Kimi CLI / Kimi Agent should be described as multiple Moonshot AI surfaces under one Agent category: Kimi web for long-context research and document workflows, Kimi Agent for task execution and planning, and Kimi Code CLI for developer-facing terminal workflows. Its value on agentk.it is not generic coding alone; it is the combination of long-context Chinese/English research, document analysis, and a growing coding-agent path that needs careful separation from the chat product.
Back to Agents
china agent
Kimi CLI / Kimi Agent
Moonshot AI's Kimi agent surface for long-context research, document-heavy workflows, and Kimi Code CLI development tasks.
Moonshot AI webcli
01
Agent profile and official evidence.
Use this first to understand what the agent is good at before checking compatible tools.
Long-context researchDocument-heavy analysisChinese and bilingual workflowsKimi Code CLI exploration
Last checked: 2026-05-12
02
Where Kimi CLI / Kimi Agent is strongest.
Short, rigorous notes for deciding whether this agent belongs in your stack.
Long-context orientation
Kimi is strongly associated with long-context reading, research, document understanding, and multi-step information work.
Agent and research product surface
Kimi's public help materials describe agent-style workflows for planning and completing tasks such as research, website generation, slides, and document work.
Kimi Code CLI path
Kimi Code CLI is the developer-facing path and should be tracked separately from the general Kimi chat or web agent experience.
China-origin content fit
Kimi is especially relevant for Chinese high-quality content discovery, translation review, and bilingual developer knowledge workflows.
03
How it connects to tools.
MCP, Skills, CLI, and Workflow support are treated as compatibility claims with sources.
CLI Supported
Kimi Code CLI is the relevant surface for terminal-based coding-agent workflows.
ACP SupportedKimi CLI documents an ACP agent server mode, which matters for integration with compatible clients.
Workflow NativeKimi is strongest for long-context research, document workflows, and task planning rather than only repository coding.
Skills UnknownDo not assume a stable SKILL.md-compatible ecosystem unless official Kimi Code docs or a reviewed source documents it.
04
Compatible tools mapped to Kimi CLI / Kimi Agent.
Open the item page for what it does, source links, stars, license, freshness, and compatibility context.
agent-desktop
Native desktop automation CLI for AI agents. Control any application through OS accessibility trees with structured JSON output and deterministic element refs.
agentic-radar
A security scanner for your LLM agentic workflows
agentsys
AI writes code. This automates everything else · 26 plugins · 50 agents · 47 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.
Ai-Agent-Skills
my curated agent skills library
AutoR
AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.
axe
A lightweight cli for running single-purpose AI agents. Define focused agents in TOML, trigger them from anywhere; pipes, git hooks, cron, or the terminal.
baguette
Headless iOS Simulator manager/farm + host-side input injection for iOS 26 — taps, swipes, multi-finger gestures, and 60 fps streaming
boss-agent-cli
AI-agent-first CLI for BOSS 直聘 — 职位搜索、福利筛选、招聘者工作流、MCP 工具与 AI 简历优化
ccpocket
Mobile client for Codex and Claude — control coding agents from your phone via WebSocket bridge
claude-squad
Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.
claurst
Agentic Coding for Builders who Ship
CodeWhale
Agentic coding terminal. DeepSeek-first, multi-provider, cache-maximal, whale-themed. Five-locale UI, CN-region endpoint, CNB mirror.
CoreCoder
Minimal AI coding agent (~1,400 LoC Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
destructive_command_guard
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
iwe
Markdown memory system for you and your AI agent
jcode
Coding Agent Harness
kilocode
Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.
linear-cli
linear without leaving the command line: list, start, and create PRs for linear issues. agent friendly.
MassGen
🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai
OpenCLI
Make Any Website into CLI & Use your logged-in browser by AI agent.
pgschema
Terraform-style, declarative schema migration CLI for Postgres. Agent friendly.
pi_agent_rust
High-performance AI coding agent CLI written in Rust with zero unsafe code
plandex
Open source AI coding agent. Designed for large projects and real world tasks.
pocketpaw
Your AI agent in 30 seconds. Not 30 hours. Self-hosted, open-source personal AI with desktop installer, multi-agent Command Center(Deep Work), and 7-layer security. Anthropic, OpenAI, or Ollama.
pup
Give your AI agent a Pup — a CLI companion with 200+ commands across 33+ Datadog products.
rmux
Universal Rust multiplexer with a typed SDK — drive any CLI or TUI app from code. Native on Linux, macOS, and Windows.
ship-safe
CLI security scanner built for the agentic era. Detects CI/CD misconfigs, agent permission risks, MCP tool injection, hardcoded secrets, and DMCA-flagged AI dependencies.
soulforge
AI coding agent that edits symbols, not strings. AST surgery, full LSP, and a live code graph wired to memory that resurfaces by file, co-change, and semantics.
superset
Code Editor for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine
three-man-team
A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.
vibeyard
The IDE built for AI coding agents.
Wax
Single-file memory layer for AI agents, sub mili-second RAG on Apple Silicon. Metal Optimized On-Device. No Server. No API. One File. Pure Swift
yao
✨ Build AI agents and web apps — with a single binary.
Abtop
Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.
Agent Of Empires
Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding. Uses tmux and git worktrees.
