Loading…
Topic
Open Source
562 posts about Open Source. Every summary links to the original.
- 562 posts
- 36 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Newest first
Posts
VibeGame: Exploring Vibe Coding Games
Vibe coding games often fails as projects grow because large context sizes degrade model performance. After evaluating Roblox MCP, Unity MCP, and open web libraries with Claude Code, the author found web tooling offered the strongest model proficiency but lacked high-level game abstractions. To bridge this gap, the author created VibeGame, an open-source declarative game engine built on three.js, rapier, and bitecs. VibeGame uses an Entity-Component-System architecture, XML-like markup, and bundled documentation in an llms.txt file to keep project context lean. While effective for basic physics and rendering mechanics, the engine requires further development for complex features like inventories, multiplayer, and interactions.
Swift Transformers Reaches 1.0 – and Looks to the Future
swift-transformers has released version 1.0 to provide a stable foundation for running local models on Apple Silicon platforms. The library supplies components missing from Core ML and MLX, focusing heavily on tokenization, chat templates, and Hugging Face Hub integration. In this major release, Tokenizers and Hub become standalone top-level modules, enabling developers to import only the components they require. The update also integrates an updated swift-jinja library for faster template processing, adopts Modern Core ML stateful models and MLTensor APIs, removes unnecessary CLI dependencies, and adds full Swift 6 support. Future development will prioritize deeper integration with MLX frameworks and agentic workflows like MCP.
Smol2Operator: Post-Training GUI Agents for Computer Use
Lightweight vision-language models often lack the precise visual grounding and action execution capabilities required for graphical user interface automation. To resolve this deficiency, the authors constructed a post-training pipeline that evolves base models into agentic GUI coders through supervised fine-tuning. The process standardizes disparate mobile and desktop dataset action spaces into a unified functional format utilizing normalized coordinates relative to image size. Training is structured into two sequential phases that first establish basic visual perception and subsequently introduce explicit reasoning steps with masked assistant loss. On the ScreenSpot-v2 perception benchmark, fine-tuning SmolVLM2-2.2B-Instruct increased element localization accuracy to 61.71 percent, while a compact 460-million-parameter model achieved approximately 58 percent accuracy.
Simplify AI-Driven Data Connectivity With MongoDB and MCP Toolbox
Organizations building generative AI applications require simplified, standardized connections to an expanding ecosystem of enterprise databases. MCP Toolbox for Databases, an open-source Model Context Protocol server based on Anthropic's standardized protocol, now supports MongoDB Atlas to streamline connections to generative AI systems. This new integration allows gen AI agents to execute standard CRUD operations alongside advanced transformations and computations using the MongoDB aggregation framework. Through flexible configuration files, developers can configure MongoDB Atlas as both a data source and a sink by defining parameters like connection URIs, target datasets, filters, projections, and toolsets. By linking flexible document data with cross-database query capabilities, enterprises can unify results and automate multi-source AI workflows.
SyGra: The One-Stop Framework for Building Data for LLMs and SLMs
Training and aligning large language models and small language models requires datasets tailored for complex reasoning, preference tuning, multi-turn questioning, and format conversion. To eliminate the need for bespoke data preparation scripts, SyGra provides a low-code and no-code Python framework for automated dataset creation, transformation, and alignment. The library integrates with diverse inference backends, including vLLM, Hugging Face TGI, Triton, and Ollama, allowing teams to focus on prompt engineering rather than pipeline infrastructure. It supports data workflows ranging from converting PDFs and knowledge bases into question-answering pairs to filtering low-quality samples and generating Direct Preference Optimization datasets. These plug-and-play workflows reduce manual curation effort while accelerating model fine-tuning and retrieval-augmented generation pipelines.
Gaia2 and ARE: Empowering the community to study agents
Existing AI agent evaluation environments are often tightly coupled to specific tasks and fail to model real-world challenges such as API failures, spontaneous events, and asynchronous conditions. To address this limitation, the Gaia2 benchmark and the Meta Agents Research Environments (ARE) framework introduce interactive read-and-write evaluation. Gaia2 incorporates 1,000 human-created scenarios spanning multi-step execution, cross-source search, ambiguity handling, adaptability, temporal reasoning, agent collaboration, and noise tolerance. Using a simulated smartphone interface equipped with 101 tools, evaluations showed that GPT-5 with high reasoning scored highest overall, while Kimi K2 was the leading open-source model. The results demonstrated that instruction following and search do not reliably predict performance on closer-to-real-world tasks.
Democratizing AI Safety with RiskRubric.ai
Cloud Security Alliance and Noma Security introduced RiskRubric.ai to provide standardized, transparent risk assessments across the open AI model ecosystem. The framework evaluates AI models across six pillars—transparency, reliability, security, privacy, safety, and reputation—using over 1,000 reliability tests, 200 adversarial security probes, automated code scanning, and harmful content evaluations. Each model receives 0–100 scores and A–F letter grades, supplemented by specific vulnerability findings and recommended mitigation strategies to assist deployment filtering. Initial benchmark results across models showed composite scores ranging from 47 to 94 with a median of 81, revealing polarized safety distributions and indicating that security hardening directly correlates with reduced safety risks.
