João André Gomes Marques

Apr 8

Scan MCP tool definitions for prompt injection before your agent calls them

#ai #security #python #opensource

1 min read

João André Gomes Marques

Apr 8

Three tiers of enforcement for AI agents - strong, bounded, detectable

#ai #python #security #opensource

2 min read

João André Gomes Marques

Apr 7

asqav-mcp is now on Docker Hub

#ai #python #security #opensource

2 min read

João André Gomes Marques

Apr 7

Asqav vs Microsoft Agent Governance Toolkit - what is the difference

#ai #python #security #opensource

2 min read

João André Gomes Marques

Apr 7

Why the E8 lattice is the perfect quantizer for KV caches

#ai #math #llm #research

2 min read

João André Gomes Marques

Apr 7

Running 1M-token context on a single GPU (the math)

#ai #gpu #llm #infrastructure

2 min read

João André Gomes Marques

Apr 7

NexusQuant is now on PyPI, HuggingFace, and 9 awesome lists

#python #ai #opensource #machinelearning

2 min read

João André Gomes Marques

Apr 7

Why attention-aware eviction beats random eviction (with data)

#ai #machinelearning #performance #python

2 min read

João André Gomes Marques

Apr 7

One line of Python to extend your LLM's context window 10x

#python #machinelearning #ai #llm

1 min read

João André Gomes Marques

Apr 7

The 12 approaches I tested before finding one that works

#machinelearning #python #ai #llm

5 min read

João André Gomes Marques

Apr 7

NexusQuant: compressão de memória para LLMs — guia prático

#python #tutorial #portuguese

3 min read

João André Gomes Marques

Apr 7

Como comprimir o KV cache do seu LLM em 33x sem treino

#python #machinelearning #portuguese

3 min read

João André Gomes Marques

Apr 7

KV cache memory calculator: how much does your LLM actually use?

#llm #machinelearning #python #gpu

3 min read

João André Gomes Marques

Apr 7

How to benchmark NexusQuant on your own model

#llm #python #machinelearning #opensource

3 min read

João André Gomes Marques

Apr 7

What I Learned Testing 12 Compression Approaches That Failed

#machinelearning #llm #research #python

6 min read

João André Gomes Marques

Apr 7

The Math Behind E8 Lattice Quantization (with Code)

#machinelearning #math #python #llm

6 min read

João André Gomes Marques

Apr 7

How Much GPU Memory Does NexusQuant Actually Save?

#machinelearning #gpu #llm #python

4 min read

João André Gomes Marques

Apr 7

How to deploy NexusQuant in production (and what's missing)

#machinelearning #llm #production #python

4 min read

João André Gomes Marques

Apr 7

NexusQuant vs KVTC vs TurboQuant vs CommVQ — honest comparison

#machinelearning #llm #performance #benchmark

4 min read

João André Gomes Marques

Apr 7

NexusQuant benchmarks: every number, honestly

#machinelearning #llm #performance #opensource

5 min read

João André Gomes Marques

Apr 7

Longer contexts are easier to compress (not harder)

#python #machinelearning #llm #performance

2 min read

João André Gomes Marques

Apr 7

Why E8 lattice quantization beats scalar quantization for KV caches

#python #machinelearning #math #llm

2 min read

João André Gomes Marques

Apr 7

Compress your LLM's KV cache 33x with zero training

#python #machinelearning #llm #opensource

2 min read

João André Gomes Marques

Apr 7

5 open source tools for AI agent governance in 2026

#ai #security #opensource #python

1 min read

João André Gomes Marques

Apr 6

5 things your AI agent should never leak (and how to detect them)

#security #ai #python #tutorial

1 min read

João André Gomes Marques

Apr 6

Add governance to Claude Desktop with an MCP server

#ai #tutorial #python #claude

1

1 min read

João André Gomes Marques

Apr 6

Add governance to OpenAI Agents SDK in 3 lines

#python #ai #tutorial #openai

1

1 min read

João André Gomes Marques

Apr 6

How to add tamper-evident audit trails to CrewAI agents

#python #ai #tutorial #crewai

1 min read

João André Gomes Marques

Apr 6

We just launched asqav on Hacker News - quantum-safe audit trails for AI agents

#showdev #opensource #python #ai

1

1 min read

João André Gomes Marques

Apr 6

EU AI Act compliance checklist for AI engineering teams

#ai #security #tutorial #beginners

2 min read

João André Gomes Marques

Apr 6

AI agent governance tools compared - 2026 landscape

#ai #security #opensource #devops

1

2 min read

João André Gomes Marques

Apr 6

How to make your AI agent accountable in 60 seconds

#tutorial #beginners #python #ai

1 min read

João André Gomes Marques

Apr 6

AI agent compliance scanner for your CI/CD pipeline

#github #devops #ai #security

1

3 min read

João André Gomes Marques

Apr 6

One decorator to make any Python function auditable

#python #tutorial #security #opensource

2 min read

João André Gomes Marques

Apr 6

Your MCP servers are unsigned. Here is why that matters.

#ai #security #python #opensource

3 min read

João André Gomes Marques

Apr 6

Your AI agents need audit trails before August 2026. Here is how I added them in 5 lines of Python.

#ai #python #security #opensource

5 min read

João André Gomes Marques

Mar 27

Stop AI Agents from Leaking PII, Secrets, and Prompt Injections

#ai #python #security #privacy

1 min read

João André Gomes Marques

Mar 27

Verify AI Agent Signatures from Your Terminal

#ai #python #tutorial #cli

1

1 min read

João André Gomes Marques

Mar 27

Add Governance to LangChain, CrewAI, and LiteLLM in 3 Lines

#ai #python #langchain #opensource

1

1 min read

João André Gomes Marques

Mar 27

One Decorator to Audit Every AI Agent Call

#ai #python #tutorial #opensource

2

1 min read

João André Gomes Marques

Mar 27

Stop AI Agents from Leaking PII

#ai #python #security #privacy

3

5

1 min read

João André Gomes Marques

Mar 27

Your AI Agents Are Running Unsupervised

#ai #python #security #opensource

2 min read

João André Gomes Marques

Mar 21

How to Add Governance to Your CrewAI Agents

#ai #python #tutorial #opensource

1 min read

João André Gomes Marques

Mar 21

OWASP Top 10 for Agentic AI: How to Protect Your AI Agents

#ai #security #python #opensource

1 min read

João André Gomes Marques

Mar 21

Governing Multi-Agent AI Systems: Policies, Approvals, and Audit Trails

#ai #python #security #opensource

1 min read

João André Gomes Marques

Mar 21

Quantum-Safe Signatures for AI Agents: Why ML-DSA Matters

#ai #python #security #opensource

1 min read

João André Gomes Marques

Mar 21

Building a Governance MCP Server for AI Agents

#ai #python #security #tutorial

1 min read

João André Gomes Marques

Mar 21

Adding Audit Trails to LangChain Agents with Asqav

#ai #python #security #tutorial

1 min read

João André Gomes Marques

Mar 21

EU AI Act Compliance for AI Agents: What Developers Need to Know

#ai #python #security #opensource

2 min read

João André Gomes Marques

Mar 21

Why Your AI Agents Need an Audit Trail (and How to Add One in 5 Minutes)

#ai #python #security #opensource

2 min read

Writing Debut