Connect your users to their apps
Repository Index
95,842 visible repositories in the index
97–120 of 1,034 · Most stars
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Sub-50mb agentic, voice and vision intelligence for consumer devices.
- cactus
- llm
- on-device-ai
- edge-ai
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D avatar running locally across platforms
- ai-vtuber
- ai-waifu
- ai
- neuro-sama
A very simple framework for state-of-the-art Natural Language Processing (NLP)
structured outputs for llms
- openai
- python
- pydantic-v2
- openai-functions
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
- gpt-2
- adaptation
- language-model
- gpt-3
[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.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
- python
- search
- nlp
- semantic-search
LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.
- huggingface
- java
- langchain
- openai
The all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end.
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
- nlp
- embedding
- bert
- ernie
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
- bert
- sentence-encoding
- deep-learning
- clip-model
TranslatedCRS - a self-hosted Claude Code mirror, a one-stop open-source relay service that lets Claude, OpenAI, Gemini, and Droid subscriptions be accessed in a unified way. It supports carpool-style shared use to split costs more efficiently, and native tools work seamlessly.
- claude-api
- claude-code
- claude-proxy
- codex-cli
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
- llm
- llmops
- model-inference
- fine-tuning
BISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration.
Retrieval and Retrieval-augmented LLMs
- embeddings
- information-retrieval
- llm
- sentence-embeddings
AI Observability & Evaluation
- llmops
- ai-monitoring
- ai-observability
- llm-eval
A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
- avx2
- c99
- cpu-inference
- deep-learning