langsmith-observability
orchestra-research
Debug your AI app with traces and test results.
LLM observability
orchestra-research
GitHub publisher98 Skills89.3k installs
Organization · Orchestra Research · On GitHub since 2026
- 888
- 888
miles-rl-training
orchestra-research
Train large AI models with less memory in miles.
Reinforcement learning
- 888
model-pruning
orchestra-research
Compress language models without retraining.
Model compression
LL - 888
nemo-guardrails
orchestra-research
Add runtime safety checks to your LLM app.
LLM safety
- 887
nnsight-remote-interpretability
orchestra-research
Probe large neural networks without local GPUs.
Mechanistic interpretability
- 887
rwkv-architecture
orchestra-research
Build streaming text applications with RWKV.
Language modeling
- 886
skypilot-multi-cloud-orchestration
orchestra-research
Run your ML jobs where cloud GPUs cost less.
ML infrastructure
+3 - 885
autogpt-agents
orchestra-research
Build AutoGPT agents that keep workflows running.
Workflow automation
+4 - 884
blip-2-vision-language
orchestra-research
Build apps that describe images with BLIP-2.
Computer vision
- 884
constitutional-ai
orchestra-research
Train safer models with AI-generated feedback.
AI safety
- 884
lambda-labs-gpu-cloud
orchestra-research
Train your AI models on dedicated cloud GPUs.
ML infrastructure
- 884
pinecone
orchestra-research
Build AI search with managed vector storage.
AI search
- 883
nemo-evaluator-sdk
orchestra-research
Compare language models on repeatable benchmarks.
Model evaluation
+2 - 882
phoenix-observability
orchestra-research
Find what went wrong in your LLM app with Phoenix.
LLM observability
- 881
llava
orchestra-research
Build LLaVA apps that answer questions about images.
Vision-language development
- 842
presenting-conference-talks
orchestra-research
Turn your research paper into talk-ready slides.
Research communication
- 842
systems-paper-writing
orchestra-research
Give your systems research paper a clear structure.
Academic writing
- 836
experiment-tracking-swanlab
orchestra-research
Track your ML experiments with SwanLab.
Experiment tracking
- 835
ml-training-recipes
orchestra-research
Train and debug your PyTorch neural networks.
Machine learning
- 804
fine-tuning-openvla-oft
orchestra-research
Train robot policies for simulation or real arms.
Robot learning
OO+1 - 803
fine-tuning-serving-openpi
orchestra-research
Fine-tune robot policies and serve their actions.
Robot policy training
OP - 799
evaluating-cosmos-policy
orchestra-research
Benchmark Cosmos Policy on simulated robot tasks.
Robotics evaluation
- 777
evolving-ai-agents
orchestra-research
Improve your AI agent through benchmark trials.
Agent optimization
+1 - 746
ara-rigor-reviewer
orchestra-research
A scored rigor review of your research artifact.
Research review