Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
llm-algo-leetcode
Docs & tutorialsHands-on LLM algorithms and systems with PyTorch, Triton & CUDA.《大模型算法与系统教程》:模型架构与训练、后训练、推理加速、性能与算子优化,配套 Notebook 练习、答案解析、测试与实验。
git clone https://github.com/datawhalechina/llm-algo-leetcode.git -
avaloka
Agents & frameworksOpen source release of Data Science Agents that can analyze and transform datasets as well as train and infer models to augment your data scientists.
git clone https://github.com/guruvaidev/avaloka.git -
ds4-on-spark
Datasets & benchmarksEntrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support
git clone https://github.com/Entrpi/ds4-on-spark.git -
Sentiment-Analysis-7B
Modelstext generation model by microsoft · transformers
microsoft/Sentiment-Analysis-7B -
text generation model by xtools-at · transformers
xtools-at/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic -
awesome-ai-web-search
AI repositoriesList of software that allows searching the web with the assistance of AI: https://hf.co/spaces/felladrin/awesome-ai-web-search
git clone https://github.com/felladrin/awesome-ai-web-search.git -
csghub
AI repositoriesCSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️
git clone https://github.com/OpenCSGs/csghub.git -
claude-code-my-workflow
SkillsA ready-to-fork Claude Code template for academic research — papers, data analysis (R, Stata, Python), slides and teaching — with multi-agent review, enforced quality gates and replication protocols. Codex and Antigravity can use it too.
git clone https://github.com/pedrohcgs/claude-code-my-workflow.git -
MiniSearch
AI repositoriesMinimalist web-searching platform with an AI assistant that runs directly from your browser. Demo: https://felladrin-minisearch.hf.space
git clone https://github.com/felladrin/MiniSearch.git -
LoCo-7B
Modelstext generation model by MuyaoYuan · transformers
MuyaoYuan/LoCo-7B -
awesome-hacking-lists
MCP serversA curated collection of top-tier penetration testing tools and productivity utilities across multiple domains. Join us to explore, contribute, and enhance your hacking toolkit!
git clone https://github.com/taielab/awesome-hacking-lists.git -
ome
AI repositoriesOpen Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton
git clone https://github.com/ome-projects/ome.git -
colgrep-agent-2B
Modelstext generation model by lightonai · transformers
lightonai/colgrep-agent-2B -
Oc-e-Non-v1
Modelstext generation model by p-e-w · transformers
p-e-w/Oc-e-Non-v1 -
awesome-ai-for-economists
AI repositoriesA curated list of AI tools, agent skills, libraries, and resources for economics research, teaching, and policy analysis. Maintained by the OpenEcon team.
git clone https://github.com/hanlulong/awesome-ai-for-economists.git -
InferCPI
MCP serversAI inference price index: token prices, cost per capability, open vs closed, hosts, cost per task.
-
Klee
AI repositoriesA native macOS AI chat app powered by MLX. 100% local inference on Apple Silicon, no cloud required. Built with ShipSwift.
git clone https://github.com/signerlabs/Klee.git -
StatsPAI
MCP serversEconometrics and causal inference (DiD, IV, RD, synthetic control, DML) with Stata/R parity grades
statspai@1.43.1 -
mlx-vlm
AI repositoriesMLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
git clone https://github.com/Neywa-Labs/mlx-vlm.git -
Execute co2-inference-calculator-mcp
MCP serversPremium agentic endpoint for co2-inference-calculator-mcp.
-
Infermedica MCP by usefulapi
MCP serversRun Infermedica symptom checks, diagnosis, triage and condition lookups.
-
Edge0-120B-q3k
Modelstext generation model by Edge0 · edge0
Edge0/Edge0-120B-q3k -
BigMoeOnEdge
AI repositoriesRun MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
git clone https://github.com/Helldez/BigMoeOnEdge.git -
inferbench
MCP serversBenchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
inferbench-cli@0.1.7
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.