OPEN SOURCE

Mistral OCR 4 and Baidu's Unlimited OCR both hit Hacker News today. The useful takeaway for developers is that OCR is no longer just text extraction. It is becoming a runtime decision for document agents.

OpenMontage is trending because it treats video production like a repo-shaped agent workflow: scripts, assets, render pipelines, review loops, and coding agents working across the whole process.

A developer used OpenAI Codex to build a fully open-source WYSIWYG editor for TikZ figures. The technical approach and reception on Hacker News offer a useful case study in what agent-built software looks like when shipped.

Baidu releases Unlimited OCR, an open-source vision-language model that parses 100+ page documents in a single pass without memory blowup. Here's what developers need to know.

Switzerland's fully open foundation model promises transparent training data and EU compliance. The HN crowd has questions about actual performance.

A YC W25 startup open-sources CADAM, a browser-based tool that converts natural language to parametric OpenSCAD models. HN debate: is text-to-CAD genuinely useful or just another demo?

Cohere shipped its first developer-facing model on June 9, 2026. North Mini Code is a 30B mixture-of-experts coding model with 3B active parameters, Apache 2.0 weights, and a deployment footprint of a single H100. Here is what it actually offers and where the open questions are.

Epic Games open-sourced Lore, a centralized version control system designed for binary-heavy game projects. It uses Merkle trees, on-demand file hydration, and native chunked storage to handle terabyte-scale repos that Git struggles with.

Kimi K2.7-Code is Moonshot's open-source 1T parameter coding model with 30% fewer reasoning tokens than K2.6. Here's how to set it up with Claude Code, pricing breakdown, and honest benchmark analysis.

OpenCode is the fastest-growing open-source AI coding agent - 160K GitHub stars, 7.5M monthly users, 75+ model providers. Here is how to set it up, configure models, and use it effectively in your workflow.

deepseek-chat is deprecated and disappears July 24, 2026 - here is how to migrate to V4 Flash or Pro, with verified pricing, thinking-mode mapping, and a step-by-step checklist.

DeepSeek's open-weights frontier family, previewed April 24, 2026. V4-Pro is 1.6T total / 49B active params; V4-Flash is 284B / 13B. 1M context standard. Weights on Hugging Face.

Open-source AI coding agent for terminal, desktop, and IDE. Works with 75+ LLM providers including Claude, GPT, Gemini, and local models. Runs parallel sessions on one project.

Open-source AI agent built in Rust, now governed by the Agentic AI Foundation at the Linux Foundation. Desktop app, CLI, and API. 15+ model providers, 70+ MCP extensions.

Open-source AI gateway: call 100+ LLM providers in the OpenAI format via a Python SDK or proxy. Spend tracking, budgets, rate limiting, load balancing, and fallbacks built in.

Open-source LLM engineering platform: tracing, evals, prompt management, and datasets. Self-hostable, OpenTelemetry-native, with 50+ framework integrations.

Open-source cloud sandboxes for AI agents. Isolated environments that start in under 200ms, run code in Python, JavaScript, and more, and persist sessions up to 24 hours.

Google released DiffusionGemma today, a 26B MoE open model that generates entire 256-token blocks in parallel instead of one token at a time. Here is what that means for latency, local inference, and the post-autoregressive landscape.

A hands-on look at Mastra, the open source TypeScript framework for building production-ready AI agents and workflows -- with verified setup commands, honest tradeoffs, and current pricing.

The rsync Claude debate shows why teams need reproducible defect forensics before AI attribution becomes a public blame machine.