LLM Council works together to answer your hardest questions
Repository Index
132,241 visible repositories in the index
1–14 of 14 · Most stars
AI that sees your screen, listens to your conversations and tells you what to do
Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
- localllm
Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
- metric-learning
- deep-learning
- computer-vision
- machine-learning
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
- agent-orchestration
- ai-agents
- harness
- agentic-ai
The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.
Community maintained hardware plugin for vLLM on Huawei Ascend
Community maintained hardware plugin for vLLM on Apple Silicon
Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrated probabilities. One base, swappable LoRA adapters, on your own hardware.
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU
Arena-Hard-Auto: An automatic LLM benchmark.
Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.
OpenAI API-compatible wrapper for Claude Code