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.
Vibe-Research, an open-source investment research dashboard that provides data for AI to make judgments, has been released.
An open-source benchmark evaluating 52 text-to-image models with 192 prompts has been released.
Lemonade, a local AI development tool, released a summer update adding support for 15 engines and semantic routing features.
The open-source workspace 'Codebay', which supports the latest Claude Code features with Docker isolation, has been released.
LangChain has released 'Auto-Evaluator', an open-source tool for evaluating the performance of LLM question-answering chains.
Connery provides open-source plugin infrastructure for integrating third-party services into LLM apps.
Headlong, an open-source AI agent harness that continues thinking on its own without external input, has been released.
Debian is conducting a developer vote on whether to allow LLM contributions, with 8 options on the table.
A guide visualizing the server and agent architecture of the Model Context Protocol through executable examples has been released.
BrowserCode is an open-source browser agent that controls actual Chrome by writing JavaScript code instead of relying on predefined APIs.
The tool 'key-amnesia' has been released, blocking AI agents from reading plaintext secrets such as .env files and executing commands securely.
IBM released three Granite 4.2 reasoning LLMs featuring 512K context and agentic RL.
JD Open Source has released JoyAI-Echo, which supports 5-minute video generation and omnmodal world models.
LangChain has secured a $10 million seed investment led by Benchmark to advance its tools for LLM application development.
Airbnb has open-sourced the privacy-preserving anonymization code for Project Lighthouse and published related technical papers.
Anthropic has launched a $5 million research grant program to independently assess the impact of AI on user wellbeing.
Open-source infrastructure 'Warren' has been released to centrally manage the execution, cost control, and failure recovery of coding agents.
IBM has released three Granite 4.2 reasoning LLMs featuring 512K context and agentic RL.
PandaProbe, an open-source platform that automatically diagnoses AI agent failures and recovers them using validated rules, has been released.
Tencent has released WeMM-Embedding, a general-purpose multimodal embedding model based on Qwen3.5.
Headlong, an open-source AI agent harness that continues its own thinking without external input, has been released.
LayerStoRm, an open-source engine that runs large MoE LLMs on consumer GPUs using PCIe streaming, has been released.
The 'Scaffold CoT' dataset, comprising 4 million entries, has been released to improve the reasoning accuracy of small models with 5B parameters or fewer.
An open-source CLI tool has been released to migrate conversation sessions from Claude Code to other AI coding agents such as Codex, Pi, and OpenCode.