open source
75 published articles
Open Source
OpenForgeRL trains AI agents without touching their inference harnesses
OpenForgeRL uses a proxy and Kubernetes to train AI agents without modifying their inference harnesses. In tests, OpenForgeGUI matched models several times larger on web navigation and desktop benchmarks.
2026-08-01
Deep Research AI
BAAI's new research agent doesn't just search longer, it checks its own homework
BAAI's AREX agents use a recursive self-improvement loop that compresses long research histories, enabling efficient verification-driven refinement. Trained with a novel long-horizon RL recipe, they outperform comparable baselines on BrowseComp, DeepSearchQA, and HLE.
2026-07-31
Frontis-MA1 / OpenMLE
The AI that improves AI now runs on one RTX 4090
FrontisAI's OpenMLE stack and 35B Frontis-MA1 agent turn recursive self-improvement into a reproducible experiment. On a single RTX 4090, the model scores 71.21% on MLE-Bench Lite, ahead of GPT-5.5 + Codex and close to much larger frontier models.
2026-07-31
Open Source TTS
Audio8's new TTS model clones voices in 11 languages for free
Audio8 releases Audio8-TTS Preview under Apache 2.0, a 0.6B model supporting 11 languages, zero-shot voice cloning, and a bundled 44.1 kHz codec. The release targets edge speech applications that need speed and privacy.
2026-07-30
Open Source Buzz Workspace Integrates Hermes Agent
Buzz and Hermes let ai agents share a channel with your coworkers
Buzz, an open-source workspace built on Nostr, now supports three ways to integrate Hermes, the autonomous agent from Nous Research. From a one-click desktop setup to a full gateway that keeps Hermes' memory and skills intact, the integration offers flexibility for different deployment needs.
2026-07-30
Advanced Parametric Head Modeling for Animation and Medical Use
The missing teeth of parametric face models: GNM head fills them in
GNM Head models the full human head including teeth, eyes, tongue, and neck, built from high-res scans and available open source.
2026-07-30
Video generation
MiniMax H3 undercuts video rivals and plans open weights
MiniMax packs image, video and audio generation into one model, prices output at under a third of mainstream per-second rates, and plans to open the weights within days. How well the outputs hold up outside its own demos is the open question.
2026-07-30
Local-First Software
The office file that refuses to be rented
Bento challenges the rented office suite model by putting a full slide editor into a self-contained, eternally openable HTML file. It's local-first, AI-friendly, and impossible to kill by pulling a server plug.
2026-07-29
Qwen / Alibaba
Alibaba splits its flagship AI model in two because one size fits nobody
Alibaba's Qwen team released Qwen3-2507, splitting its model line into dedicated instruct and thinking variants. The update brings substantial gains in reasoning, instruction following, and 256K context support, extensible to 1M tokens.
2026-07-29
Physical AI
Nvidia's 4B model does what most small robots can't: act, not just talk
Nvidia's Cosmos 3 Edge packs world modeling into 4B parameters, ranking first on VANTAGE-Bench among its size class. Its dual-transformer design blends reasoning with real-time action prediction for robots, all deployable on Jetson and RTX hardware.
2026-07-28
AI Models
Macaron-V1-Venti's 748B four-specialist design beats GPT-5.5 and Opus 4.8
Macaron-V1-Venti from MindLab Research leads benchmarks in personal intelligence, coding, terminal use, and Generative UI, using a novel Mixture of LoRA architecture that keeps the model compact while specialized.
2026-07-27
AI Tools
This open-source canvas fixes the one thing chat AI still gets wrong about your sketches
PenEcho is an open-source shared canvas where handwriting, equations, and diagrams become part of an AI conversation. It supports Claude Code, OpenAI Codex, and API-based models, runs locally, and adds a spatial layer to AI interaction that chat windows cannot replicate.
2026-07-27