Kimi-K2.6 · Cloudflare AI Gateway

Claude Code alternative, on your own Cloudflare account.

An open-source terminal coding agent powered by Kimi K2.6 and routed through your own Cloudflare AI Gateway — with per-request logs, response caching, and authoritative cost out of the box.

Install View source

Get Kimiflare updates

Occasional release notes, technical write-ups, and early experiments on building AI coding agents on Cloudflare.

No spam. Only meaningful ships.

zsh

kimiflare Ready when you are.

  › Explain this codebase
  › Find and fix a bug
  › Refactor a file

Type a message or /help for commands · ctrl-c to exit · shift+tab to cycle modes

› add a /health endpoint

────────────────────────────────────────

thinking… I'll need to read the server file first, then add the endpoint.

⠋ read(src/server.ts)

✓ read(src/server.ts)

⠋ edit src/server.ts

Permission requested

tool: edit

action: edit src/server.ts

@@ -42,6 +42,10 @@
  app.get('/', …)
+  app.get('/health', (_, res) => res.json({ ok: true }))
  …

› Allow once Allow for this session Deny

✓ edit src/server.ts

Done — added /health that returns { ok: true }.

────────────────────────────────────────

■ Update landing page terminal (12s · ↑ 2.3k tokens)

✓ Read current UI components

■ Update terminal simulation

☐ Create PR

[edit] k2.6 · medium · thinking…

in 2,847 (1,203 cached) · out 412 · ctx 12% · 0.00321

›

Features

What it does

Plan / Edit / Auto modes

Plan mode blocks all mutating tools for safe research. Edit mode prompts per call. Auto mode approves everything for trusted tasks.

Live task panel

For multi-step work, the agent publishes a task list with progress icons, elapsed time, and token deltas. Multi-step work feels managed.

Image understanding

Drop image paths (PNG, JPG, WebP, GIF, BMP up to 5 MB) into any prompt. The model sees them inline — perfect for UI reviews, diagrams, and screenshots.

Extensible JSON themes

Fully customizable color palettes with WCAG contrast validation. Pick from built-in presets or define your own. Live preview with Ctrl+T.

Web search, GitHub, and headless browser

Research the web, read GitHub repos, and fetch JavaScript-rendered pages — all without leaving your terminal.

LSP semantic code intelligence

Hover, go-to-definition, references, and diagnostics via Language Server Protocol. Auto-configured per project with an interactive wizard.

Turn supervisor with tiered skills

The agent picks the right skill depth for the task — from quick edits to deep research — with graceful preemption and visible TUI indicators.

Streaming reasoning

Toggle the model's chain-of-thought with /reasoning or Ctrl-R. See how it thinks in real time.

Session persistence

Every turn is auto-saved. /resume lists past sessions with message counts in a paginated picker. Never lose your place.

Smart permissions

Bash session-allow is keyed by the first token (allow all git commands). Write/edit show a unified diff before you approve.

262K context window

Read entire modules, large configs, and full stack traces without the model losing track. All on your Cloudflare account.

MCP server integration

Plug in external tools via the Model Context Protocol — local stdio servers or remote SSE endpoints. GitHub, Sentry, docs search, databases, and more.

AI Gateway — observability by default

Every request flows through your own Cloudflare AI Gateway. Per-request logs, response caching with configurable TTL, authoritative per-turn cost from the logs API, and a per-feature breakdown in /cost. The status bar shows the gateway-confirmed cost and latency for the last turn.

Explicit cross-session memory

The agent never surveils your conversation. Memories are stored only when you ask — via remember, recall, and forget tools — with SQLite + embeddings for durable, privacy-respecting retrieval across sessions.

Architecture

kimiflare Node.js TUI
↓ user msg → agent loop → runKimi()
↓ POST SSE via your AI Gateway
gateway.ai.cloudflare.com logs · cache · cost
↓
Workers AI @cf/moonshotai/kimi-k2.6
↑ tool result ← tool executor ← tool_calls
↑ permission modal for write / edit / bash

Tools

Core tools

Tool	Permission	Description
read	auto	Read a text file (≤ 2MB) with optional line range
write	prompt	Create or overwrite a file. Shows a diff before approval
edit	prompt	Replace an exact substring. Fails unless unique match
bash	prompt	Run a shell command. Session-allow keyed by first token
glob	auto	Match files by pattern, sorted by mtime
grep	auto	Regex search. Uses ripgrep if available
web_fetch	auto	Fetch a URL, convert HTML → markdown (≤ 100KB)
web_search	auto	Search the web and return summarized results
github_read	auto	Read files and issues from public GitHub repos
browser_fetch	auto	Headless browser for JavaScript-rendered pages
tasks_set	auto	Publish a live task list for multi-step work

Plus LSP intelligence (hover, go-to-definition, references, diagnostics), cross-session memory (remember / recall / forget), and MCP extensibility for plugging in external tool servers.