Full-text search across 67657 articles. Combine with topic and date filters; results sorted by relevance.
Slack Technologies, LLC, a Salesforce company, launched Add to Slack, a one-click deployment bridge that lets anyone deploy AI agents from 10 creation platforms—including OpenAI, LangChain, Lovable, n8n, and Vercel—direc…
Google has released ADK, an open-source agent development framework available in Python, TypeScript, Go, Java, and Kotlin, enabling developers to build, debug, and deploy production-grade AI agents at enterprise scale. T…
A bootcamp graduate developer cut their AI API bill from $500 to $12 per month by switching from OpenAI's GPT-4o to DeepSeek V4 Flash via a Global API service. The developer discovered the 40x price difference after rese…
A new Claude Code-based interview coach, built by Lenny's Newsletter community research lead Noam Segal from techniques used by over 30 tech professionals, helps job seekers prepare for interviews. The tool encodes succe…
Production teams are demoting retrieval-augmented generation (RAG) from a default architecture to a last-resort component, favoring deterministic lookups and agentic search, according to a postmortem from Inspecly, an au…
QECTOR, a quantum error correction decoding environment built on the qector-decoder-v3 core, has released an official integration for Claude Code and Claude Desktop, enabling fully offline, zero-egress quantum error corr…
DocBrain, a self-hosted, read-only memory layer for humans and AI agents, captures undocumented knowledge from tickets, threads, incidents, and code changes with per-claim provenance, and its client source is open under …
JetBrains released PyCharm 2026.2 with 263 fixes and improvements, focusing on Python code insight, type inference, and SQLAlchemy 2.0 support. The update resolves long-standing false positives in SQLAlchemy, improves co…
Igor Liska used an AI agent, Claude Code, to reverse-engineer the Canon PIXMA TS3300 printer's setup protocol, avoiding the vendor app and reconfiguring his network. The agent, running in a container, drove a Raspberry P…
Seahorse, a new open-source memory system for LLM agents, stores persistent, bi-temporal memory in local markdown files readable in Obsidian, addressing the problems of opaque, costly, and unreliable existing memory tool…
AWS has released Strands, an open-source AI agent SDK for building production agents, available via pip and npm. The SDK includes tools, hooks, and MCP server integrations for coding agents like Claude and Cursor. Strand…
Block Inc. has added an experimental self-hosted Git forge called Buzz Projects to its open-source workspace Buzz, enabling users to host Git repositories, code reviews, and discussions on a user-controlled relay. The fe…
The software industry is moving from AI-assisted coding to AI-agentic software engineering, where AI agents take ownership of entire development tasks. Two frameworks, Spec Kit and BMAD, enable this transition by promoti…
Payward, the parent company of cryptocurrency exchange Kraken, joined Anthropic's Project Glasswing on Aug. 17 and gained restricted access to Claude Mythos 5 for defensive cybersecurity work, planning to scan its softwa…
Obsidian Skills, an open-source project, enables AI agents such as Claude Code and Codex to read and search Obsidian markdown notes as a knowledge base, built on the agent skills specification for portability across comp…
GitHub's recent outages since November 2025 are caused by an explosion of agentic AI generating thousands of API calls per second, according to a blog post by Birkey. The proposed fix is organization-level flow control v…
A June 2026 study by LightSpeed and Tencent found that four frontier models—Claude Sonnet 4.5, DeepSeek-V4-Pro, GLM-5, and Gemini-3-Flash—misjudged their total context size with median relative error between 0.43 and 0.8…
Dash0, a New York-based observability startup valued at $1 billion, announced on August 17 that it acquired Berlin-based Polar Signals, a continuous-profiling company, for an undisclosed sum. The deal adds CPU, memory, G…
A 1979 paper's arguments against formal verification remain relevant but are being challenged by AI-driven coding, according to a 2026 analysis. The original paper claimed program verification would fail to affect confid…
Cerebras Systems' knowledge base rebuild, documented across four posts, shows that hybrid retrieval alone never outperformed pure vector search on the company's support corpus, but adding an LLM reranker delivered the fi…