HomePricingHow it worksSkills
Log in
GitHub repository

orchestra-research/ai-research-skills

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

View repository
Skills
98
Installs
81.4K
Stars
13.2K
License
—

Skills in this repository

01
ml-paper-writing
2,188
02
academic-plotting
995
03
mlflow
935
04
serving-llms-vllm
929
05
faiss
924
06
tensorrt-llm
921
07
stable-diffusion-image-generation
903
08
ray-train
875
09
peft-fine-tuning
865
10
weights-and-biases
863
11
gguf-quantization
862
12
autoresearch
860
13
huggingface-accelerate
858
14
unsloth
858
15
crewai-multi-agent
856
16
prompt-guard
855
17
audiocraft-audio-generation
853
18
evaluating-llms-harness
853
19
qdrant-vector-search
853
20
segment-anything-model
853
21
ray-data
852
22
knowledge-distillation
851
23
quantizing-models-bitsandbytes
847
24
fine-tuning-with-trl
846
25
llama-cpp
846
26
tensorboard
846
27
pytorch-lightning
845
28
deepspeed
844
29
grpo-rl-training
844
30
langchain
844
31
verl-rl-training
844
32
dspy
843
33
optimizing-attention-flash
843
34
axolotl
842
35
huggingface-tokenizers
842
36
hqq-quantization
841
37
sentence-transformers
841
38
modal-serverless-gpu
840
39
awq-quantization
839
40
distributed-llm-pretraining-torchtitan
839
41
long-context
839
42
nanogpt
839
43
sglang
839
44
openrlhf-training
838
45
sentencepiece
838
46
whisper
838
47
chroma
837
48
clip
837
49
instructor
837
50
pytorch-fsdp2
837
51
moe-training
836
52
speculative-decoding
836
53
training-llms-megatron
836
54
outlines
835
55
pyvene-interventions
835
56
simpo-training
835
57
slime-rl-training
835
58
llama-factory
834
59
llamaindex
834
60
nemo-curator
834
61
evaluating-code-models
833
62
gptq
833
63
sparse-autoencoder-training
833
64
transformer-lens-interpretability
833
65
implementing-llms-litgpt
832
66
llamaguard
832
67
model-merging
832
68
guidance
831
69
langsmith-observability
831
70
nemo-guardrails
831
71
skypilot-multi-cloud-orchestration
831
72
torchforge-rl-training
830
73
autogpt-agents
829
74
mamba-architecture
829
75
miles-rl-training
829
76
nnsight-remote-interpretability
829
77
pinecone
829
78
constitutional-ai
828
79
model-pruning
828
80
rwkv-architecture
828
81
nemo-evaluator-sdk
827
82
blip-2-vision-language
826
83
lambda-labs-gpu-cloud
826
84
phoenix-observability
826
85
llava
825
86
systems-paper-writing
781
87
experiment-tracking-swanlab
774
88
presenting-conference-talks
772
89
ml-training-recipes
762
90
fine-tuning-openvla-oft
746
91
fine-tuning-serving-openpi
744
92
evaluating-cosmos-policy
742
93
evolving-ai-agents
715
94
ara-rigor-reviewer
676
95
ara-compiler
663
96
ara-research-manager
662
97
writing-systems-papers
5
98
pytorch-fsdp
2