Kimi Code CLI shifts to TypeScript, adds video

// 1h agoPRODUCT UPDATE

Kimi Code CLI shifts to TypeScript, adds video

Moonshot AI's terminal agent reaches v0.4.0 with a complete TypeScript rewrite and support for video input. The update introduces a three-agent swarm architecture for parallelized planning, exploration, and coding.

// ANALYSIS

Kimi Code CLI is evolving from a Python script into a high-performance system-level tool that rivals Claude Code and Aider. The move to TypeScript signals a focus on latency and distribution.

–TypeScript migration delivers millisecond startup speeds and a single-binary distribution, removing Node.js/Python runtime dependencies.
–Video input support allows the agent to "see" UI bugs and visual specs, closing the gap between CLI tools and visual development.
–The new 3-agent parallel architecture (coder, explore, plan) reduces the linear bottleneck of standard "think-then-act" loops.
–Native MCP and ACP support ensures compatibility with both external tools and established IDEs like VS Code and Zed.
–Support for an "Agent Swarm" of up to 100 sub-agents positions Kimi as a heavy lifter for large-scale refactors.

// TAGS

kimi-code-clicliai-codingcoding-agentagentmcpopen-source

DISCOVERED

1h ago

2026-05-30

PUBLISHED

2h ago

2026-05-30

RELEVANCE

9/ 10

AUTHOR

GithubProjects

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE42m ago

Claude Code defaults to Opus 4.8

Claude Code v2.1.154 promotes Opus 4.8 to the default high-effort model, adds dynamic workflows that can orchestrate work across dozens to hundreds of background agents, and improves fast mode economics and speed on Opus 4.8. The release also refines cleanup flows with a lighter `/simplify` path, renames effort labels for clarity, and tightens several CLI and agent workflows for heavier terminal-based coding sessions.

TUTORIAL51m ago

LLMWhisperer powers complex-document RAG pipelines

The video shows LLMWhisperer as Unstract’s layout-aware text extraction layer for PDFs, images, and scanned documents. That preprocessing step turns messy files into LLM-ready input for downstream extraction and RAG workflows.

TUTORIAL51m ago

Unstract tutorial covers local setup

This YouTube walkthrough shows how to self-host Unstract, the open-source document extraction platform, with Docker and local model support. It positions the tool as a practical fit for offline and private RAG-style workflows that turn PDFs and other files into structured outputs.

Kimi Code CLI shifts to TypeScript, adds video