20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Repository Index
56,139 visible repositories in the index
73–96 of 325 · Most stars
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
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with AI.
The simplest way to run LLaMA on your local machine
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
- bert
- sentence-encoding
- deep-learning
- clip-model
KoboldCpp - Run GGUF AI models locally with a KoboldAI UI. One File. Zero Install.
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.
Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
Ekko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.
- ai-agent
- chat-ui
- dashboard
- hermes-agent
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
- python
- fine-tuning
- gguf
- huggingface
Sketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts.
- design-tool
- material-3-expressive
- material-design
- material3
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Locally run an Instruction-Tuned Chat-Style LLM
the LLM vulnerability scanner
- ai
- llm-evaluation
- llm-security
- security-scanners
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
- decision-model
- jev
- qwen3
High-speed Large Language Model Serving for Local Deployment
An Application Framework for AI Engineering
- artificial-intelligence
- java
- spring-ai
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
- academia
- arxiv
- brave
- deep-research
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.
- gateway
- llm-gateway
- guardrails
- mcp-gateway