Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Devon
Tools & appsDevon: An open-source pair programmer
git clone https://github.com/entropy-research/Devon.git -
Ternary-Bonsai-2-4B-gguf
Modelsimage text to text model by prism-ml · llama.cpp
prism-ml/Ternary-Bonsai-2-4B-gguf -
MiniCPM5-2B-GGUF
Modelstext generation model by openbmb · transformers
openbmb/MiniCPM5-2B-GGUF -
how-to-train-your-gpt
Docs & tutorialsBuild a modern LLM from scratch. Every line commented. Explained like we are five.
git clone https://github.com/raiyanyahya/how-to-train-your-gpt.git -
Qwen-Sharp-Chat-Templates
Modelsmodel by peculiar-ragdoll · mlx
peculiar-ragdoll/Qwen-Sharp-Chat-Templates -
hax
AI repositoriesA minimalist, terminal-native coding agent written in C.
git clone https://github.com/OleksandrChekhovskyi/hax.git -
MiniCPM-V-4.7-1B-gguf
Modelsimage text to text model by openbmb · llama.cpp
openbmb/MiniCPM-V-4.7-1B-gguf -
LFM2.5-8B-A1B-GGUF
Modelstext generation model by LiquidAI
LiquidAI/LFM2.5-8B-A1B-GGUF -
base-llm
Docs & tutorials从 NLP 到 LLM 的算法全栈教程,在线阅读地址:https://datawhalechina.github.io/base-llm/
git clone https://github.com/datawhalechina/base-llm.git -
hass_local_openai_llm
Agents & frameworksHome Assistant LLM integration for local OpenAI-compatible services (llamacpp, vllm, etc)
git clone https://github.com/skye-harris/hass_local_openai_llm.git -
helicone
Prompts🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
git clone https://github.com/Helicone/helicone.git -
langfuse
Prompts🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
git clone https://github.com/langfuse/langfuse.git -
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 -
text generation model by ukisai · gguf
ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF -
Swift-Qwen3.8-27B-GGUF
Modelsimage text to text model by ukisai · gguf
ukisai/Swift-Qwen3.8-27B-GGUF -
text generation model by GnLOLot · gguf
GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF -
Clover-35B-A3B-Preview-GGUF
Modelstext generation model by Diffuspace · llama.cpp
Diffuspace/Clover-35B-A3B-Preview-GGUF -
Observer
Agents & frameworksThe orchestrator that deploys micro-agents that monitor anything for you. Running completely locally. Open Source.
git clone https://github.com/Roy3838/Observer.git -
image text to text model by orcarouter · gguf
orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF -
restai
AI repositoriesRESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generation with dynamic loading generators. Live chat deployment. Built-in block based graphical language. Prompt versioning and much more...
git clone https://github.com/apocas/restai.git -
awesome-instruction-datasets
PromptsA collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。
git clone https://github.com/jianzhnie/awesome-instruction-datasets.git -
OmAgent
AI repositories[EMNLP-2024] Build multimodal language agents for fast prototype and production
git clone https://github.com/om-ai-lab/OmAgent.git -
LEANN
AI repositories[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
git clone https://github.com/StarTrail-org/LEANN.git -
geobench
Datasets & benchmarksGeoGuessr benchmark for language models
git clone https://github.com/ccmdi/geobench.git
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.