[ICLR 2026] LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
Repository Index
142,273 visible repositories in the index
1,753–1,776 of 1,944 · Most stars
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
- agent-memory
- agentic-ai
- ai-agents
- ai-infrastructure
LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.
- efficient
- gpt4o
- gpt4v
- large-language-models
A decentralized agent network for building collaborative, LLM-powered agent-to-agent (A2A) systems.
FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs
- agents
- grpo
- huggingface
- llm
Long Horizon Terminal Benchmark with Dense Reward Grading
- long-horizon-agents
- long-horizon-tasks
- claude
- fable5
[CVPR 2025] RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete. Official Repository.
Repository of DISC-MedLLM, it is a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services.
The repository host gives no description.
Supercharge your command line with LLMs and get shell scripting assistance in Fish. 💪
- fish-plugin
- fisher
Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.
- anthropic-claude
- browser-automation
- home-automation
- jarvis
Repository for the "Building LLMs for Production" book by Towards AI.
Use Code Llama with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.
- code-llama
- code
- llama
- studio
A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.
- azure
- generative-ai
- gpt
- language-model
Can AI agents rebuild websites through browser exploration?
- benchmark
- harbor
- website-reconstruction
- agent-evaluation
The AutoGPT MetaTrader Plugin is a software tool that enables traders to connect their MetaTrader 4 or 5 trading account to Auto-GPT.
A Graph-Centric Framework for Orchestrating Multi-Agent Systems with Vibe Graphing.
- graph
- llm
- mas
- multi-agent-systems
Real-time multimodal desktop agent evolving toward a persistent AI OS interface (0.17 α).
Deep Reinforcement Learning (PPO) in Autonomous Driving (Carla) [from scratch]
- autonomous-driving
- ddqn
- reinforcement-learning
- self-driving-car
LLM finetuned for medical question answering
Ollama Automated Security Intelligence Scanner
The self-improvement layer for AI agents. Ratel reads your agent's traces, finds what fails, recommends fixes and runs evals on real sessions before you ship. Self-hosted: one app, one Postgres. Includes the TypeScript and Python SDK
- accuracy
- agents
- context
- harness
sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRgv6ZD
Interactive Composition Explorer: a debugger for compositional language model programs