Open Source Radar

Popular and fast-rising open source projects worth a look.

Open Source Radar

Google ships EmbeddingGemma 2, an open multimodal embedding model for on-device apps

The 740 million parameter model maps text, images, audio and video into one embedding space under an Apache 2.0 license, and Google says it needs as little as 191 megabytes of memory to run.

By The Poliety Staff · 5 paragraphs

Tell HN: GitHub refuses to remove cracked copies of my software after a month
NandhaKishorM/laya Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request. Python · 31.3k stars · Apache-2.0
storytold/photocraft An open-source, clean-room reimplementation of Adobe Photoshop in pure Rust Rust · 11.8k stars · Apache-2.0
shihabal3amri/DiPlay Independent CarPlay receiver for compatible Android head units. Wired and wireless public preview. Kotlin · 5.7k stars · GPL-3.0
yetone/magpie Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar. Go · 5.6k stars · MIT
KKKKhazix/AIHOT 一个自己找热点、自己写日报的网站框架。把信源和精选标准换成你的，它就是你的行业热点站。 TypeScript · 6.3k stars · MIT
rehan-remade/universal-modder Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos. Python · 4.9k stars · MIT
cdyforever/how-to-live-better 《高性价比人生指南》全书 528 条的在线单页阅读版：手机可读、可搜索、零依赖、支持离线 HTML · 9k stars
CopilotKit/OpenDots Your always-on AI coworkers that move between text, calls, and Slack. TypeScript · 4k stars · MIT
jaredpalmer/kev Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own Python · 8.6k stars · Apache-2.0
Niko1221/Strata Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input. C++ · 16.4k stars · MIT
jev-chat/jev-chat-jarvis The chat decision assistant: before you reply, Jev reads the chat, judges intent and risk, and drafts replies you fill in with one tap. You press send. Android · Windows · macOS · iOS | 聊天辅助决策工具：先看懂对方再回复，发不发由你。 Kotlin · 7.4k stars · MIT
unstablebuild/rune the development environment for pros Go · 1.2k stars · GPL-3.0
TypeLLM/TypeLLM TypeLLM: LLMs with type-safe generation Python · 933 stars · Apache-2.0
pallavi-shekhar/ai-engineering-interview-questions-company-wise Your Cheat Sheet For AI Engineering Interviews at Top AI Companies - Questions and Answers. Markdown · 1.7k stars · Apache-2.0
zai-org/ZCode Z.ai's coding agent harness. Powerful, intelligent, extensible. TypeScript · 7.5k stars · Apache-2.0
tamaratran/fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. TypeScript · 7.5k stars · MIT
mizorewww/laya-mlx Native MLX runtime for Laya typed decision models - 7-14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API. Python · 6.8k stars · Apache-2.0
shadcn-ui/lint An agent-first linter for Tailwind design systems. Write design system rules that agents can verify. TypeScript · 3.1k stars · MIT
amitshekhariitbhu/ai-system-design AI System Design - Learn how to design AI systems built on LLMs, RAG, and AI Agents step by step. Markdown · 641 stars · Apache-2.0
jtydhr88/screenwriting-skills Professional agent skills for screenwriting, television writing and dramaturgy Python · 1.6k stars · MIT
2akouwu/reverify Stop your AI from making things up - it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI. Python · 1.3k stars · MIT
Show HN: Arcadeia - A self-hosted media library with animated video previews
aimeoa/hanshuang-codex 针对GPT 6.0,workbuddyV4.1flash的破甲实验项目 Python · 1.1k stars · MIT
devagrawal09/jev-review A staged code-review workflow and local dashboard built with TypeSafe Jev. TypeScript · 675 stars · MIT
XHToken/Spark-X2.5 Spark-x2.5 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models 672 stars · Apache-2.0
hkqr/my-free-code Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming, tools, reasoning, fallbacks, and local model support Python · 623 stars · MIT
jzjzzzzzzz/agent-me Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin. TypeScript · 534 stars · MIT
Loopera-ai/loopera 面向基本面因子研究的智能体-A hypothesis-driven AI agent for fundamental factor research, with evidence-gated validation and research memory. 520 stars
whirlchat/whirl The AI chat app that sweats the details. Every top model, real memory, living documents, and your own tools. TypeScript · 491 stars · MIT