Tools Bench.

morluto/rea

☆146.1K

Reverse engineer anything with agents, from app behavior down to native binaries.

bilawalsidhu/gods-eye-view

☆53.2K

A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe.

cathrynlavery/diagram-design

☆52.2K

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, and Pi. 44 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.

microsoft/BitNet

☆40.8K

Official inference framework for 1-bit LLMs

mksglu/context-mode

☆27.1K

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

storytold/artcraft

☆21.0K

ArtCraft is an intentional crafting engine for artists, designers, and filmmakers

kōdlo

264

kōdlo finds prospects that fit your ICP and tells you how to warm each one up. Upload product catalogues and other docs to the Knowledge Hub, and its agent turns them into personalized messages, offers, deep searches and decks. Track client data, collaborate with your team, and manage tasks, all in one place. Connect Claude Desktop/ChatGPT Work or your code agent with kōdlo MCP to scale and orchestrate contexts.

Automations in Perplexity Computer

189

Computer Automations turns recurring work into reliable, ongoing workflows. Define a task once... such as monitoring sources, compiling reports, updating trackers, or drafting follow-ups... and an agent executes it on a schedule or in response to triggers. Built for professionals, teams, and operations leaders who need continuity without constant supervision, it remembers prior runs, builds on accumulated context, and acts proactively rather than waiting for a prompt.

Ghost Core

177

Ghost Core is a personal AI computer that runs AI models on-device, connects to your apps, files, and devices, and builds continuous context to proactively help you.

OpenScreen 2

164

Record your screen and the demo looks great on the first take: zooms planned from your clicks, smooth cursor, 3D camera moves, cursor themes, backgrounds and webcam layouts. Then let your AI agent do the edit over MCP, or cut the video yourself by deleting words in the transcript. Windows, macOS and Linux. Free, MIT, no account, no watermark.

Edgee Mod for Claude Code

87

A Claude Code mod that puts Edgee in your terminal. Keep your Claude plan, switch your session to any of 200+ models in one keystroke, and see live what compression and routing save you. Same conversation, same context. Two commands to install.

HireKey

269

HireKey is a recruiter-informed AI job-search co-pilot for tech job seekers who want to apply strategically & interview with confidence. It helps you assess your role fit, tailor resumes, communicate experience & track applications. Unlike basic ATS tools, HireKey combines AI with 10 years of recruiting experience at Microsoft, Amazon & Stripe, plus practice out loud with an interactive AI voice coach that responds to your answers & provides real-time interview feedback.

Frontrunner 🏇: Cursor for GTM

3

Platform to build and run GTM agents Frontrunner · Fall 2026 · B2B Tags: Artificial Intelligence, Sales, Marketing. Website: https://usefr.com/

Breadcrumb, record everything on your mac + context manager for AI

49 pts

Hi HN, I'm Justin. Breadcrumb records everything you do on your Mac (screen + meetings + AI transcripts + what you and your AI decided) and turns it into memory your AI can search. It's local and encrypted. You can also teach it rules by talking to it and it makes sure the right rules turn up in the right context. Works with Claude Code / Codex / Cursor / opencode. All of this is exposed to your AI as 30+ MCP tools (here's the definitions): https://innerloop.works/breadcrumb/mcp I started it in... (49 points, 9 comments).

Proton Drive for Linux

120 pts

Hello everyone, I wanted to share this small project that I have. It's born out of a necessity that I had, because Proton doesn't ship a Linux version of the drive yet (it's apparently coming out later this year but who knows?) and all the current solutions are hacky and wonky at best. But for the time being I really needed to mount my Proton drive on my Linux machine the way I mounted it on my Mac, so I (and my faithful AI slave) did this small utility that allows you to mount your Proton Drive... (120 points, 44 comments).

BraiNOTES, handwritten notes on your lecture PDFs in a browser tab

34 pts

In August, I posted here about TeXbrain, a LaTeX editor that runs completely in the browser, with no need for an account or server. (I didn't excpect it to get that much feedback, bug reports and help from here!) This is the same idea for the other half of my studies, the handwritten notes. I take them on a convertible laptop, and I've had a hard time with apps for that, taking notes from a device to another, exporting as PDF, needing an account for many of them, etc. So I've been working on the... (34 points, 2 comments).

Opus 5.5 made a fully featured Figma clone in 3 hours / 8 prompts

21 pts

I think a chasm has been crossed. Opus 5.5 few shotted a fully working Figma for me. In the past year I have been trying to benchmark vibe coded apps and see how good they get and this week it did it with very very little guidance from me. I basically just told it reach feature parity. Prior to this vibe coded apps would resemble the real software, this is not a resemblance it's the real thing. As a casual Figma user in the past, I can't really see a difference. And if there is one you have an L... (21 points, 12 comments).

