47,133 repositories indexed
73–94 of 94 · Most stars
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.
gemini bindings for Neovim
TranslatedBig Blue Fish desktop pet with local LLM. A Windows AI desktop pet with a built-in 4B local large model. It uses a whale-girl persona that combines weather, tech news and the current application to keep you gentle company through text bubbles. Supports one-click installation and pausing inference when off power.
Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.
From a universe of models to Collective Model Intelligence.
MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU, streaming experts from flash with lookahead scheduling (LES) and DSpark speculation.
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
🌳 Connecting ChatGPT with the Internet
PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.
DeepWrite AI is Made with the Help of ChatGPT3 and Specific Model is Prepared for Generating Perfect Blog Post with atmost Clarity. This is Just the Version 1.0 More Improvement Will be Implemented.
TranslatedLocal-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health
The repository host gives no description.
BIA Bob is a Jupyter+LLM-based assistant for interacting with image data and for working on Bio-image Analysis tasks.
Manage and use multiple Ollama instances with automatic offline detection/failover and model availability tracking
GPTModels - a multi model, window based LLM AI plugin for neovim, with an emphasis on stability and clean code
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
FairPlayCombined is a platform designed to accelerate app development using .NET, Blazor, and more. It includes real-world templates like video sharing and dating apps, reducing costs and time-to-market. Perfect for developers, startups, and businesses, it empowers innovation and delivers value with pre-built tools and resources.
This is a german ELMo deep contextualized word representation. It is trained on a special German Wikipedia Text Corpus.
Claude Code dashboard: see where your limits are headed before you hit them. Calibrated usage forecasts, live rate-limit gauges, session costs, memory browser. Single binary, zero config, plus a VS Code extension.
Local-only observability for AI agents on your machine. One timeline across coding and non-coding agents.
Catch silent failures in agent workflows by verifying real system state