Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
dialogstudio
Datasets & benchmarksHugging Face dataset by Salesforce
Salesforce/dialogstudio -
Synthetic-Persona-Chat
Datasets & benchmarksHugging Face dataset by google
google/Synthetic-Persona-Chat -
UltraInteract_sft
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/UltraInteract_sft -
OpenMathInstruct-1
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/OpenMathInstruct-1 -
AutoMathText
Datasets & benchmarksHugging Face dataset by math-ai
math-ai/AutoMathText -
webnovel_cn
Datasets & benchmarksHugging Face dataset by zxbsmk
zxbsmk/webnovel_cn -
toxic-chat
Datasets & benchmarksHugging Face dataset by lmsys
lmsys/toxic-chat -
ceval-exam
Datasets & benchmarksHugging Face dataset by ceval
ceval/ceval-exam -
Mistral: Codestral 2508
ModelsMistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)
mistralai/codestral-2508 -
flint-chart
MCP servers🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs.
git clone https://github.com/microsoft/flint-chart.git -
synthetic_text_to_sql
Datasets & benchmarksHugging Face dataset by gretelai
gretelai/synthetic_text_to_sql -
alpaca-gpt4
Datasets & benchmarksHugging Face dataset by vicgalle
vicgalle/alpaca-gpt4 -
Code-Feedback
Datasets & benchmarksHugging Face dataset by m-a-p
m-a-p/Code-Feedback -
ChaosIntelligence
Tools & apps把智能体当函数,把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.
git clone https://github.com/Cattmonkey/ChaosIntelligence.git -
OpenMathInstruct-2
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/OpenMathInstruct-2 -
multiturn_chat_0.8M
Datasets & benchmarksHugging Face dataset by BelleGroup
BelleGroup/multiturn_chat_0.8M -
strix-halo-guide
Datasets & benchmarksEvidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.
git clone https://github.com/hogeheer499-commits/strix-halo-guide.git -
CoT-Collection
Datasets & benchmarksHugging Face dataset by kaist-ai
kaist-ai/CoT-Collection -
airllm
AI repositoriesAirLLM 2.8T LLM inference with single 4GB GPU
git clone https://github.com/lyogavin/airllm.git -
gpqa
Datasets & benchmarksHugging Face dataset by Idavidrein
Idavidrein/gpqa -
smol-smoltalk
Datasets & benchmarksHugging Face dataset by HuggingFaceTB
HuggingFaceTB/smol-smoltalk -
LLaVA-Video-178K
Datasets & benchmarksHugging Face dataset by lmms-lab
lmms-lab/LLaVA-Video-178K -
ai-draw
AI repositoriesCreate and edit drawings through conversation.
git clone https://github.com/bugkeep/ai-draw.git -
pdfa-eng-wds
Datasets & benchmarksHugging Face dataset by pixparse
pixparse/pdfa-eng-wds
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.