Kimi Code Desktop detailed: transparent agent steps, tower multi-agent mode and built-in browser
KimiDevs · x · 2026-09-21
Kimi detailed the feature set of Kimi Code Desktop (macOS/Windows):
- Transparent AI coding: every agent step is visible — tool calls, reasoning, and exactly which files changed each round; sensitive actions trigger approval prompts, with three permission modes (always ask / ask when needed / fully automatic)
- Full conversation-to-delivery workflow: plans are reviewable before work begins; long tasks can move to background; experimental tower multi-agent mode runs agents in parallel
- Built-in browser: right-panel browser with persistent tabs per session, page context shared with the agent — check docs, preview results, and verify pages without switching windows
Related event: Kimi Launches Code Desktop with Parallel Multi-Agent Coding(2 posts)→
More from coding & agent
- Google open-sources AX, an agentic orchestrator likened to Kubernetes for agent executions — arpit_bhayani · 2026-09-21
- Watching Claude use a Charuco board to estimate product dimensions from a photo and model it in OpenSCAD — _Stocko_ · 2026-09-21
- AI intern cuts job boot time ~60%, saving ~5 CPU-days per day — DanielLockyer · 2026-09-21
- Anthropic engineer demos 22-minute async Claude Code workflow that runs unattended — anthara_ai · 2026-09-21
- Would coding agents do fine with just bash? Benchmarking without read/write/edit tools — lucasmeijer · 2026-09-21
- StepFun's Step 5 Preview early tests: Pareto frontier on cost vs. capability — StepFun_ai · 2026-09-21