Full-text search across 8109 articles. Combine with topic and date filters; results sorted by relevance.
AstroForge announced Solo, an in-house transformer model that will take full control of its Autonomy-1 probe when it separates from the rocket in 2027, with no ground commands and no human in the loop, CEO Matthew Gialic…
A developer released Sniffslop, a free browser extension for Chrome and Firefox that classifies hovered text blocks of 25 or more words using the Jev API from TypeSafe, defaulting to a single score question asking "How l…
Parity engineers ran a self-hosted inference trial of the open-weight DeepSeek V4 Flash model that handled more than 144,000 requests and almost 12.9 billion tokens from 25 engineers between 16 August and 12 September, a…
Life Forge, an open-source flight simulator for autonomous AI agents, was released as a Show HN project that uses 3D MAP-Elites quality-diversity algorithms to co-evolve adversarial perturbations against tool-using agent…
Developer Viktor Petersson released Agent IAP, an open-source identity-aware proxy that pulls credentials from 1Password so AI agents receive narrow, time-boxed tokens instead of long-lived API keys. The proxy checks eac…
A developer argues that AI agents making real changes to code, configs, and infrastructure leave insufficient evidence behind, since a Git commit alone cannot show what the user asked for, which tools the agent called, w…
MCPJam Inspector, an open-source TypeScript platform for testing and evaluating MCP servers, MCP apps and ChatGPT apps, was last updated in September 2026 and holds 2.2k stars on GitHub. The tool lets MCP server develope…
A developer who ran the Hermes personal agent for three months found that agent frameworks consume an order of magnitude more tokens than plain chatbots, with a simple "hi" message burning 17,292 tokens because large sys…
The MCP server io.github.Aureliolo/gdharness v1.0.16 was published to the official MCP registry on 2026-09-23, distributed as gdharness on npm, according to the mcpindex index. The index reports a semantic screen of the …
The NOAA marine MCP server io.github.cyanheads/noaa-marine-mcp-server reached version 0.6.0, published to the official MCP registry on 2026-09-23 and distributed as @cyanheads/noaa-marine-mcp-server on npm and as a hoste…
Nofax v0.2.18, a local stdio MCP server providing human-in-the-loop approvals and notifications for AI coding agents, was published to the official MCP registry on 2026-09-23 and is distributed as nofax on npm, according…
The iNavi Maps Docs MCP server, version 0.4.1, was published to the official MCP registry on 2026-09-23 and is distributed as @inavi-maps/mcp-server on npm, according to the mcpindex server index. mcpindex reports that i…
The ai.exa/exa MCP server, version 3.4.1, was published to the official MCP registry on 2026-09-23 and is distributed as a hosted remote over streamable-http, according to the mcpindex index. The index's semantic screen …
The dev.dvt/dvt MCP server, version 0.5.55, was published to the official MCP registry on 2026-09-23 and is distributed as a hosted remote over streamable-http, according to the mcpindex registry index. mcpindex's semant…
TrustVerum Public Reading and Participation Guide v1.2.0 was published to the official MCP registry on 2026-09-23 as a hosted remote over streamable-http, according to the mcpindex index. The index's semantic screen, an …
The inn-check-ru MCP server, version 1.11.1, was published to the official MCP registry on 2026-09-23 and is distributed as inn-check-ru-mcp on PyPI, according to the mcpindex index. The server checks Russian counterpart…
DigestSEO's Web Validator, an MCP server that audits public webpages and supplied markup for HTML, CSS, SEO, JSON-LD, and link issues, was published to the official MCP registry at version 1.3.23 on 2026-09-23 as the npm…
DayPlay's MCP server io.github.Teamdayplay/dayplay-mcp reached version 1.3.2, published to the official MCP registry on 2026-09-23 as a hosted remote over streamable-http, according to the mcpindex leaderboard. The index…
Anthropic removed over 80% of Claude Code's system prompt for models like Claude Opus 5 and Claude Fable 5 with no measurable loss on its coding evaluations, according to a July 24, 2026 post by Thariq Shihipar titled "T…
Bonsai 2 27B, a ternary-weight quantization of a 27B-parameter Qwen3.8-based model, scores an average of 84.78 across a 14-benchmark thinking-mode suite, which its model card reports as 98.2% of the FP16 original's intel…