kimi

A high-throughput and memory-efficient inference and serving engine for LLMs

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.

TokenSpeed is a speed-of-light LLM inference engine.

Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究平台 — Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72，即将推出™ TPUv6e/v7/Trainium2/3

Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere

AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.

支持将openai、claude、azure openai, gemini,kimi, 智谱AI,通义千问,讯飞星火API等模型服务方的调用转为openai方式调用。屏蔽不同大模型API的差异，统一用openai api标准��式使用大模型(Shield the differences between different large model APIs and use large models in a unified openai API standard format)

基于MoneyPrinterTurbo，AI生成分镜大纲与视频（动态，不是念ppt），接入万相通义wan2.1 ai文生视频、图生视频功能，灵活把控视频生成。Based on MoneyPrinterTurbo, AI generates image outline and video (dynamic, not ppt), and integrates wan2.1 text-to-video and image-to-video functions to flexibly control video generation.

Governance standard and reference toolset for LLM-maintained knowledge corpora

Desktop app + OpenAI-compatible API that proxies LLM web UIs for unofficial integration of LLMs into SillyTavern and other clients.

Bridgic is the next-generation agent development framework for building intelligent systems.

长篇网络小说自动化写作 AI Agent，支持Chatgpt、gemini、Deepseek等国内外模型接入，采用拆书 + 仿写的模式，从新世界观、大纲、卷纲设计，到章节片段完善&章纲设计，有效解决 AI 写作中的「前后矛盾」、「容易遗忘」、「缺乏特色」和「AI味重」等问题，支持 百万字量级 连载创作。

一个让 Claude Code 调用 Codex 干活，并可以同时调用多个模型（GPT、Kimi、DeepSeek 等）的 MCP 工具。

Open-source agent skills for turning raw book ideas into full manuscripts with blind literary evaluation gates.

Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Kimi, Cursor, Gemini, OpenCode, or Command Code from any compatible tool.

PARL (Parallel-Agent Reinforcement Learning) is a training paradigm that teaches models to decompose complex tasks into parallel subtasks and coordinate multiple agents simultaneously.

Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek models in Codex CLI or any OpenAI client. Cross-platform, single-file, no auth changes.

Markdown-first multi-model AI orchestration in one tmux session. A single coordinator (Chrono) routes scoped task packets across 4 frontier model families (Codex / Claude / Gemini / Kimi) to 68 role-based specialists — isolated git worktrees, cross-family review gates, durable memory. No server. Dogfooded daily.