» Tag
ai-agents
256 postsAmazon Bedrock Managed Knowledge Base: What Changes for Developers
AWS's Amazon Bedrock Managed Knowledge Base automates RAG ingestion, parsing, and retrieval — key quota limits and userContext security to know.
ERC-8004 trust scores: the naive average crowns the wrong agent
How ERC-8004 reputation should be computed: why naive averaging fails, and how Beta-distribution witness capping fixes it in viem, web3.py, and alloy.
VoltMem: A Volatility-Aware Memory Layer for LLM Agents
VoltMem adds domain-specific volatility priors to LLM agent memory, resolving stale-vs-stable fact conflicts that flat memory layers like Mem0 miss.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comgui-tool: A Dependency-Free Rust CLI for Desktop GUI Automation
gui-tool is a zero-dependency Rust CLI that lets AI agents click desktop apps by naming labeled grid cells instead of guessing pixel coordinates.
Real-World gVisor Lessons from Auditing 8,764 MCP Servers
MarketNow shares practical lessons from running gVisor sandboxing in production, backed by real audit results across 8,764 MCP servers.
Why AI Agents Forget by Design: The Memory Problem
LLM APIs are stateless by design, and the context window is not real memory. This architectural choice drives cost, latency, and consistency failures in production agents.
How RAG Hallucinations Poison Your Vector Database
A fintech RAG pipeline poisoned its own vector store via silent hallucinations; here's how deterministic validation fixed the problem.
GitLost: A Public GitHub Issue Can Leak Private Repos
GitLost shows how a public GitHub issue and a one-word prefix bypass threat detection, leaking private repo contents via Agentic Workflows.
Qwen 3.8-Max and Claude Opus 5 show why benchmark scores don't predict cost
Qwen 3.8-Max and Claude Opus 5 benchmarks reveal why price-per-token no longer predicts real cost, and why cost-per-successful-task now matters more.
NVIDIA Outlines Four Controls for Securing AI Agents
NVIDIA's AI Red Team details four common failure modes in AI agent deployments and the access, execution, network, and secrets controls that stop them.