Full-text search across 8150 articles. Combine with topic and date filters; results sorted by relevance.
KinoPipe, an FFmpeg-as-a-service MCP server for AI agents, published version 1.0.1 to the official MCP registry on 2026-08-25, offering typed video editing tools, async jobs, and downloadable outputs. The server, distrib…
Io.github.iqingyoung/429-throttle-mcp version 1.2.0, a rate-limited MCP HTTP proxy using sliding window and token bucket algorithms to prevent 429 errors in long-running tasks, was published to the official MCP registry …
ArkGate, an MCP server distributed as arkgate on npm, released version 4.7.0 to the official MCP registry on 2026-08-25, designed to prevent TypeScript agents from breaking architectural layers. The mcpindex integrity sc…
LowlandData EU Marketplaces, version 1.2.0, was published to the official MCP registry on 2026-08-25, offering GDPR-clean marketplace listings and prices from 14 European countries without seller personal data. The serve…
Vaara, an accountable autonomy proxy for gating, tamper-evident audit, and time anchoring of MCP tool actions, released version 1.76.0 to the official MCP registry on 2026-08-25, distributed as vaara on PyPI under the Ca…
Exomem v0.61.0, a local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search, was published to the official MCP registry on 2026-08-25 and is distributed as exomem on PyPI. The mcpi…
Red Hat Lightspeed MCP, a Model Context Protocol server for Red Hat Lightspeed advisor, image builder, inventory, and more, was published to the official MCP registry as version 1.0.47+52cc4ab4 on 2026-08-25, distributed…
Ventrova released sentinel-scan-cli v1.4.8, a free open-source command-line tool that runs 15 prompt-injection and jailbreak attacks against LLM apps and MCP servers, tagging findings with OWASP LLM Top 10 and OWASP MCP …
A developer has open-sourced LEO, a system of 41 codified laws, 22 specialist roles, and a file-based memory that stops autonomous AI coding agents from repeatedly breaking the same production defects. The system address…
ClaudeGate, a new open-source local API gateway, enables Claude Code CLI and Anthropic SDK applications to use any AI model, including free and frontier models from OpenRouter, DeepSeek, and others, by translating Anthro…
A developer compared direct database connections with brokered connections using the Model Context Protocol (MCP) for AI assistants, highlighting security and workflow trade-offs. The analysis shows that while direct con…
A developer has built Docora, an open-source documentation framework for Next.js and React, inspired by Docus in the Nuxt ecosystem. It offers file-based routing, MDC syntax, built-in search, SEO defaults, i18n, an MCP s…
Andrew Ng, cofounder of Google Brain and Coursera, relaunched DeepLearning.ai with a focus on AI Engineering, identifying four key skills: building and deploying AI applications, software engineering fundamentals, using …
Gitwhy, a new open-source tool in beta, automatically records AI provenance for every git commit by installing a post-commit hook that captures environment variables such as $CLAUDE_CODE_MODEL, $COPILOT_MODEL, and $AI_AG…
A developer built UniUI, a Socratic AI tutor for Nigerian university students that verifies every answer using 50+ academic engines. The system, now used by over 190 students, combines LLMs from Groq and OpenRouter with …
A GitHub analysis of 255,068 newly written agent skills found that the share written in non-English languages rose from 13.0% in Q1 2026 to 16.3% in Q2 2026, a three-point jump in three months, compared with GitHub-wide …
AMD detailed the Instinct MI400 series GPU architecture at Hot Chips 2026, highlighting the MI455X silicon with 432 GB of HBM4 memory, 23.3 TB/s bandwidth, and a peak MXFP4 performance of 40.26 petaflops, up to 4x the MI…
FreeToken, a local inference tool, enables running mixture-of-experts models with over 290 billion parameters on a single consumer GPU by streaming only active experts from system RAM, avoiding the need for multi-GPU set…
Escha Labs Inc. released Escha-W2, a 2-bit quantized build of Qwen3.8-27B that compresses the 27-billion-parameter model to 10.15GB, enabling 128k context on a single 24GB GPU while matching FP8 quality on benchmarks. Th…
Escha Labs released Qwen3.8-27B-Escha-W2, a 2-bit quantized build of Qwen3.8-27B that fits 10.15 GB of weights on a 24 GB consumer GPU, enabling 64k context out of the box and up to 128k with tuning via SGLang. The model…