Public AI on Hugging Face Inference Providers 🔥
Hugging Face has integrated Public AI as a supported Inference Provider on the Hugging Face Hub. Public AI operates as a nonprofit, open-source project providing access to sovereign and public models from institutions such as the Swiss AI Initiative and AI Singapore. Its distributed infrastructure combines a vLLM-powered backend serving OpenAI-compatible APIs across partner-donated clusters with a global load-balancing routing layer. Users can access these models through the Hugging Face web UI, Python client SDK, and JavaScript SDK using either direct provider API keys or routed Hugging Face tokens. At the time of announcement, inference through the Public AI provider is free of charge, supported by donated GPU time and advertising subsidies.
How we built it: Real-time analytics for Stripe Billing
Stripe built a real-time streaming analytics system for Billing after customers said they needed to detect emerging behavior and adapt pricing quickly, replacing a batch pipeline whose subscription updates lagged by 24 hours on average. The architecture uses Apache Flink to maintain compressed subscription history and incrementally process analytics events, while a custom Apache Spark job generates initial Flink state from billions of historical events and supports validation and exports. A new Apache Pinot v2 query engine performs windowed aggregations and joins without offline preaggregation; most updates are processed in under one minute, nearly all reach users within 15 minutes, and production query latency is under 300 milliseconds. Metric-definition changes trigger historical recalculation while new events are buffered and later replayed, preserving a consistent Dashboard view during the transition.
Visible Watermarking with Gradio
Generative artificial intelligence tools produce images, video, audio, and text that have become increasingly difficult to distinguish from real-world media captures. To improve synthetic media transparency, Hugging Face introduced visible watermarking capabilities directly into the Gradio web application framework. Developers can now overlay visual watermarks on image and video outputs by specifying a single watermark parameter using file paths, open image objects, or NumPy arrays. The implementation also supports QR code watermarks, which can match the visual style of generated media while conveying detailed background information. Furthermore, the Gradio Chatbot component accepts a text watermark parameter that automatically attaches attribution metadata whenever users copy generated responses to their clipboards.
Introducing the Palmyra-mini family: Powerful, lightweight, and ready to reason!
WRITER released three open models in the Palmyra-mini family ranging between 1.5B and 1.7B parameters, designed for efficient inference and specialized reasoning tasks. Built on the Qwen architecture, the release includes the standard palmyra-mini base model alongside two Chain of Thought variants, palmyra-mini-thinking-a and palmyra-mini-thinking-b. In benchmark evaluations, palmyra-mini achieved 52.6% on Big Bench Hard, while palmyra-mini-thinking-a reached 82.87% on GSM8K and palmyra-mini-thinking-b reached 92.5% on AMC23. For palmyra-mini-thinking-b, applying reinforcement learning fine-tuning to an OpenReasoning-Nemotron-1.5B base improved single-shot pass@1 accuracy while reducing sampling diversity and majority@64 performance. The models are available in GGUF and MLX-BF16 quantizations and support inference engines including vLLM, SGLang, TRTLLM, and TGI.
Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers
To support OpenAI's GPT-OSS series of models, the transformers library introduced several performance upgrades that apply across supported architectures. The release integrates zero-build custom kernels downloadable directly from the Hub, reducing external dependency bloat and compilation friction for operations like Liger RMSNorm and MegaBlocks MoE. Native support for MXFP4 quantization groups vector elements into 32-value blocks with shared scales, allowing GPT-OSS 20B to fit in roughly 16 GB of VRAM and GPT-OSS 120B in roughly 80 GB. In addition, transformers incorporates Flash Attention 3 with attention sinks, continuous batching via the generate_batch API for experimentation, and automatic memory pre-allocation to speed up model loading on GPUs.
Fine-tune Any LLM from the Hugging Face Hub with Together AI
Together AI and Hugging Face have introduced an integration enabling developers to fine-tune compatible Hugging Face Hub models directly on Together AI's managed infrastructure. To launch a fine-tuning job via the Python SDK, users provide a base model from Together's catalog as a configuration template alongside the target Hugging Face repository identifier. This base model template dictates GPU allocation, memory configuration, training pipelines, and inference setup for custom models with matching architectures and sizes. The workflow operates bidirectionally, pulling from public or token-authenticated private repositories and optionally pushing completed checkpoints back to the Hub upon completion. Geared toward CausalLM models under 100 billion parameters, the capability enables faster iteration cycles and domain adaptation without custom DevOps infrastructure.
