Full-text search across 7889 articles. Combine with topic and date filters; results sorted by relevance.
Agent-ML-skills, a curated pack of 15 battle-tested machine learning skills, has been released to teach AI coding agents like Codex, Claude Code, and Cursor how to avoid common ML mistakes such as data leakage and scorin…
BridgeToAgent has released a free MCP connector that allows AI assistants like ChatGPT, Claude, and Cursor to check whether any online store is readable and shoppable by AI agents. The tool scores stores on a 0–100 readi…
A developer has identified a critical gap in the modern software stack, coining it the "Intent Layer" — the missing middle between user signal tools like Dovetail and Intercom and execution tools like Cursor and Claude C…
AgentBrew launched as a centralized Model Context Protocol multiplexer that lets AI developers configure tools once and use them across multiple agents including Claude Code, Gemini CLI, and Cursor. The open-source tool …
According to a Business Insider survey of over two dozen startup founders and VCs, Anthropic's Claude Code has become the dominant AI coding tool in startups, praised for handling complex engineering tasks and autonomous…
Stripe design manager Owen Williams built Protodash, an internal AI-powered prototyping platform that lets designers and product managers create high-fidelity dashboard prototypes without writing code. The tool, which ev…
Two new tools from Railway to improve how AI agents interact with their platform: a Remote MCP Server at mcp.railway.com that allows any MCP-compatible agent (like Claude or Cursor) to manage projects via OAuth without l…
AI-generated code now accounts for 42% of all developer output as of January 2026, up from 6% in 2023, according to a report on enterprise AI code optimization. The same report notes that 96% of developers do not fully t…
Qualixar released SuperLocalMemory (SLM), a local-first long-term memory tool for MCP clients including Claude Code, Codex and Cursor, installable via `npm install -g superlocalmemory` on Node 18+ and Python 3.12+, or `p…
Nexusyn launched a long-term memory engine for AI agents that scores 81.1% (284/350) on LongMemEval-S and 74.3% (1,476/1,986) on LoCoMo, according to the company's published benchmarks. The Go-based engine combines bi-te…
Developer Rehan launched Universal Modder, an open-source toolkit that lets AI coding agents mod almost any PC game through a shared knowledge base, Agent Skills, a fal MCP server and a `um` CLI. The project supports Cla…
Conductor released version 0.89.0, adding "Sign in with ChatGPT" so users can bring their ChatGPT plan into Conductor via Settings → Agents → Codex and a "Continue with ChatGPT" button, built in partnership with OpenAI. …
The Model Context Protocol (MCP) message format is JSON-RPC 2.0, using request objects with jsonrpc, method, params and id fields, result or error responses, and notifications without an id, all POSTed over HTTP to a sin…
A developer built and open-sourced Glow Comments (v0.2.3), a visual HUD extension for VS Code, Cursor, and Windsurf that highlights risky or AI-generated code through luminance-based glow effects and an "Audit Lens" nega…
Directus launched a native MCP server that connects AI tools such as Cursor and Claude Desktop directly to a user's live database, letting developers scaffold collections and content teams translate posts through convers…
A developer released ai-memory, an open-source Rust binary that provides vendor-neutral, git-backed long-term memory for more than 20 AI coding harnesses including Claude Code, Cursor, and Codex. The tool captures sessio…
CTXFW, an open-core context firewall and Model Context Protocol gatekeeper from HeuristicoLab, compacts peripheral code in coding-agent context windows by 72.4% by replacing distance-1 and distance-2+ module implementati…
AI engineer and educator Chase Lean used OpenAI's GPT-6 Astra to build an interactive aquarium wallpaper for Mac, posting a seven-part thread on X on September 17th showing fish that change direction as the cursor moves.…
Reinforcement learning has become the standard final stage of training frontier language models, with GRPO on verifiable rewards now the standard recipe since DeepSeek-R1 popularized it, according to a technical analysis…
Supabase released "Observability on Auto-Pilot" on Sept. 13, 2026, shipping four prepared prompts — Health and Performance (checked hourly) and Security and Capacity (checked daily) — that customers run through their own…