Blades
Blades is a Go-based multimodal AI Agent framework.
Ccmanager
Coding Agent Session Manager for Claude Code / Gemini CLI / Codex CLI / Cursor Agent / Copilot CLI / Cline CLI / OpenCode / Kimi CLI
Claude Code Tools
Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents.
Claude Codex Bridge
Visible multi-agent CLI teams for Claude, Codex, Gemini, OpenCode, and Droid with project memory and tmux supervision
Cli Printing Press
Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compound insight commands.
DeepSeek Reasonix
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
Dmux
A dev agent multiplexer for git worktrees and coding agents.
Emdash
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
Grok Cli
An open-source coding agent for the Grok API
Herdr
agent multiplexer that lives in your terminal.
Hunk
Review-first terminal diff viewer for agentic coders
Imsg
CLI for Apple's Messages.app so your agent can send and receive text messages/iMessages.
Inkos
Autonomous novel writing AI Agent — agents write, audit, and revise novels with human review gates
LearnPrompt
永久免费开源的 AIGC 课程, 目前已支持Claude Code，Codex，Hermes，OpenClaw，Obsidian，Prompt Engineering, ChatGPT, Midjourney, Runway, Stable Diffusion, AI数字人，AI声音&音乐，开源大模型
Opensrc
Fetch source code for npm packages to give AI coding agents deeper context
Orca
Orca is the next-gen IDE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop and mobile.
OSWorld
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Tirith
Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.
X Cmd
Shell Superpowers for AI Agents.
Zcf
Zero-Config Code Flow for Claude code & Codex
AI Novel Writing Assistant
面向长篇小说创作的 AI Native 开源系统，用 Agent、世界观、写法引擎、RAG 和整本生产工作流，帮助新手从一句灵感走到完整小说。AI-native engine for end-to-end novel creation — from idea to full chapters, with structured planning, worldbuilding, and agent-driven workflows.
Aider
aider is AI pair programming in your terminal
Backlog.md
Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem
Bytechef
Open-source platform that unifies AI agent orchestration and workflow automation — autonomy and precision in one platform.
Chatgpt Cli
ChatGPT CLI is a powerful, multi-provider command-line interface for working with modern LLMs. It supports OpenAI, Azure, Perplexity, LLaMA, and more, with features like streaming, interactive chat, prompt files, image/audio I/O, MCP tool calls, and an experimental agent mode for safe, multi-step automation.
Cli
The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetings, and more, with 200+ commands and 20+ AI Agent Skills.
CodeMachine CLI
CodeMachine is an open-source tool that orchestrates AI coding agents into repeatable, long-running workflows. ⚡️
Continue
⏩ Source-controlled AI checks, enforceable in CI. Powered by the open-source Continue CLI
DeepSeek TUI
Coding agent for DeepSeek models that runs in your terminal
Dify
Production-ready platform for agentic workflow development.
Flow Like
Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration and rich customization.
Hacker Podcast
一个基于 AI 的 Hacker News 中文播客项目，每天自动抓取 Hacker News 热门文章，通过 AI 生成中文总结并转换为播客内容。
Langchain4j Aideepin
基于AI的工作效率提升工具（聊天、绘画、知识库、工作流、 MCP服务市场、语音输入输出、长期记忆） | Ai-based productivity tools (Chat,Draw,RAG,Workflow,MCP marketplace, ASR,TTS, Long-term memory etc)
Netdata
The fastest path to AI-powered full stack observability, even for lean teams.
Nx
The Monorepo Platform that amplifies both developers and AI agents. Nx optimizes your builds, scales your CI, and fixes failed PRs automatically. Ship in half the time.
Obsidian Skills
Agent skills for Obsidian. Teach your agent to use Markdown, Bases, JSON Canvas, and use the CLI.
OpenHands
🙌 OpenHands: AI-Driven Development
OpenMontage
World's first open-source, agentic video production system. 12 pipelines, 52 tools, 500+ agent skills. Turn your AI coding assistant into a full video production studio.
Pro Workflow
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.
Sim
Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
ToolJet
ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀
Trellis
The best agent harness.
Trigger.dev
Trigger.dev – build and deploy fully‑managed AI agents and workflows
Mcp Scanner
Scan MCP servers for potential threats & security findings.
Muapi Cli
Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Aichat
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
Harbor
Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.
Inspector
Development platform to debug, chat, inspect, and evaluate MCP servers, MCP apps, and ChatGPT apps.
N8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Pyspur
A visual playground for agentic workflows: Iterate over your agents 10x faster
05
Recommended stacks.
Practical combinations that connect this Agent with tools already in the directory.
Research-to-signal workflow
Use Kimi as a research and translation candidate source, then route publishable material through Signals review.
Kimi Code developer path
Track CLI, ACP mode, and editor/terminal integrations separately from the general Kimi web product.
Document analysis path
Use Kimi-related learning content for long-document reasoning and bilingual research workflows before recommending tool integrations.
- Kimi web agent, Kimi Code CLI, Kimi Agent, and Moonshot API are different surfaces and should not be merged into one compatibility claim.
- Official English documentation may lag Chinese product updates, so last-checked dates matter.
- Third-party Kimi CLI guides should remain candidate-only unless official or repository-backed.
- Do not show install commands unless they are clearly official and current; prefer official links.