AI Briefing#open-source
The latest AI and developer news about #open-source, with the original source and a short summary.
The latest AI and developer news about #open-source, with the original source and a short summary.
Goldie, an open-source CLI tool that integrates with coding agents to automatically generate store assets based on actual app execution screens, has been released.
NVIDIA released a NemoClaw-based agent that separates knowledge and judgment, improving benchmark accuracy to 90.9%.
Copperhead, an open-source PCB design AI agent that directly modifies KiCad files and automates ERC/DRC verification, has been released.
Solo.io has released agentdesktop, an open-source tool that controls AI agents and MCP servers in developers' local environments.
The MCP tool 'Watch Skill' for Claude Code has been released, enabling it to analyze screen recordings to verify code changes.
The OUI-1 model, fine-tuned from DiffusionGemma, achieved 71.7% on the Generative UI Benchmark, releasing high-quality UI generation technology capable of local execution.
inclusionAI has released Ling-3.0-flash-VL, a multimodal model featuring a 1M token context window and MoE architecture.
An open-source skill has been released to prevent verbose responses from AI coding agents by prioritizing core action instructions and step-by-step guidance.
The local gateway 'my-free-code' has been released, allowing 9 coding agents, including Claude Code, to share model configurations.
Reverify, a deterministic verification tool that checks AI binary analysis hallucinations against actual byte data, has been released.
The open-source tool 'Portable Resume' has been released to transfer session context between various coding agents such as Claude Code and Codex.
An open-source skill has been released that requires AI coding agents to write detailed briefs before coding.
The LLM-based multi-agent financial trading framework TradingAgents released v0.4.0, enhancing support for macro data and latest models.
VoiceStudio, an open-source tool for performing voice cloning, video dubbing, and transcription locally, has been released.
Catenary, a spatial canvas-based IDE for managing AI coding agents, has been released for free.
Researchers have released EmbedFlow, an open-source tool that enables instant switching between embedding models by leveraging existing indexes without backfilling.
Apache Incubator project Maka has released a workspace that stores all agent execution logs locally.
The Qwen team and Huazhong University of Science and Technology (HUST) have released Qwen-Drive-1.0, a vision-language model specialized for autonomous driving, achieving a score of 90.7 on the NAVSIM benchmark when applying RL.
Human-Agent-Society has released 'Reef', an open-source infrastructure that updates model weights and harnesses in real time using user feedback during agent serving.
The open-source library ParaRNN, which supports parallel training of nonlinear RNNs, has been released, achieving up to a 200x speedup.
Tencent has released EVIE-8B and its lightweight counterpart EVIE-4.5B, visual document retrieval models that achieved SOTA on ViDoRe V3.
The open-source autonomous research framework freephdlabor has been released, eliminating fixed workflows by having ManagerAgent dynamically assign tasks.
Light Origins has released LightNav-0, a 4B-parameter navigation model that controls multiple robots using only a front-facing RGB camera without depth sensors.
The open-source tool hayamimi has been released, generating real-time multilingual subtitles using only the CPU without GPU dependencies.