CZL AI
Act. Create. Build.
More than a chat box. CZL Agent plans, calls tools and checks its own work on an in-house harness until the job is done; AI apps work out of the box; the API gateway gives you every major model through one endpoint.
Desktop app for Windows and macOS; the same account works on the web and as a PWA
Three platforms, one account
One balance and one plan across web, desktop and API.
CZL Agent
An agent that acts: web research, writing and running code, generating files, long-term memory, reminders — and on desktop it works on your computer.
AI Apps
Ready-made tools — Imagic, background swap, 5-shot e-commerce images, multi-style images, email replies. Fill in a form, get the result.
API Gateway
An OpenAI-compatible unified endpoint with Responses / Chat Completions / Messages protocol conversion and automatic multi-upstream failover.
What a plain chat page can't do
The agent doesn't just generate text — it delivers working results.
Code generation and editing
Bind a local project folder and it reads, writes and edits code, runs builds and tests, with an expandable diff for every change; scripts run instantly in the cloud sandbox.
Word / Excel / PowerPoint and files
Generates documents, spreadsheets, slides and charts with Python in the sandbox, delivered as attachments you can keep refining in later turns.
Talk with images
Understands uploaded images, generates and edits images in the conversation including masked inpainting; on desktop it can open images on your computer, and past images are replayed across turns.
Seamless with Claude Code / Codex
Discovers the MCP servers and Skills you already set up in Claude Code and Codex, and applies your project's CLAUDE.md / AGENTS.md as rules — your dev environment works out of the box.
Message queue and steering
Messages sent mid-generation are queued and injected into the running task between tool calls (steering), so you can course-correct without waiting.
Real stop and resume
Stop aborts the upstream stream and the tool loop on the server; an interrupted answer resumes from where it stopped without redoing completed actions.
In-house Agent harness
The loop, memory, context, tools and permissions around the model, built in-house on frontier agent-engineering theory.
Harness framework
- A perceive–plan–act–observe agentic loop where the model decides the next step
- Bounded autonomy: budgets plus a forced wrap-up, so runs never spiral and always deliver
- Human-in-the-loop: high-risk actions pause for your confirmation
- Reasoning continuity: thinking stays linked to the tool calls it led to, across rounds
Four-layer RAG memory
- Working memory: live state and situational awareness of the current session
- Episodic memory: summaries of past sessions, recalled by semantic relevance
- Profile memory: a stable long-term user profile that stays in context
- Semantic memory: a vector fact store for retrieval-augmented generation, with automatic extraction, dedup and forgetting
Context engineering
- High-signal, low-noise context supply
- Prompt-cache-friendly layered assembly that keeps stable and volatile content apart
- Progressive context compaction so long tasks never lose the thread
- Progressive disclosure of tools, so a large toolset never crowds the context
Cloud code sandbox
- Isolated execution of untrusted code
- Output as delivery: execution results become downloadable files
- Closed-loop self-correction driven by execution feedback
Local tools with a bundled runtime
- Least privilege with tiered authorization
- Execution decoupled from the UI: tasks live on business entities and survive reloads and closed windows
- Batteries included: a bundled runtime that works with zero setup
- Ecosystem-native: compatible with the MCP protocol and the Skills spec
Reliability engineering
- Cooperative cancellation: stop means really stop
- Instruction hierarchy: web pages, files and tool output are data, not instructions
- Idempotency and honest state: verify when a result is unknown, never repeat side effects
- Streaming fault tolerance: pre-first-token buffering, multi-route failover and graceful shutdown
Built in-house, on frontier ideas
CZL Agent's harness, four-layer memory, context engineering, tool scheduling, chat frontend and Wails desktop app are all developed in-house by CZL; the API gateway's protocol conversion, billing and failover were redesigned by CZL as well. The design draws on the published ideas and engineering experience of OpenClaw, OpenAI Codex and Anthropic Claude Code, and keeps iterating on real production data.
- No third-party agent framework — the loop, tools and memory are built layer by layer
- Draws on Codex's state-consistency design and Claude Code's permission levels and Skills
- Stop, retry and idempotency designed after OpenAI / Anthropic agent engineering practices
Get started
The desktop app unlocks local tools, project folders, Skills and MCP; the web app is ready instantly.
CZL AI is developed and operated by CZL
About CZL →CZL focuses on two business lines: AI and international logistics.