AI Agents
AI Agent technology and applications
Articles
Datalab’s Marker 2 vs MinerU, Docling and LiteParse: 76.0 on⭐8
Datalab’s Marker 2 scores 76.0 on olmOCR-bench with 5× MinerU’s throughput, outperforming Docling and LiteParse in document parsing speed and accuracy for produ...
Meet the New Claude Opus 5: Frontier-Class Agentic Coding and⭐7
Anthropic launches Claude Opus 5 with frontier-level agentic coding and computer use at the same price as earlier Opus models.
Build a Complete OCR Pipeline with Baidu's Unlimited-OCR for⭐8
Learn to build a complete OCR pipeline using Baidu's Unlimited-OCR 3B model for high-resolution images and multi-page PDFs with optimized GPU setup and batch pr...
Best Open Speech Recognition (ASR) Models in 2026: WER,⭐7
Compare 2026's top open ASR models: Cohere Transcribe, Whisper Large-v3, Nvidia NeMo Canary, Meta SeamlessM4T-v2 on WER, language support, latency, and licenses...
You Didn’t Get the AI Model You Paid For⭐9
Many AI providers now silently swap requested models for cheaper or faster alternatives, with up to 30% of API calls affected by 2026, creating legal and ethica...
Andrew Ng Releases OpenWorker: An Open-Source, Local-First AI⭐8
Andrew Ng launches OpenWorker, an open-source, local-first AI agent that delivers finished tasks like reports and emails, not open-ended chat.
Mistral AI Releases Leanstral 1.5: An Apache-2.0 Lean 4 Code⭐7
Mistral AI releases Leanstral 1.5, an Apache-2.0 Lean 4 code agent solving 587 of 672 PutnamBench problems for advanced theorem proving.
Meet WebBrain: An Open-Source, Local-First AI Browser Agent That⭐8
WebBrain is an open-source, local-first AI browser agent that reads pages and automates tasks in Chrome and Firefox without sending data to external servers.
RAG-Anything Tutorial: Build a Multimodal Retrieval Pipeline for⭐8
Build a multimodal retrieval pipeline in Google Colab with RAG-Anything. Learn to index text, tables, equations, and images for hybrid search and AI-powered rea...
Meet Alibaba’s Page Agent: A JavaScript In-Page GUI Agent That⭐7
Alibaba’s Page Agent uses JavaScript to control web interfaces via natural language and the DOM, offering accurate, in-page browser automation without external ...