» curated · synthesized
Skip the noise.
Read the signal.
Curated tech news and synthesis for developers and technology professionals.
» Latest posts
379 postsRelay: A Self-Hosted LLM Gateway With Eval-Gated Smart Routing
Relay is a self-hosted, single-binary LLM gateway with zero telemetry and an eval harness that gates smart routing by default.
26 Repos in 29 Days With Claude Code: The Real Failures Weren't Code
A 29-day AI-coding sprint built 26 repos and 335 pages with Claude Code — real failures were SEO cannibalization, URL drift, and buggy audit tools, not code.
AI Voice Phishing Rivals Human Scammers—And Costs Far Less
A 4,100-person study finds AI voice phishing matches human scammers in persuasiveness, with 70% detection accuracy and profitable economics at scale.
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.comLLMrPro: Open-Source LLM Balancer Pools Local Machines With Cloud Fallback
LLMrPro is an open-source, self-hosted LLM balancer that unifies your own machines and cloud providers behind one OpenAI-compatible API.
PlatypusDB: A Bitemporal, Agent-Native Database Built for WunderOS
PlatypusDB pairs a Gleam control plane with a Zig data plane in a bitemporal, Merkle-WAL-based database purpose-built for agentic memory in WunderOS.
AI's Cost Paradox: Smarter Models, Yet Runaway Token Bills
AI models keep improving, yet 'token amplification' in agentic workloads is driving usage costs sharply upward, forcing firms to curb AI spending.
venv-manager: A Python venv runtime built for humans and AI agents
venv-manager is an open-source Go tool with an MCP server and file watcher that manages Python venvs for both humans and AI coding agents.
Spoold: Durable Outbound HTTP Delivery Without a Database
Spoold is a lightweight Go daemon that gives outbound HTTP requests durable, at-least-once delivery without a database or message broker.
How Netflix Built Its Own In-House LLM Serving Stack
Netflix details its in-house LLM serving architecture: vLLM engine choice, Triton packaging, OpenAI-compatible API, and production rollout issues.
Malicious Sites Use JavaScript to Build Malware in Browser Memory
A malvertising campaign uses fake sites to have browsers assemble malware in memory.