Open Source
Linux, GitHub, open licenses, contributions and open source communities.
27 published articles
Code release
xAI just gave away the code that runs Grok Build
xAI open-sourced Grok Build, its terminal-native coding agent. The code includes the agent loop, tool system, TUI, and extension framework. Developers can compile it themselves and run it fully local with their own inference backend.
2026-07-19
Agent orchestration
L'agent IA qui s'installe en 5 lignes de code et tourne 24h/24
Le framework PraisonAI permet de déployer des agents IA autonomes en 5 lignes de code, avec support de 24 LLM, protocole MCP, mémoire intégrée et détection de boucles infinies. L'instanciation prend 14 microsecondes.
2026-07-18
Open Source AI
480 ms and open source: a streaming model that finally matches Whisper's quality
Voxtral Realtime matches offline transcription quality at sub-second latency and is open source. The 13-language model uses a novel causal audio encoder and is trained end-to-end for streaming rather than adapted from offline systems.
2026-07-17
Model Quantization
Inkling was a 1.9 TB model. Unsloth just squeezed it into a desktop.
Unsloth's dynamic GGUF quantization shrinks Inkling, a 975B-parameter open model, from 1.9 TB to 270 GB at 1-bit with 74.2% accuracy retention. The method selectively preserves high-precision layers, enabling local inference on machines with 290 GB of combined RAM and VRAM.
2026-07-16
Coding AI
Opencode just did the one thing developers actually asked for
Opencode added tabbed navigation, and developers can finally switch between multiple agent sessions and code reviews without losing their context. The feature addresses a long-standing pain point for those juggling simultaneous code generation tasks.
2026-07-16
special report / edge ai
Nvidia just cracked open DeepStream. Your edge AI project will never be the same.
The full source code of Nvidia's DeepStream video analytics SDK is now on GitHub under Apache 2.0 and CC-BY-4.0, opening edge AI development to a wider audience. Version 9.1 brings LLM-based coding agents, Triton Inference Server integration, and consolidated repositories for end-to-end pipelines.
2026-07-16
Open Source
Ai2 opened every drawer in the AI cabinet. Here's what came out.
Ai2 released Olmo 3, a fully open model family from 7B to 32B, and dumped the complete training data, code, and tools on the table. Every checkpoint, every hyperparameter, the kind of transparency the field has been demanding and mostly not getting.
2026-07-11
AI Open Source
The compliance shortcut that beats every proprietary AI vendor
Domyn and AISquared built regulated-industry AI on Ai2's open-source Olmo family and Dolma/Dolci datasets. Full transparency into architecture and training data helped them meet compliance requirements and cut infrastructure costs by roughly 50%.
2026-07-11
Open Source Robotics
LeRobot v0.6.0 trains robots to see the future, then charges nothing for the vision
LeRobot v0.6.0 introduces world model policies that imagine the future during training and vanish at inference, a new rewards API, six simulation benchmarks, and faster data loading. The framework aims to democratize robot learning with leaner code and cloud training options.
2026-07-11
Open-Source Release Engineering
How Hugging Face Ships Its Python Client Every Week Using Open Tools and a Human-in-the-Loop
Hugging Face revamped its huggingface_hub release process, moving from a manual half-day effort every 4–6 weeks to a weekly automated pipeline. The entire stack is open-source, costs roughly $0.25 per release, and keeps a human in the loop for judgment tasks while deterministic scripts verify model output.
2026-07-05
Open source
Microsoft just opened a codebase that kills the worst part of enterprise data work
Data Formulator 0.7 is an open-source AI system from Microsoft Research that helps enterprise teams connect fragmented data sources, prepare and analyze data with context-aware agents, and iteratively refine visualizations in a shared workspace, all without requiring SQL or programming skills.
2026-07-03
AI Infrastructure
Sipp.sh Launches Open-Source Library for Local AI Inference with 3x to 5x Speedup
Noumena Labs launches Sipp, an open-source AI inference library that delivers 3-5x faster token decode speeds via a new Rust and C++ stack. Designed for web, games, and desktop apps, Sipp offers low-cost, zero-latency compute with full data privacy.
2026-07-02