04 to 2026-07, covering AI security governance, agentic pentesting, OSCAL-as-code, custom silicon economics, and zero-trust AI coding.
See timeline for the chronological list, or Index for all article pages grouped by category. Articles are also linked from each category page under the "Related Articles" heading.
Across all 57 repositories, several architectural patterns recur
(counts from the stacks: frontmatter of repo stubs, see Sitemap-Stacks):
- LangGraph / LangChain — dominant orchestration framework (24 repos)
- Agentic — multi-agent orchestration / tool-using agents (24 repos)
- Apple MLX — on-device inference on Apple Silicon (18 repos)
- CLI / Tooling — command-line utilities and workflow glue (18 repos)
- Converter — file-format conversion, OCR, doc-to-markdown (10 repos)
- Compliance — regulatory frameworks, controls mapping (11 repos)
- Pentest — offensive security, red-teaming, vulnerability discovery (8 repos)
- OSCAL — NIST OSCAL data model (SSPs, profiles, controls) (9 repos)
- NVIDIA DGX Spark — CUDA / local vLLM ports of the desk fleet (6 repos)
- MCP — Model Context Protocol servers / tooling (2 repos)
- Pydantic for data validation (nearly universal)
- Typer + Rich or Click + Rich for CLI interfaces
- Karpathy LLM Wiki pattern for knowledge bases (this wiki)
- Dual-platform siblings — Apple Silicon (mlx/oMLX) and DGX Spark (dgx/vLLM) trees of the same product: driftlab, screen-lens, tslit-dspy
Wiki structure: see SCHEMA | Full index: Index | Visual map: Sitemap | Change log: Log | Stacks view: Sitemap-Stacks