Introducing olmOCR, our open-source tool to extract clean plain... text from PDFs! Built for scale, olmOCR handles many document types with high throughput. Run it on your own GPU for free—at over 3000 token/s, equivalent to $190 per million pages, or 1/32 the cost of GPT-4o!show more

1/ Introducing Glider - the smallest model to beat... GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥show more

Turn any PDF, image, DOCX, or PPTX into clean... Markdown! Production workloads contain millions of pages, mixed formats, inconsistent layouts, low-quality scans, and documents written in dozens of languages. Datalab Marker v2 (open-source with 40k stars) handles that workload at scale through one open-source document parsing pipeline. It recovers: - Reading order - Complex equations - Images and captions - Tables and nested tables - Text from scanned pages - Headings and page structure It can return Markdown, JSON, or HTML for RAG pipelines, search indexes, data extraction systems, document agents, and archive migrations. Marker v2 runs at up to 23.7 pages per second on a single B200 GPU and supports more than 90 languages. GitHub repo: (don’t forget to star it ⭐) I recently used Datalab to build an agent that scans an identity document, extracts the required fields, and fills a tax form automatically. The article covers the full workflow, including document parsing, structured extraction, field mapping, and form completion. Read it below.show more

Parsing PDFs at scale with LLMs is cost prohibitive.... Newer models (e.g. gemini 3) are good at reading pdfs, but you burn unnecessary vision tokens even when the page is text heavy. We’ve built in a “cost-optimizer” within LlamaParse that will dynamically route pages to fast/cheap parsing depending on its complexity. Complex pages (e.g. those with tables/charts/diagrams) will still get routed to our VLM-enabled modes. This will let you save anywhere from 50-90% of parsing costs, at much higher accuracy compared to the comparable mode of feeding screenshots into VLMs. Check it out!show more

Qwen has just released a model on par with... GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details belowshow more

Introducing: OpenGranola 🔥 I built an open source meeting... copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link belowshow more

Free and open-source desktop app for downloading videos or... extract audio from hundreds of sites, including YouTube and TikTok, with playlists, history, and built-in compressionshow more

Cline Desktop just launched. An open-source workspace for open-weight... models 🤯 > Import tasks from other coding agents > Run agents in parallel > Schedule tasks to run on their own Free models built in: DeepSeek V4 Flash, GLM 5.3 Flash, Laguna S 2.1. I had early access and I can assure you it feels incredible. Pick your model and provider, and run it. 100% open source.show more

Today SciPhi is open-sourcing Triplex, a SOTA LLM for... knowledge graph construction. Triplex is so small that it can be used with SciPhi's R2R to build knowledge graphs directly from your laptop. Triplex outperforms few-shot prompted gpt-4o at 1/60th the inference cost.show more

Introducing step . parts, an open source directory of... 12,000+ STEP parts for your next CAD project Many CAD tools like Autodesk have huge closed libraries of standard mechanical and electrical parts The goal is to build an equivalent catalog for the open source CAD communityshow more

NanoBanana 2 just made your static ad agency obsolete.... And I just open sourced the entire tool. Drop your product page URL. It pulls your logos, product images, fonts, colors, and brand voice automatically. Builds a full brand guide for you. Then generates ad creatives at scale using nearly 4,000 high-performing ad templates across 8 niches. It dynamically matches the best templates to your brand and brief. Here's what makes it different: → Instant resizing Get any ad in 1x1, 4x5, 9x16 with one click. No regeneration. No broken text. → Highlight-to-edit See an issue? Highlight the area and tell it what to fix. → Multiple brand profiles Run different brands or segments from one tool. → Auto persona building from real customer reviews → Multiple QC loops on briefs and final assets Catches AI-isms before you do. → Upload your own templates or use ours Runs locally. Just needs your Claude and Google API keys. This is the lite version of what we use internally. You get the full finished tool AND the open source code to make it your own. Creatives still design the system, this handles iteration and scale. Want a copy to download? 1. Like this post 2. Comment "AI" Will DM you the tool along with a tutorial shortly after.show more

This free tool lets Claude scrape Google Maps for... you, on autopilot. It's called Google Maps Scraper Kit. Give Claude a city and a business type, and it drives a local scraper to hand back a clean list of businesses, names, phones, emails, websites, ratings, and reviews. → One-command setup, runs entirely on your laptop → Claude Code skill triggers on plain language → Optional social media lookup at no extra cost → Built-in rate-limit safeguards and proxy support for larger jobs 100% Free. Open source.show more

We are launching Open Dots, run the same capabilities... in 1/10th of the cost OpenAI shipped Dot yesterday for Pro users. Ours is open source, runs on your Mac and cheaper Here's how it works: - each dot has its own browser that stays logged in securely - it can use and setup triggers on your Gmail, Calendar and 1,500 other apps - you can call it and give it things to do while you talk - dots can coordinate and schedule reminders built with Composio OpenRouter free and open source:show more

You can now input PDF files directly to the... Responses and Chat Completions APIs! Then let o1, gpt-4o, or gpt-4o-mini generate text with that context.show more

For TreeHacks, we built Braille Bot. It transforms any... document—text, images, or websites—into printed braille at a fraction of the cost. It can be easily installed on an existing 3D printer for just $15, significantly cheaper than anything currently available.show more

Introducing BlockPicks, a free-to-play, play-to-earn prediction game. The goal... is simple, onboard users into web3 on a mass scale with small amounts of $BLOCK each week for their participation. Our original BlockSix game wasn’t built to scale. So, we built a new one from scratch. Here’s what’s new…show more

We're launching 5x faster document parsing in the Firecrawl... MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!show more

One more end-of-the-year update for the #holisheet. Next year,... we will show more fancy results with this low-cost, high-throughput, label-free, volumetric, open-source, lens-scanning, rotating, HOlographic LIght-SHEET. In collaboration with the PrakashLab. #staycuriousshow more

Alright guys, hear me out I was skeptical about... Llama 4 coding skills... until I started comparing it to other models, including the earlier version of GPT-4o This thing is free, open source, and honestly pretty close to GPT-4o (pre-update), wild if you think about itshow more

New open-source agent harness just landed! I got early... access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.show more