Movement deltas need at least two snapshots. The first cycle establishes the baseline; later runs show 24h and 7d star movement.
GitHub Radar
Open Source Radar
Top open-source AI, developer tooling, inference, and automation projects tracked from the public GitHub API. VQV records snapshots so movement becomes visible over time.
Top 30 Open Source Projects
Ranked by current GitHub stars.New & Notable
Smaller tracked projects with recent activity and early signal.anthropics/anthropic-sdk-python
anthropics/anthropic-sdk-python is a tracked Python repository in the VQV Open Source Radar.
modal-labs/modal-client
SDK libraries for Modal
run-llama/llama_deploy
Deploy your agentic worfklows to production
Moving Toward Top 30
Projects outside the Top 30 ranked by momentum.continuedev/continue
open-source coding agent
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
qdrant/qdrant
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
openai/openai-python
The official Python library for the OpenAI API
sgl-project/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
ComposioHQ/composio
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
chroma-core/chroma
Search infrastructure for AI
microsoft/semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
camel-ai/camel
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
weaviate/weaviate
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database...
NVIDIA/TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains co...
anthropics/anthropic-sdk-python
anthropics/anthropic-sdk-python is a tracked Python repository in the VQV Open Source Radar.
SWE-agent/SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
bentoml/BentoML
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
modal-labs/modal-client
SDK libraries for Modal
lmstudio-ai/lms
LM Studio CLI
TabbyML/tabby
Self-hosted AI coding assistant
huggingface/text-generation-inference
Large Language Model Text Generation Inference
run-llama/llama_deploy
Deploy your agentic worfklows to production
Fastest Movers
Across the full tracked set.Method
How this ranking works
Top 30 is ranked by current GitHub stars. Moving projects are ranked by VQV Momentum Score, a deterministic blend of recent star deltas, recent push activity, and current project scale. New & Notable highlights tracked projects below 5,000 stars so early-stage repos are not buried under mature projects. GitHub data comes from the public API; no GitHub scraping is used.