GitHub 2026-02-14 Daily Trending Projects

Synkra AIOS is a CLI-first, agent-driven core framework that encodes planning and contextualized development into executable developer stories — converting PRDs into actionable artifacts to improve consistency and automation for teams adopting AI-assisted full‑stack workflows.

Chrome DevTools MCP exposes Chrome DevTools to AI coding agents via an MCP server, enabling automated browser control, deep debugging and performance analysis; however, the repository lacks contributors, commits, and releases, so evaluate maintenance and compliance risks before production use.

PAI is a personal AI infrastructure template emphasizing modular skills, history capture, and observability with a backend-agnostic design—enabling technically proficient users to build their own personal AI systems.

AI Engineering Hub provides 93+ difficulty-tiered LLM, RAG, and agent practical projects and tutorials for learning and rapid prototyping; verify license and maintenance status before using in production.

MTProxy is Telegram's MTProto proxy implementation for self-hosting on Linux to improve connection availability and privacy; however, repository activity is sparse and the official Docker image is outdated, so evaluate maintenance and security responsibilities before deployment.

Superhuman gathers DeepMind's benchmarks, datasets, and agent examples for advanced math reasoning—enabling evaluation on short-answer, proof, and grading tasks—but parts depend on closed models and the repo shows limited activity, so users should watch reproducibility and maintenance risk.

free-llm-api-resources compiles free or trial LLM API providers with model and quota details to enable fast evaluation and prototyping for cost-conscious developers and researchers; verify license and data-use terms before production use.

This repo provides interactive Jupyter/Colab notebooks accompanying the book 'Hands‑On Large Language Models', covering tokens/embeddings, transformer internals, prompt engineering, RAG, and multimodal examples—ideal for teaching and hands‑on learning but requiring manual dependency and environment management.

slime is a high-throughput framework for large-scale RL post-training that combines Megatron and SGLang to decouple training and rollout; it targets research and engineering scenarios requiring verifiable environments and custom data pipelines, but license transparency and maintenance visibility are limited and deployment costs are high.

DebugSwift delivers a visual toolkit for network, performance, UI and resource debugging to speed issue diagnosis in development/testing; however, the repository shows low activity and an unspecified license, so perform code and compliance review before adoption.