A curated collection of noteworthy tools, articles, and resources from across the web — searchable, organized, and enriched with AI analysis.
Showing 193-216 of 1252 bookmarks
All Stories
The San Francisco Compute Company. Buy and resell large-scale, vetted GPU clusters from the terminal.
llama.cpp with adaptive speculative decoding (--spec-draft-adaptive) and a Vulkan backend tuned for AMD Strix Halo. 4.7x on structured output, 1.9x mainline prefill on MoE. - LaurentZuijdwijk/llama…
8 Claude skills · 100+ recon capabilities · 80 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · ~10,000 lines of structured tradecraft. Drop-in SKI…
Agent-native way to access any website. Bridging agent CLI and web GUI through API. - imoonkey/openweb
Pinned stock Qwen3.8-27B NVFP4 + DFlash2 recipe and measured evidence for one NVIDIA DGX Spark - sxuff/qwen38-27b-nvfp4-dflash2-dgx-spark
Highlights that adapt their length and shape to the query, so agents read exactly the passages they need.
What Support Qwen3.8-Flash-Next (qwen4_exp), text-only. Model structure: 36 GDN (gated delta net) + 12 QSA (compressed block-sparse attention) layers 4-stream hyper-connection residual PLE n-gram…
Run any model in Grok Bot — one-command setup, model picker UI, evidence-based provider wire maps, and an update-proof doctor. Not farming you, arming you. - OnlyTerp/opengrok
GLM-5.3 Flash EXL3 for 2x DGX Sparks. Contribute to MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks development by creating an account on GitHub.
Tesla V100 32GB to 60 tok/s — every gotcha, measured.
Companies with mature operations may earn $100K–$2M+ per anonymized data package. Request a preliminary estimate in five questions.
Score past Claude Code, Codex, and Warp agent conversations against tested rubrics, then get concrete edits to your SKILL.md files — free and open source.
Start with OpenAPI. Generate SDKs in multiple languages, interactive API documentation, and an agent-first CLI.
The mobile terminal for AI coding agents on iOS and Android. Native mosh, push notifications, voice input. Zero desktop install.
Start free with Documentation.AI. Compare plans for AI documentation, private docs, analytics, authentication, team seats, and higher AI usage.
[OFFICIAL PRODUCT PAGE]·The first mini PC with Strix Halo, available in 64G and 128G versions. It’s based on the Sixunited’s AXB35-02 board with stock cooling. Reviews·Retro Game Corps·Alex Ziskind·ServeTheHome·Team Pandory·jack stone
Serve Markdown to AI agents and LLMs via the Accept: text/markdown header. Browsers get HTML, agents get clean Markdown.
Statically verify your layout code. Contribute to chenglou/freerange development by creating an account on GitHub.
A collection of high-performance JavaScript tools written in Rust
Aperture’s GA release offers built-in tokens, Tailscale MCP endpoints, chat Projects, and fine-grained tool permissions.
Today we’re launching a developer preview of WebMCP on Cloudflare. With one switch, any site becomes usable by browser AI agents — no new APIs, no origin changes — while the human stays in control and creators keep their traffic.
🤖 WebMCP. Contribute to webmachinelearning/webmcp development by creating an account on GitHub.
SigNoz is an open-source, OpenTelemetry-native observability platform for your team and their AI agents. Get logs, metrics, and traces in one tool with features like APM, distributed tracing, log m…
Gemini 3.5 Transcribe demo. Hold a key. Speak. It types. Smart dictation for macOS. - google-gemini/jot-gemini-transcribe-macOS
