Coding agents are overturning Joel Spolsky's 25-year-old 'never rewrite' rule, as regenerating code becomes cheaper than reviewing it, according to an essay by Seoul-based developer Hichoi-Dev. The ne…
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 …
A new open catalogue, low-level-skills-trothbyte on GitHub, documents 55+ failures of AI coding agents in assembly, Rust, concurrency, and systems code, backed by independent research, but its propose…
DeepSeek's open-source Harness runtime, released on GitHub on August 13 under an MIT license, reportedly surpassed 95,000 stars in two days, signaling that the agent harness—the runtime, tool registry…
The Model Context Protocol (MCP) shipped its largest revision since launch on 2026-07-28, deleting protocol-level sessions, the Mcp-Session-Id header, the initialize handshake, SSE resumability, and t…
GitClear's analysis of 623 million code changes from 2023 through 2026 shows AI-era tech debt is measurable: refactoring dropped from 21% of changed lines in 2022 to 3.8%, while copy/pasted code rose …
Dextra Labs' reference architecture for customer-service agents that execute workflows, such as processing refunds and updating accounts, correctly distinguishes between retrieval chatbots and action-…
Rust SDK rmcp 3.x now tracks the stable 2026-07-28 MCP spec revision and offers compile-time schema checking and single-binary distribution, making Rust a more reliable choice for MCP servers that hav…
A Dev.to post by Taylor Wang argues that reviewing AI-written rate limiters should focus on whether the code allows injecting a fake clock, not on the bucket math, because injectable time turns genera…
Crawdad, an AI agent security proxy, published Contemporary Agent Attacks, an open benchmark of 497 attack samples and 1,172 benign ones, including a documented failure list where its own product scor…
A Keras model file is executable code, not data, because its config can carry marshalled CPython bytecode via Lambda layers, and Keras's safe_mode has been bypassed repeatedly, with CVEs including CVE…
ProofRun, a five-day-old Go CLI with 12 stars on GitHub, treats coding-agent test claims as cache entries that expire, binding results to a SHA-256 hash of the code state and marking them STALE when c…
HolaOS, an open-source AI agent workspace climbing GitHub's trending charts with roughly 9,700 stars, positions the agent as a swappable component while memory, tools, and OAuth grants persist across …
LoopX, a stdlib-only Python project from ex-ByteDance engineer Ruiteng Huang, has gained 4,800+ GitHub stars since May by keeping agent state outside the runtime, using a CLI and file-backed store to …
On August 5, AWS made native vector search generally available in Amazon DynamoDB across all commercial regions and GovCloud, enabling single-digit-millisecond latency at 99%+ recall for up to 4,096 d…
Microsoft Foundry's agent identity model, built on Microsoft Entra, provides three permission planes—user-present, autonomous, and approval-gated—to address over-privileged agents, but a publish-time …
SpaceX closed its $60 billion all-stock acquisition of Cursor's parent Anysphere on August 15, days after SpaceX's IPO, while Windsurf was rebranded as Devin Desktop by Cognition in June and GitHub re…
WebGPU is now enabled by default in every major browser, making in-browser LLM inference a deployable tier, according to a tutorial on dev.to that builds a health-log analyzer running Llama-3-8B entir…
Semantica, a Python framework with more than 8,000 GitHub stars, is positioning agent memory as an audit tool by recording decisions as first-class nodes with W3C PROV-O provenance and bi-temporal fac…
Deltix, an agentic UX testing tool for mobile apps, debuted on Hacker News with a bumpy launch but introduced a design pattern that the agentic-testing space is converging on: AI at authoring time, de…