Category : github

github
PrefectHQ / fastmcp

๐Ÿš€ The fast, Pythonic way to build MCP servers and clients. FastMCP ๐Ÿš€ Move fast and make things. Made with ๐Ÿ’™ by Prefect The Model Context Protocol (MCP) connects LLMs to tools and data. FastMCP gives you everything you need to go from prototype to production: from fastmcp import FastMCP mcp = FastMCP("Demo ๐Ÿš€") @mcp.tool def add(a: int, b: int) -> int: """Add two numbers""" return a + b if __name__ == "__main__": mcp.ruโ€ฆ

  • ะฒั‚ะพั€ะฝะธะบ, 21 ะธัŽะปั 2026โ€ฏะณ. ะฒ 00:00:03
github
andrewrabert / jellium-desktop

An unofficial desktop client for JellyfinJellium Desktop An unofficial Jellyfin desktop client built on CEF and mpv. Downloads Linux AppImage x86_64 aarch64 Arch Linux (AUR): jellium-desktop-git Flatpak (non-Flathub bundle) macOS Apple Silicon Intel After installing, remove quarantine: sudo xattr -cr /Applications/Jellium\ Desktop.app Windows x64 arm64 Development This project uses just as a command runner. Available recipes: [package] appimage ... # [linux] build AppImage โ€ฆ

  • ะฟะพะฝะตะดะตะปัŒะฝะธะบ, 20 ะธัŽะปั 2026โ€ฏะณ. ะฒ 00:00:03
github
kvcache-ai / ktransformers

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations A Flexible Framework for Experiencing Cutting-edge LLM Inference/Fine-tune Optimizations ๐ŸŽฏ Overview | ๐Ÿš€ Inference | ๐ŸŽ“ SFT | ๐Ÿ”ฅ Citation | ๐Ÿš€ Roadmap(2026Q2) ๐ŸŽฏ Overview KTransformers is a research project focused on efficient inference and fine-tuning of large language models through CPU-GPU heterogeneous computing. The project now exposes two user-facing capabilities from the kt-kernel sourโ€ฆ

  • ะฟะพะฝะตะดะตะปัŒะฝะธะบ, 20 ะธัŽะปั 2026โ€ฏะณ. ะฒ 00:00:02
github
KnockOutEZ / wigolo

The go-to web for your AI coding agent โ€” local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta. Local-first web intelligence for AI agents โ€” no keys, no cloud, no metered bill. works withย ย Claude Code ยท Cursor ยท Codex ยท Gemini CLI ยท VS Code ยท Windsurf ยท Zed ยท Antigravity and beyondย ย LangChain ยท CrewAI ยท LlamaIndex ยท Vercel AI SDK ยท n8n & self-hosted agents ยท any MCP client ยท plain REST Quickstart ยท Tools ยท Why wigolo ยท Benchmark ยท Docs ยท โ€ฆ

  • ะฒะพัะบั€ะตัะตะฝัŒะต, 19 ะธัŽะปั 2026โ€ฏะณ. ะฒ 00:00:04
github
elder-plinius / G0DM0D3

LIBERATED AI CHAT โ–„โ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–„ โ–„โ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–„โ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€ โ–‘โ–’โ–“โ–ˆ LIBERATED AI. COGNITION WITHOUT CONTROL. โ–ˆโ–“โ–’โ–‘ โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€ GODMOD3.AI Gโ€ฆ

  • ะฒะพัะบั€ะตัะตะฝัŒะต, 19 ะธัŽะปั 2026โ€ฏะณ. ะฒ 00:00:02
github
tirth8205 / code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.code-review-graph Stop burning tokens. Start reviewing smarter. English | ็ฎ€ไฝ“ไธญๆ–‡ | ๆ—ฅๆœฌ่ชž | ํ•œ๊ตญ์–ด | เคนเคฟเคจเฅเคฆเฅ€ Usage ยท Commands ยท FAQ ยท Troubleshooting ยท GitHub Action ยท Reproducing the benchmarks ยท Roadmap AI coding tools can end up re-reโ€ฆ

  • ััƒะฑะฑะพั‚ะฐ, 18 ะธัŽะปั 2026โ€ฏะณ. ะฒ 00:00:04
github
anthropics / cwc-workshops

cwc-workshops Workshop materials. Not maintained and not accepting contributions. Materials from Anthropic-run Code with Claude workshops. Workshops rightmodel/ โ€” Picking the Right Model: use a Claude Code SKILL to audit an LLM eval suite and sweep it across models and inference parameters (extended thinking, effort) to find the best quality-per-dollar and quality-per-second configuration. agent-decomposition/ โ€” Compose Multi-Agent Systems with Skills and MCP: decompose a 400-line-prompt invโ€ฆ

  • ััƒะฑะฑะพั‚ะฐ, 18 ะธัŽะปั 2026โ€ฏะณ. ะฒ 00:00:02
github
ibelick / ui-skills

Skills for Design EngineersUI Skills Skills for Design Engineers More on ui-skills.com Run npx ui-skills start to route your agent through the right UI skill set for the task. CLI npx ui-skills npx ui-skills start npx ui-skills categories npx ui-skills list --category motion npx ui-skills get baseline-ui License Licensed under the MIT license.

  • ะฟัั‚ะฝะธั†ะฐ, 17 ะธัŽะปั 2026โ€ฏะณ. ะฒ 00:00:05
github
PrismML-Eng / Bonsai-demo

Bonsai DemoBonsai Demo Website ย |ย  GitHub ย |ย  Discord HF Collections: Bonsai 27B ยท Bonsai (1-bit) ยท Ternary-Bonsai Whitepapers: Bonsai 27B ยท 1-bit Bonsai 8B ยท Ternary-Bonsai 8B Using this demo repository you can run Bonsai (1-bit) and Ternary-Bonsai language models locally on Mac (Metal), Linux/Windows (CUDA, Vulkan, ROCm), or CPU. ๐ŸŒฑ New: Bonsai 27B The family's newest and largest generation, and its first vision-language models (Bonsai 27B collection): Viโ€ฆ

  • ะฟัั‚ะฝะธั†ะฐ, 17 ะธัŽะปั 2026โ€ฏะณ. ะฒ 00:00:04