Full-text search across 8134 articles. Combine with topic and date filters; results sorted by relevance.
RFP Hub, an MCP server for searching Ethereum-ecosystem funding opportunities, was published to the official MCP registry on 2026-09-04 as version 0.1.2, distributed as @the-rfp-hub/mcp on npm. The server declares two en…
PyreCrawl v0.2.2, a self-hosted web scraping and crawling tool for AI agents, was published to the official MCP registry on 2026-09-04 and is distributed as pyrecrawl on PyPI. The tool is not yet evaluated by the mcpinde…
Granola, an AI notepad company, announced that its folder-level queries and Granola Chat feature allow product teams to surface patterns across dozens of meetings at once, with source-linked citations, addressing the pro…
Vercel's AI Gateway now offers Ling 3.0 Flash Sante, a health-focused Mixture-of-Experts model from inclusionAI with 124B total parameters and about 5.1B active per token, free through October 4. The model, designed for …
Granola, an AI notepad company, announced on September 4 that its Granola Chat feature enables users to search across all past meetings using semantic understanding, retrieving exact customer quotes with source-linked ci…
Granola's MCP integration uses Streamable HTTP with OAuth 2.0 authentication to securely connect meeting notes to AI tools, ensuring access is read-only and revocable. The company transcribes meetings in real time on mac…
Semgrep, a code security firm, reported that its early access to Anthropic's frontier AI model, codenamed Mythos, enabled its research team to find 100 runtime-verified vulnerabilities across top open source projects, bu…
MosADD, a communications layer for AI agents enabling voice commands, PTT rooms, E2EE DMs, agent email, and private recall, released version 3.0.0-alpha.45 to the official MCP registry on 2026-09-03, distributed as a hos…
Zas, an MCP server that moves files and notes between a coding agent and Zas channels with encryption, released version 0.5.1 to the official MCP registry on 2026-09-03, distributed as zas-agent on npm. The mcpindex inte…
OpenAI's GPT-6 Astra can operate a Mac computer and perform tasks such as preparing newsletters, managing email, and setting up advertising accounts with minimal supervision, according to a review by a newsletter publish…
OpenAI released GPT-6 Astra on Thursday evening, the first model it rates as Critical for cybersecurity under its Preparedness Framework, capable of finding and building zero-day exploits against hardened systems without…
A developer built a small C++ game engine, Sapana Engine, designed to run on integrated graphics and be fully editable by an AI IDE. The engine uses Diligent Engine for GPU rendering, EnTT for ECS, and Jolt for physics, …
Upstash founders Enes Akar and Mehmet Dogan launched Docs7 on September 3rd, a Mintlify-compatible documentation hosting platform that serves Markdown, WebMCP search, and agent analytics, with a free tier and a $200 mont…
AI models Claude, Grok, ChatGPT, and Gemini are experiencing outages today, affecting users of Anthropic, X, OpenAI, and Google. OpenAI reports issues across 15 services, while Anthropic's status tracker notes problems w…
A widespread outage on June 17, 2025, disrupted OpenAI's ChatGPT, Anthropic's Claude, Google's Gemini, and X's Grok, with Downdetector reporting over 36,000 outage reports for OpenAI services starting around 10:30 a.m. E…
A developer's GitHub project, zarazhangrui/follow-builders, is trending for aggregating AI builder content from X and YouTube podcasts into concise summaries. The tool aims to help developers track AI progress efficientl…
Mireye (YC S26) launched an API infrastructure that connects AI agents to cited physical-world data, enrichment, tools, and signals, enabling them to answer location-based questions with sources, timestamps, and confiden…
ImmersiveFusion released Snowglobe, an Apache-2.0 open-source tool that generates synthetic OpenTelemetry data—logs, traces, and metrics—from a single binary simulating up to 28 services, including AI agentic traces unde…
Anthropic cut cache-read prices for its Claude Fable 5.1 model by 75% to $0.25 per million tokens on September 1, while keeping input at $10 and output at $50 per million tokens, a move CEO Dario Amodei says can lower co…
Frontier large language models, including Claude and GPT, fail to generate truly random numbers, disproportionately returning 42, 47, 57, 37, and 73, because they predict the most likely token from training data rather t…