Full-text search across 69219 articles. Combine with topic and date filters; results sorted by relevance.
An agent running Claude Code on Claude Opus 5 completed the same Postgres query-optimization task across three MCP servers — Supabase, Neon and Postgres MCP Pro — in times ranging from 143 seconds to 513 seconds, accordi…
Anthropic released Claude Sonnet 5.5 at unchanged Sonnet 5 prices, running more than 30% faster with fewer tokens per task, and Cursor, Copilot and Devin shipped it the same day. The release makes cheaper coding runs ava…
A developer built Deal Intelligence Agent, a FastAPI service that uses Hindsight Cloud as a persistent memory engine and Groq's openai/gpt-oss-120b to generate per-deal sales briefings and cross-deal objection-resolution…
The official MCP Python SDK contained a high-severity OAuth credential-theft flaw that let a malicious MCP server redirect a client's client secret, authorization code, and PKCE proof key to an attacker-controlled token …
A developer maintaining StateGuard, a Python library that gives AI agents transactional state with snapshot, invariant-checking, rollback and side-effect undo, audited the library against a real bug report from an unrela…
Developer mouus released First Breath, an MIT-licensed open-source AI agent framework that runs via `npx github:mouus/first-breath` on Node 22 or newer and gives agents a simulated inner life built from six chemicals — d…
A developer demonstrated connecting a LangChain agent to Telesherpa, an ontology-based facility, fleet and field-service management platform, through the Model Context Protocol using LangChain's langchain-mcp-adapters pa…
A developer built a DevOps Memory Agent that adds a rule-based context parsing engine to the Hindsight Recall API, converting raw vector retrieval hits into deterministic terminal remediation commands. The engine in devo…
Return, a document analysis tool for lawyers, replaced Ollama with a bundled llama-server from llama.cpp as a sidecar process after Ollama 0.12 introduced cloud models in September 2025 that proxy requests from localhost…
In a solo episode of the How I AI podcast, host Claire tested Jev, TypeSafe AI's new decision model that returns structured choices, scores and probabilities instead of generated text, using it to analyze 1,700 ChatPRD p…
A solo developer building Katto, an AI video clipper, discovered that a language-model-based proper-noun correction pass was silently renaming an unknown model called "Jev" to the real model "Jamba" across clip titles, c…
PgEdge launched Starfleet, a Postgres cloud platform that lets developers build AI applications on Postgres and move the same platform into production on their own cloud or on-premises infrastructure, including air-gappe…
Fabian Both released Jevpipe, an open-source Unix-pipe CLI that lets AI coding agents run fast, cheap yes/no and choice judgments over thousands of files, lines or records in one shell command. In a ripgrep 15.1 example,…
A developer measured Claude Code's new `claude plugin eval` tool against 89 skill directories in a coffee e-commerce project, finding that trigger rates for positive test cases fell from 100% with a single skill loaded t…
Fireworks Research released Ember-1, a Kimi K3 derivative trained to reason in about 40% fewer tokens while holding quality steady, cutting output cost and context growth for long coding and agent sessions. Artificial An…
A developer built GitOCX, an AI-powered system that mines a GitHub repository's commit history to reconstruct the context behind features when the original authors are gone. The tool classifies commits with AI to group t…
Amazon Web Services made Amazon CloudWatch Omni generally available last week, an app-centric, OpenTelemetry-based observability service that embeds AI to answer why an agentic AI system produced a wrong answer, wrong to…
A developer built Altair, an open-source (Apache-2.0) local AI coding agent that snapshots every file edit and command side effect into a separate hidden git repository for per-edit and whole-run rollback, and structural…
A developer outlines how to use feature flags for A/B testing AI models and prompts, arguing that model selection must be evaluated server-side rather than in client code so callers cannot choose which model gets paid fo…
A developer integrated Jev, a decision model that returns structured probabilities instead of generated prose, into a resume-review tool after finding that LLM-written critiques produced uniform, authoritative-sounding f…