LLMxRay an open-source observability tool for LLMs

10 pts

Hacker News discussion (10 points, 0 comments).

I Cut my Agent Tokens By 50%

6 pts

This started by watching the built-in tool calls in Claude code. We noticed that a LOT of the time was being spent searching for lines of code with regex. This approach makes sense when you are working in an unknown environment, but we all work inside of some codebase structure and tracking. This took us down the rabbit hole of codebase indexing and led to us building Indexio. Indexio was built to eliminate the time and tokens agents waste rediscovering a codebase. Regex calls return lots of dat... (6 points, 5 comments).

MiniMax H3 Turbo LoRA

1.5K likes

Video generation with a synchronized soundtrack MiniMax-H3 — unquantized, split across two Spaces Joint video and soundtrack out of a single denoising pass, at bfloat16 with no quantization anywhere. This Space is the denoising half: the 61.73 GiB transformer and the two autoencoders. The 62.14 GiB Qwen3-VL conditioner runs in qwen3vl-conditioner, which this Space calls over the gradio API for every request. The weights are the public MiniMaxAI/MiniMax-H3 diffusers checkpoint. MiniMax-H3 is 195.9 GiB in bfloat16 and a ZeroGPU Space is evicted at 150 GB of storage. An unquantized single Space is therefore impossible, which is why quantized demos of it run NVFP4 or float8 weights. Cut the Mini...

Jev Decision Index

605 likes

Benchmarks and news on various repros of TypeSafe's Jev Who is rebuilding TypeSafe's Jev (System One / RLCD) in the open? This static Space opens on the Decision Index leaderboard; the News tab tracks the artifacts in one combined grid, color-coded by kind: Decoding: parallel constrained decoding on stock models (inference technique, no new weights) Diffusion: text diffusion models run in a "Jev mode" Trained: Jev-like scoring heads and fine-tunes, weights often on the Hub, promised models listed last Prior art: "this already exists" claims Explainers: architecture speculation, explainers, benchmarks and roundups Cards sort by a trending score: ♥ likes on X + 5 × GitHub stars + 8 × Hub likes...

Viggle Turbo for Qwen-Image-2.1

274 likes

6-step Qwen-Image-2.1, T2I + editing, vs-base comparison Viggle Turbo v0.3 — 6-step Qwen-Image-2.1 A distilled Qwen-Image-2.1 that generates and edits images in 6 steps with no classifier-free guidance, about 5× faster than the 40-step base model. On most prompts it is hard to tell apart from the base model; small, dense text and complicated edits (multi-reference composition, face swaps, identity-preserving edits) can still fall short of it. v0.3 (2026-09-29): at 6 steps, less grain than v0.2.1 and a little softer on fine texture. We think 6 steps is close to its capacity: every further gain we found cost something elsewhere. The new 9-step setting runs 7 turbo steps and lets the base model...

The ultimate guide to multi-harness RL

235 likes

Train open models with RL inside real agent harnesses A research article built with research-article-template. Source lives in FineEnvs under content/articles/multi-harness-rl/. | Path | What | | --- | --- | | app/src/content/article.mdx | Frontmatter and the chapter registry — the explicit import list is the running order | | app/src/content/chapters/ | One .mdx per section | | app/src/content/embeds/ | Standalone HTML/D3 visualizations, one file each | | app/src/content/assets/image/ | Images | | app/src/content/assets/data/ | Data files, served at /data/ | | app/src/content/bibliography.bib | References, cited as [@key] | From the repo root, over the Hub HTTP endpoint (no git remote, no n...

Model Pulse

195 likes

Hugging Face model download stats, history & trends Daily download history, likes and derivative families for every model on the Hugging Face Hub, going back to July 2024. Look up any model: ?model=org/name Compare up to five models on one chart See how much of a model's reach comes from its quantizations, fine-tunes, adapters and merges Galaxy: every model built on a base model, drawn as a galaxy (?view=galaxy) Wrapped: any author's last 12 months on the Hub in six cards (?view=wrapped) Weekly rankings: most downloaded, fastest growing, new breakouts, biggest families, organizations A README badge with monthly downloads and a sparkline, updated daily Data comes from daily snapshots of cfahl...

MiniMax-H3 Character Swap LoRA

108 likes

Swap one character in a clip for a reference character MiniMax-H3 Character Swap LoRA A demo of akatz-ai/MiniMax-H3-Character-Swap-LoRA, Akatz Labs' experimental character-replacement adapter for MiniMax-H3's ref2va partition. Hand it a scene clip and a character reference, name who to replace, and it puts the reference character into the shot — identity, outfit and art style carried over — while the background, camera, lighting and everyone else stay where they were. Video and its synchronized soundtrack come out of a single denoising pass. Two references, in the order the model reads them, and a short targeting instruction: | Slot | Label in the prompt | What it is | |---|---|---| | refere...