Mohammed, founder of MemorySync, documented how Microsoft Agent Framework .NET's MapAGUIServer hosting resolves GitHub issue #2517 by loading or creating an AgentSession from the AG-UI threadId and sa…
A developer built JevOps, an architecture that uses an LLM only to extract interpreted facts from messy engineering context and then hands those facts to a deterministic Jev policy engine that makes t…
OpenAI unveiled Dots, always-on cloud agents running on GPT-6 Astra with a dedicated cloud computer that reach more than 4,000 apps through a plugin ecosystem, at its DevDay 2026 on September 29 in Sa…
An independent technical guide lays out a tool-neutral JSON contract for specifying D&D encounter maps, pairing a structured brief (grid scale, required zones, routes, hazards) with a small JavaScript…
An engineer outlines a framework for gating AI feature rollouts on measurable exit criteria, combining automated evaluations, security tests, progressive delivery, and production monitoring so release…
Angie Jones, then VP of Engineering for AI Tools and Enablement at Block, described how the company rolled out its open-source Goose agent to all 12,000 employees in about eight weeks by gating MCP se…
MV2 of Munim, Inc. audited 50,742 double-quoted passages in a public Hugging Face dataset of 8,946 IELTS Writing Task 2 essays with feedback generated by GLM-4.7, finding that only 37.7% of quotes wer…
A developer running a 750-page travel directory migrated its database out of Lovable Cloud into a self-owned Supabase project using Claude Code, after replaying the repo's 89 migrations failed at file…
A developer behind AI Craftbook detailed how the small Next.js backend on Vercel verifies inbound Resend webhooks using Svix's HMAC-SHA256 signature scheme, checking the raw request body, a five-minut…
A developer documented a setup for adding free web search to the Cursor code editor through the Model Context Protocol, using a single mcp.json entry pointing at the @agentsearchhq/agentsearch-mcp npm…
A developer's survey of unattended coding-agent runs found that most overnight failures stem from plumbing rather than bad model output: schedulers that silently skip or misfire, permission prompts th…
A developer has described a JSON-based mobile test format that stores actions and selectors instead of recorded coordinates, allowing a single file with "platform": "mobile" to run on both Android and…
A developer built ToolSieve, a benchmark that measures whether canonicalising MCP tool descriptions into a fixed purpose/params/returns/side-effects schema reduces tool-poisoning attacks. Using 1,312 …
A developer released iPhone IPA Manager, an open-source Windows application with an optional private Discord bot that consolidates IPA files, Apple account assignments, and provisioning-profile renewa…
A developer designed a tenant-aware scheduler and vendor-neutral retrieval API for catalog-enrichment chatbots, making each enrichment stage idempotent, observable, and budgeted so semantic search run…
The GAL (General Agent Loop & Executor) project released a single-binary AI agent runtime that runs inside a kernel-level OS sandbox by default across Linux, macOS, and Windows. The runtime ships CLI …
A developer built a public "oracle" application around Perplexity's pplx-decider-flash-v1.2, a 4B-parameter decision model with its language head removed that returns calibrated probabilities over 255…
A developer released Commex, an open-source, self-hostable alternative to Disqus that lets site owners keep their own comment data. Users create an account, configure an organization with their own Mo…
Patrick, founder of Pidgeon, built an email API that lets AI agents obtain their own persistent addresses and wait for verification codes without polling. The await endpoint holds a request open for u…
Naetive has launched a tool that gives multiple AI coding agents a single shared understanding of a project, connecting Claude Code, Codex CLI, ChatGPT, Claude on the web and Claude Desktop through th…