maxxing the ability to run different LLMs on the smallest devices possible
Repository Index
132,218 visible repositories in the index
1,105–1,128 of 2,136 · Most stars
A framework for the evaluation of autoregressive code generation language models.
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
- foundation-models
- multimodal
- representation-learning
- vision-language
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
- benchmark
- large-language-models
- prompt-injection
- security
OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.
A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR
Run 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.
- android
- cpp
- edge-ai
- gguf
A family of lightweight multimodal models.
On-premises conversational RAG with configurable containers
- claude
- custom-gpts
- docker
- docker-compose
Rust library for generating vector embeddings and reranking locally!
- embeddings
- rag
- retrieval
- retrieval-augmented-generation
CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.
Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.
Qwen-AgentWorld: Language World Models for General Agents
Local observability for AI coding agents. Agenttrail Map shows your project as a live map of what each agent is working on, in the browser or natively in Herdr.
- agent-monitoring
- agent-observability
- ai-agents
- ai-coding-agents
Search photos on Unsplash using natural language
- unsplash
- clip
- machine-learning
- computer-vision
talkie is a vintage language model from 1930
WebWhiz allows you to create an AI chatbot that knows everything about your product and can instantly respond to your customer's queries.
Repo for Chinese Medical ChatGLM 基于中文医学知识的ChatGLM指令微调
- chinese
- medical
- medqa
- nlp
开源、可私有化部署的 Web Agent 底座,支持多用户、隔离沙箱,以及 Skills 和 MCP 扩展。Open-source, self-hostable Web Agent foundation with multi-user support, isolated sandboxes, and extensibility through Skills and MCP.
[NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web" -- the first LLM-based web agent and benchmark for generalist web agents
Build fast and accurate GenAI apps with GraphRAG SDK at scale 🌟
- falkordb
- graphrag
- knowledge-graph
- rag
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
A lightweight multilingual LLM
A blueprint for building production-ready RAG systems that minimize hallucination, featuring switchable 3-step (Speed) and 4-step (Precision) pipelines.