Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
Repository Index
98,836 visible repositories in the index
73–96 of 108 · Most stars
🔨 List all IP ranges from: Google (Cloud & GoogleBot), Bing (Bingbot), Amazon (AWS), Microsoft, Oracle (Cloud), GitHub, Facebook (Meta), OpenAI (GPTBot) and other with daily updates.
- googlebot
- google-cloud
- amazon-aws
- microsoft
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
something like visual-chatgpt, 文心一言的开源版
Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.
- huggingface
- inference
- llm
- mechanistic-interpretability
An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE methodology.
- ai-security
- application-security
- attack-trees
- cybersecurity
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
- ai-agent
- autonomous-agent
- claude-code
- deep-learning
Evaluate your LLM's response with Prometheus and GPT4 💯
- evaluation
- litellm
- llm
- llmops
Caveman Compression is a semantic compression method for LLM contexts. It removes predictable grammar while preserving the unpredictable, factual content that defines meaning.
Free, open source BI platform with AI conversational analytics (BYO-LLM), pixel-perfect paginated reports, interactive dashboards, SSO, embedding, multi-tenancy & row-level security. Every feature free in Community Edition. Self-hosted, Docker-ready
- agentic-bi
- ai-analytics
- bi-tools
- business-analytics
azooKey-Desktop is an open-source Japanese input method for macOS, written in Swift and powered by the Zenzai neural kana-kanji converter. It provides live conversion, optional LLM-based “Magic Conversions”, and Tuner-backed personalization for a smooth, desktop typing experience.
- azookey
- ime
- input-method
- inputmethodkit
Own the flow: one open-source AI platform for your knowledge, models and channels – web, WhatsApp, email, Outlook, Nextcloud & ownCloud. Local and cloud models side by side, with the cost on every answer.
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
- apple-silicon
- clover
- coding-agents
- decision-models
BLEURT is a metric for Natural Language Generation based on transfer learning.
Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity in real time. Lightweight background daemon (<50MB RAM), SQLite storage, Material Design 3 dashboard. Zero telemetry.
- developer-tools
- golang
- quota-tracker
- ai-api-monitoring
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
- apple-silicon
- llm
- llm-inference
- local-llm
Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
- meta-learning
- reinforcement-learning
- rsi
- ai-agents
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
- ai-agents
- benchmarking
- llm-evaluation
- python
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky commands to the content that dictated them. Open source, no telemetry.
- agent-security
- ai-agents
- ai-security
- claude-code
TranslatedPrompt editor for DSH with method cards, draft comparison and quote recovery. DeepSeek Harness (DSH) prompt engineering plugin. Spot omissions in the input box and add a sentence picked from 90 method cards, or rewrite against the original draft, check quotes and restore the original words.
Deepinfer inspired implemetation on SM80 Ampere architecture. Deepest respect for DeepSeek opensource this work!
PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-then-correct), OpenAI-compatible local server, report and logs.