kimi-k3

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.6, Claude Fable 5, Claude Sonnet 5, DeepSeek V4, Grok, OpenRouter, Kimi k3, GLM 5.2, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.7

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

Run Kimi K3 locally on CPU with ~55GB measured runtime RAM. A single-file Linux inference server powered by cPilot Runtime.

ServerKit is a lightweight, modern server control panel for managing web applications, databases, and services on your VPS or dedicated server. Built with Python/Flask backend and React frontend.

Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.

Long Horizon Terminal Benchmark with Dense Reward Grading

11 installable skills for Claude Code, OpenAI Codex, and Hermes, for finding your unknowns before they get expensive: blindspot pass, brainstorms, interviews, references, plans, notes, pitches, a merge quiz, plus a context audit, agent interface design, and progressive disclosure. Community distillation, not official Anthropic.

A WIP vibe friendly game engine.

Kimi K3, deepseek v4 flash, glm 5.2,

AI驱动的影视广告创作平台/AI-driven platform for film and television advertising creation

Evidence-backed structural validation of Kimi K3 UD-IQ1_M and UD-Q4_K_XL split GGUF releases using OMIV.

Modern desktop client for FTP, SFTP, SSH, and S3-compatible storage. FTP, SFTP, SSH, and S3 in one clean workspace.

Adaptive MoE inference for Kimi K3 — beyond-memory expert streaming, reversible runtime profiles, measured optimization results, and an open NVIDIA/GPU/NPU adaptation roadmap.

SillyTavern extension: client-side reasoning_content thinking prefill for Kimi/Moonshot models (kimi-k3-jb patch equivalent, no server modifications)

Autonomous multi-agent pentest framework — plans, exploits, verifies (proof-required), CVSS-scores and writes client-ready reports. 104/104 (100%) on the XBOW validation benchmarks, powered by Kimi K3.

Build and train a mini Kimi K3 from scratch — a pure-PyTorch playground from a custom 88M model to 2T-scale LLM profiles.

Summer Town Interactive Map

KinetAios

Kimi Code CLI 的桌面客户端 — Electron 桌面壳内嵌官方 kimi web 界面，附加 Git 面板、代码预览、模型管理、使用统计等桌面端增强。