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.
OpenMuse is an open-source personal AI agent built on CopilotKit that features a persistent browser, optional Linux terminal, and file management, with web search enabled by default via Parallel.
Devin now retains personal learnings across sessions via a Git-based Memory Drive and uses a daily background 'Dreaming' process to consolidate and link memories.
The open-source CLI tool removes Apple Intelligence foundation models from disk and blocks their re-download by redirecting asset requests to a closed local port.
The tool reports up to 62.5% reduction in overall tool output and 88.4% on Claude Code by using optimizers like RTK to minimize context noise.
New mixed-precision 3-bit weights for Qwen3.8 27B enable a 569,878-token reusable cache on a single AMD R9700, accelerating agent workflows by up to 12x for first-token latency with a 2.9-point MMLU-Pro drop vs MXFP4.
GPT-6 Astra solves all 30 standard puzzles, while solve rates drop to 20% on 15x15 grids at best effort levels.
The family includes specialized models for speech, syllable control, and long-document translation, covering 150 languages.
The framework uses strict directory isolation and an email/dispatch system to allow agents to report bugs and coordinate tasks without human intervention.
The open-source tool replaces shared API keys with individual sign-ins, logging every call under the user's name with one-hour token lifetimes.
The new benchmark evaluates 507 stateful business workflows by verifying final database states rather than tool call success, revealing that 67% of agent failures occur despite clean termination.
Aperture, a newly launched open-source AI code editor, validates code changes through parsing, type checking, and in-browser test execution before applying them to files.
The ban applies to all COSMIC repositories except cosmic-flatpak, where AI assistance is permitted for simple manifest submissions.
The update reduces voice roughness and break-up while maintaining ~300 ms first-audio latency on laptop CPUs.
The MIT-licensed tool uses SQLite FTS5 and optional local embeddings to provide offline, Markdown-based memory for AI coding agents.
The 9B multimodal model claims 8 of 9 top scores in its size band on spatial benchmarks and includes an open-sourced data pipeline.
The 6B parameter model was trained on approximately 2,500 hours of real robot data and supports parallel grippers and dexterous hands.
Debian announced a self-service LLM inference portal on September 23, 2026, with recent updates adding the scaleway/qwen3.8-27b model and improved documentation.
Meta has open-sourced code allowing users to build their own Muse AI gadgets using hardware like ESP32 and Raspberry Pi, while also distributing 5,000 pre-built 'Muse Home Link' devices.
Muse has open-sourced its device SDKs and firmware under the Apache 2.0 license, allowing developers to build custom hardware interfaces for the Muse AI assistant using ESP32 and Linux devices.
Redis creator antirez has released ds4, a C-based inference engine supporting DeepSeek V4, GLM 5.x, and Qwen3.8 Flash Next on high-memory hardware.
Streamline combines Cloudflare Workers, Containers, and Stream to enable real-time video manipulation like overlays and burned-in subtitles.
The new MIT-licensed benchmark evaluates models on finding and fixing real-world bugs in large codebases before users encounter them.
The platform allows agents to run on schedules or triggers with shared memory and requires human approval for risky actions.
The 8B model, based on Qwen3-8B, generates reports in an average of 51.1 seconds compared to 178.5 seconds for the previous Claude-based Thinking mode.