VoxLock Extracts the Target Speaker for Voice Agents Without Requiring Enrollment
VoxLock is a 27M-parameter streaming isolator for voice agents, needs no enrollment, scores 4.95% WER on Krisp, runs on one CPU with 24 ms latency.
VoxLock is a 27M-parameter streaming isolator for voice agents, needs no enrollment, scores 4.95% WER on Krisp, runs on one CPU with 24 ms latency.
Open-source LiveMACE tests LLM agents in live markets, measuring tool use, memory, rules, and collaboration beyond returns over 30 days.
Seven GitHub tools use API, graph, benchmark, and portable-state patterns to help AI agents retain facts and tasks beyond context windows.
Nokia's applied research team open-sourced AnyJev, a Python library that converts any open LLM into a structured, calibrated decision model without any training. Supporting choice, yes/no, and score q…
RoboSchool is a free, open-source robotics simulation platform that works seamlessly with OpenAI Gym. It enables researchers, students, and hobbyists to experiment with robot control and reinforcement…
Torvalds now enjoys AI coding for beginners, but Linux kernel AI reviews help fix bugs while stressing maintainers.
Wagtail maintainers cover AI code review, productivity metrics, and generative CMS features while weighing open-source quality and risk.
NVIDIA, NTU, and MIT researchers released SoL-Pi, an MIT-licensed extension for the open-source Pi coding agent that cuts recorded token traffic by 44.7–49% on EdgeBench and lowers API costs by roughl…
Jukebox is a neural network that generates music as raw audio across many genres and artist styles, even producing basic singing. Unlike MIDI-based systems, it creates rich, recording-like sound. Its …
RL-Teacher is an open-source tool that trains AI agents through occasional human feedback instead of hand-crafted reward functions. It addresses the difficulty of specifying rewards for complex real-w…
Whisper is OpenAI's newly released open-source neural network for automatic speech recognition (ASR). It stands out by combining accuracy with robustness, achieving near human-level performance on Eng…
Symphony is an open-source specification for Codex orchestration that transforms existing issue trackers into control panels for AI coding agents. By assigning work through labeled issues, teams enabl…
A viral project showed a language model producing watercolor paintings by writing JavaScript with p5.brush rather than generating images directly. This article recreates Surya Narreddi's recipe fully …
Funes is an open-source Hugging Face tool that transforms coding agent session logs into a searchable, portable memory layer. With a single command, it indexes agent turns locally, provides recall and…
Benchmark averages hide a serious reliability problem in LLM agents: a GPT-4.1 ReAct agent scoring 77.4% average success (Mean@5) passed all five repeated runs on only 53% of tasks — a 24.4-point cons…
Linkup Research released SPARSEUP, an open-source learned sparse embedding model under Apache 2.0, built on a 149M-parameter ModernBERT backbone. It averages 56.4 nDCG@10 on BEIR-13, reportedly the be…
OpenClaw, a self-hosted open-source AI agent, released version 2026.9.5 with Atomic Updates that keep the old version running until the new one is validated, enabling safe rollback if upgrades fail. T…
Flet 1.0 is officially released and production-ready, letting Python developers build apps for iOS, Android, Windows, macOS, Linux and web using pure Python—no Swift, Kotlin, Dart or JavaScript needed…
AWS Strands Agents team introduced Strands Harness, an open-source, general-purpose agent harness that bridges the gap between prototype and production. Licensed under Apache 2.0 with Python and TypeS…