Self-hosted AI coding assistant
Repository Index
56,638 visible repositories in the index
1–17 of 17 · Most stars
TranslatedAn enhanced tool for CodexApp, striving to make Codex better to use and more comfortable. It strives to make Codex and other AI Agents easier and more comfortable to use.
The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
- text-extraction
- document-intelligence
- metadata-extraction
- pdf-extraction
A Datacenter Scale Distributed Inference Serving Framework
- diffusion
- disaggregated-serving
- kubernetes
- llm-inference
Fast, flexible LLM inference
- llm
- rust
- uqff
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.
Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.
- gateway
- generative-ai
- llm-inference
- llms
Postgres with GPUs for ML/AI apps.
- ml
- machine-learning
- ai
- ann
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
- llama
- llamacpp
- llm-inference
- ollama-api
A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.
A blazing fast inference solution for text embeddings models
A high-performance inference engine for AI models
TranslatedLocal AI routing gateway with Agent client takeover — reuse existing client logins, call 50+ AI clients through one base URL, with unified OpenAI / Anthropic / Images APIs, multi-account routing, check-in, balance and request reports
- autoclaw
- catpaw
- local-proxy
- openai-compatible
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
The repository host gives no description.
Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.
Modern desktop application (Rust + Tauri v2 + Svelte 5 + Candle (HF)) for communicating with AI models that runs completely locally on your computer. No subscriptions, no data sent to the internet — just you and your personal AI assistant
- ai-chat
- artificial-intelligence
- candle
- chatbot