Skip to content
View n24q02m's full-sized avatar
  • Ha Noi, Viet Nam
  • 19:08 (UTC +07:00)

Block or report n24q02m

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
n24q02m/README.md

Nguyen Quang Minh · @n24q02m

I design and ship AI systems, developer tools, and MCP infrastructure. On the research side I work on making AI efficient, auditable, and well-behaved.

Research

I'm interested in AI that stays efficient, auditable, and reliable — keeping cost down while every answer remains checkable, and understanding how models behave at their edges. Representative published work:

  • TACET (Latin: it is silent) — Cost-Amortised Reasoning via Self-Distilling Neuro-Symbolic Cascades: From Knowledge-Graph QA to Regulatory-Compliance Checking. A three-tier cascade — a sound Datalog engine, a calibrated ComplEx link predictor, and an LLM teacher — with an online distillation loop that mines teacher answers into auditable Horn rules, amortising LLM cost while every symbolic answer ships a replayable proof tree; the same mechanism carries from knowledge-graph QA to streaming GDPR compliance checking. code · preprint doi:10.5281/zenodo.20621240.

MCP Servers & Plugins

Quick Install (Claude Code)

/plugin marketplace add n24q02m/claude-plugins

Then /plugin install <name>@n24q02m-plugins. The marketplace ships every server below plus the agent-chat plugin.

Active servers (CLI-first: each ships a native CLI plus an MCP server)

Server Description Agent Setup Install
wet Web search, content extraction, and documentation indexing Guide pip install wet-mcp · CLI: wet · MCP: uvx wet-mcp
mnemo Persistent AI memory with hybrid search and cross-machine sync Guide pip install mnemo-mcp · CLI: mnemo · MCP: uvx mnemo-mcp
crg Knowledge graph for token-efficient code reviews Guide pip install better-code-review-graph · CLI: crg · MCP: uvx better-code-review-graph

Setup any server: Copy the Agent Setup guide link and send it to your AI agent with "Please set up this MCP server for me."

Docs hub: mcp.n24q02m.com — unified documentation for MCP servers, skret and better-semantic-release.

Plugins

Plugin Description Install
agent-chat-plugin Peer agents coordinate through markdown messages in a shared folder — no orchestrator, and waiting costs no tokens /plugin install agent-chat-plugin@n24q02m-plugins

Libraries

Package Description Install
mcp-core Streamable HTTP transport, OAuth 2.1, browser-based credential setup, lifecycle, and a shared embedding daemon npm i @n24q02m/mcp-core / pip install n24q02m-mcp-core
fastretrieval Multi-model retrieval runtime for dense, sparse, late-interaction, image, ColPali, and reranking workloads on ONNX or GGUF pip install fastretrieval
web-core Shared web infrastructure: SSRF-safe HTTP, SearXNG search, multi-strategy scraping, stealth browsers pip install n24q02m-web-core

Tools

Tool Description Install
jules-task-archiver Chrome Extension to bulk-archive completed Jules tasks Download zip
better-semantic-release Drop-in python-semantic-release fork with release-safety guards for orphan tags and registry collisions. Same config schema, same CLI, same Action interface. pip install better-semantic-release
skret Cloud-provider secret manager CLI — secrets without the server (AWS SSM + local YAML; OCI/Azure/GCP roadmap) scoop install skret / brew install skret · Docs

Archived (read-only — replaced by CLI-first tools or native APIs)

Repository Was Successor / note
wet-mcp Web MCP server Renamed to wet (PyPI package stays wet-mcp)
mnemo-mcp Memory MCP server Renamed to mnemo (PyPI package stays mnemo-mcp)
better-code-review-graph Code-graph MCP server Renamed to crg (PyPI package stays better-code-review-graph)
better-notion-mcp Notion MCP server Use the official Notion API/SDK directly
better-email-mcp Email (IMAP/SMTP) MCP server Use standard IMAP/SMTP tooling
better-telegram-mcp Telegram MCP server Use the official Telegram Bot API / MTProto clients
better-godot-mcp Godot Engine MCP server Use Godot's native scripting/CLI
better-workspace-mcp Google Workspace MCP server Use Google Workspace APIs directly
imagine-mcp Image/video understanding + generation MCP server Use provider-native APIs (Gemini, OpenAI, Grok)
qwen3-embed Qwen3 embedding/reranking package Superseded by fastretrieval (pip install qwen3-embed still works)
better-drive Two-way Google Drive sync Archived — use rclone directly

Products

  • KnowledgePrism -- Chat with your knowledge. Ingest anything (URL, PDF, EPUB, DOCX, CBZ, audio, video, image, text) into a persistent per-project knowledge graph, then produce any format (translation, brief, podcast, slide deck, mindmap, quiz, export). One chat-first agent plans compound requests as a typed capability DAG; ProjectKG is the auto-maintained spine, not a feature. klprism.com
  • Aiora -- A health and environment companion for daily wellness. getaiora.com
  • LinguaSense -- Realtime knowledge transfer from any screen or microphone. Desktop + mobile. (coming)
  • Akasha / GWM (exploratory research, not a shipped product) -- a graph-centric world model with an LLM teacher and continuous learning; early-stage.

Pinned Loading

  1. tacet tacet Public

    A self-distilling neuro-symbolic cascade that amortises LLM cost across knowledge-graph QA and regulatory-compliance checking, with auditable Datalog proof trees.

    Python 1

  2. crg crg Public

    Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.

    Python 69 10

  3. wet wet Public

    Open-source MCP server for AI agents: web search, content extraction, and library docs -- 5-strategy scraping, runs without API keys.

    Python 18 5

  4. mnemo mnemo Public

    Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.

    Python 11 6

  5. fastretrieval fastretrieval Public

    Fast multi-model retrieval runtime: ONNX and GGUF embeddings, reranking, and a declarative model contract

    Python 2

  6. better-semantic-release better-semantic-release Public

    Drop-in python-semantic-release fork with built-in release-safety guards (orphan-tag + registry-collision).

    Python 1