Jupyter Agents: training LLMs to reason with notebooks
Small language models often struggle to compete with large frontier models on complex, agentic data science tasks. To improve notebook-based reasoning, researchers simplified agent scaffolding down to roughly two hundred lines of code with dedicated execution and final answer tools, boosting baseline easy accuracy on the DABStep benchmark from 44.4 percent to 59.7 percent. They constructed a curated training dataset by deduplicating two terabytes of Kaggle notebooks, automatically fetching five terabytes of linked datasets, and scoring educational value and relevance using Qwen3-32B. Question-answer pairs grounded in verified execution traces were generated to fine-tune compact Qwen3-4B thinking and instruct models. The team released the trained models alongside the dataset and execution sandboxes, establishing a foundation for reinforcement learning and distillation on notebook workflows.
mmBERT: ModernBERT goes Multilingual
mmBERT is a massively multilingual encoder model trained on more than 3T tokens across over 1,800 languages to improve upon existing multilingual architectures like XLM-R. Built upon ModernBERT with a Gemma 2 tokenizer, mmBERT employs a three-phase training curriculum consisting of pre-training on 60 languages, mid-training on 110 languages, and a final decay phase covering 1,833 languages. The training pipeline integrates an inverse mask ratio schedule, dynamic language temperature annealing, and TIES merging across three decay variants. Benchmark evaluations demonstrate strong natural language understanding on English GLUE and multilingual XTREME, as well as competitive retrieval performance on MTEB v2 and CoIR. The release includes standard base and small models alongside open training data and checkpoints.
Welcome EmbeddingGemma, Google's new efficient embedding model
Google DeepMind released EmbeddingGemma, a multilingual embedding model with 308 million parameters and a 2048-token context window designed for on-device applications. Based on the Gemma3 transformer backbone, the architecture replaces causal attention with bidirectional attention to function as an encoder, followed by mean pooling and two dense layers producing 768-dimensional vectors. The model incorporates Matryoshka Representation Learning, allowing outputs to be truncated down to 512, 256, or 128 dimensions for reduced memory and storage footprints. Trained on approximately 320 billion multilingual tokens across more than 100 languages, the quantized model operates under 200 MB of RAM. In domain-specific evaluations on the MIRIAD dataset, fine-tuning increased NDCG@10 from 0.8340 to 0.8862, outperforming larger baselines.
SAIR: Accelerating Pharma R&D with AI-Powered Structural Intelligence
SandboxAQ released the Structurally Augmented IC50 Repository (SAIR), an open-source dataset containing 5.24 million computationally co-folded 3D protein-ligand structures paired with empirical IC50 binding potency data. The repository addresses training data scarcity in structure-based drug discovery, where over 40 percent of the included target proteins lack experimental structures in the Protein Data Bank. To construct the dataset, engineers executed over 130,000 GPU hours of the Boltz1 co-folding model on 760 NVIDIA H100 processors hosted via NVIDIA DGX Cloud on Google Cloud Platform. Infrastructure optimizations maintained over 95 percent GPU compute utilization, compressing the generation timeline from three months to three weeks. Quality validation using PoseBusters confirmed that 97 percent of the predicted complexes met physical plausibility and chemical sanity standards.
Heroku AI Expands Model Offering with OpenAI’s gpt-oss-120b
Heroku has made OpenAI’s open-weight gpt-oss-120b available through Heroku Managed Inference and Agents, giving developers an OpenAI-compatible chat completions API for compatible SDKs and frameworks. The model uses a Mixture-of-Experts architecture with 117 billion total parameters, activating 5.1 billion per token and enabling operation on a single 80GB GPU; its Apache 2.0 license permits inspection and fine-tuning. It is designed for agentic workflows involving instruction following, function calling, web searches, and Python execution, while reported benchmarks place it near or above several open-weight models and sometimes OpenAI o4-mini. The add-on provides deployment, secure application access, agent actions, monitoring, and scaling without infrastructure management, with pricing of $0.15 per million input tokens and $0.60 per million output tokens.
Guardrails for money movement: Integrating Stripe MCP with Portia AI
Portia AI presents a customer-refund agent that combines its guardrails with Stripe’s official Model Context Protocol server. The agent reads a refund request, compares it with a policy file, identifies the relevant Stripe customer and payment intent, and evaluates whether the request should be approved. Portia’s planner produces a multi-agent plan, while execution agents run it and persist outputs in plan state; an execution hook pauses before the Stripe create-refund call. A clarification presents the request and the agent’s rationale to a human, who can approve it in the CLI; approval allows the refund to proceed, while rejection exits without creating one. The example also handles Gmail OAuth and can send the customer an email describing the outcome.
MCP UI: Breaking the text wall with interactive components
Model Context Protocol (MCP) can let AI agents search catalogs, interpret reviews, build carts, and support purchases, but a text-only flow does not provide the visual and interactive details central to commerce. Shopify presents MCP UI as an extension that returns embedded UI resources for components such as product cards, with delivery through inline HTML, remote resources in sandboxed iframes, or Remote DOM. Its intent-based message system keeps components from directly modifying state: actions such as view_details, checkout, notify, and ui-size-change are surfaced for the agent to interpret, while render data lets hosts provide CSS for adaptive styling. The open-source, deliberately extensible protocol is demonstrated in a Shopify Storefront MCP UI Server prototype and is intended for commerce as well as data visualization, form builders, and media players.
Related topics
All topics →Weekly digest
The best engineering reads, once a week.