AI Open Source
Open source AI ecosystem and community
Articles
How GitHub's Legal Team Streamlined Workflows with Copilot CLI⭐9
Discover how GitHub's legal team used Copilot CLI to automate document reviews, boost efficiency, and streamline compliance workflows in 2026.
Turning a Giant AI-Generated Pull Request into a Reviewable Stack⭐9
Learn to break down massive AI-generated pull requests into reviewable stacks. Discover strategies to split, order, and manage code changes for efficient team r...
Deploy Local Agents Everywhere with LFM2.5-2.6B⭐9
Deploy LFM2.5-2.6B locally for private, low-latency AI agents on edge devices. Cost-efficient, offline-ready, and ideal for privacy-first applications.
Stacked Sessions and Pull Requests in the GitHub Copilot App⭐8
GitHub Copilot app now offers stacked sessions for managing interdependent code changes and direct pull request creation, reducing context switching and merge c...
GPU Management: Why Idle GPUs Are the New Grounded Aircraft⭐8
In 2026, the era of idle GPUs is drawing to a close, with idle hardware now seen as the new grounded aircraft—expensive, underutilized, and increasingly...
Tame Dependabot: Group Updates, Reduce Noise, and Prioritize⭐9
Learn to tame Dependabot by grouping updates, reducing PR noise, and prioritizing security in 2026 for efficient dependency management.
The OlmoEarth Platform: Geospatial Inference at Planetary Scale⭐9
OlmoEarth by Ai2 enables planetary-scale geospatial AI, analyzing satellite imagery globally for land cover, change detection, and object detection with low lat...
Disrupting Supply Chain Attacks on npm and GitHub Actions⭐8
Explore strategies to disrupt supply chain attacks on npm and GitHub Actions, including hardened CI/CD, dependency monitoring, and package integrity checks.
LFM2.5-Encoders for Fast Long-Context Inference on CPU⭐8
LFM2.5-Encoders enable fast long-context inference on CPU with 0.2B parameters. Optimized for edge devices, privacy, and offline use. Hugging Face model with 69...
The Harness Is All You Need (Mostly)⭐9
Discover why the training harness—orchestration, data pipelines, and deployment—often matters more than model architecture for ML success in 2026.