AI coding IDEs, coding agents, repository assistants and software engineering automation tools from Chinese teams.
CodeFlicker / StreamLake
CodeFlicker belongs in AI Coding because its public product surface is explicitly built around code editing, coding agents, IDE extensions, CLI and development workflows.
Best fit · Developers and engineering teams evaluating a China-linked AI coding suite across desktop IDE, plugins, terminal CLI and cloud agents.
Coverage · 100/100
Qoder
Cloud Agents has an independent API, console, runtime object model, sandbox, session lifecycle and security surface, making it a distinct developer platform rather than a Qoder IDE feature.
Best fit · Engineering teams embedding long-running coding, review, refactoring, testing and batch-agent workflows into backend services without operating the runtime themselves.
Coverage · 100/100 · backfill: pricing
Qoder
Qoder CLI has its own cross-platform installer, terminal interface, headless contract, memory, GitHub automation, Cloud Mode and SDKs, so it warrants a dedicated profile separate from Qoder Desktop and Cloud Agents.
Best fit · Developers and platform teams that want one coding agent across interactive terminals, headless scripts, GitHub workflows, isolated worktrees, cloud Sessions and embedded SDK integrations.
Coverage · 100/100
Qoder
Qoder Mobile has dedicated native and web clients, app-store availability rules, push notifications and remote/cloud task controls, giving it a distinct control-surface boundary from Desktop, CLI and Cloud Agents.
Best fit · Qoder users who need to monitor long-running coding tasks, clear approvals and launch GitHub-backed cloud work while commuting or away from their development machine.
Coverage · 100/100
ByteDance / Volcano Engine
TRAE is a coding IDE and agent product rather than a generic chat assistant, so the new AI Coding category is the right fit.
Best fit · Developers comparing Chinese AI IDEs, builder-style coding workflows and task-level AI software engineering agents.
Coverage · 100/100
Tencent Cloud
CodeBuddy belongs in AI Coding because it is a full software-engineering assistant rather than a general chat product or raw model API.
Best fit · Developers and teams evaluating Tencent-backed AI coding IDE, plugin and CLI workflows with cloud deployment and agent automation.
Coverage · 100/100
Alibaba Cloud
Qwen Code is a distinct AI coding product and should be tracked separately from Qwen Cloud models or token plans.
Best fit · Developers who want a terminal coding agent for Qwen models and prefer open-source tooling with editor integrations.
Coverage · 100/100
OpenRouter
Owl Alpha belongs in AI Coding because OpenRouter explicitly positions it for agentic workloads, code generation and compatibility with mainstream coding-agent tools.
Best fit · Developers testing long-context coding agents, tool-heavy automation and Claude Code or OpenClaw workflows without model token charges.
Coverage · 100/100
DeepReinforce
Ornith 1.0 belongs in AI Coding because its public model cards and collection position it around agentic coding benchmarks and coding-agent deployment.
Best fit · Teams evaluating open agentic-coding models for self-hosted coding agents, terminal automation, SWE-Bench workflows and long-context tool use.
Coverage · 100/100
Moonshot AI
The public repository confirms that Kimi Code is an installable MIT-licensed agent platform, while the K2.7 Code resource confirms its current default hosted coding model.
Best fit · Developers who want a fast open terminal agent with multimodal coding context, parallel subagents and editor integration.
Coverage · 100/100
Zhipu AI
GLM Coding Plan has its own prices, endpoints, supported-tool policy, quotas and MCP allowances, so it should be tracked separately from the BigModel API and z.ai assistant.
Best fit · Developers who want predictable GLM usage for supported coding agents, repository work and MCP-assisted research.
Coverage · 100/100
Zhipu AI
ZCode is a complete development environment with its own agent, task workspace, Git, terminal and remote-control surfaces, so it is distinct from the GLM model API and Coding Plan subscription.
Best fit · Developers managing long-running repository tasks, parallel agents and Git-heavy workflows that need remote supervision.
Coverage · 100/100
Ant Group
Ring has a coding-agent and tool-use profile that fits AI Coding better than the generic Ant Ling entry.
Best fit · Teams comparing Chinese reasoning and coding-agent models for tool orchestration, repository work and long-horizon autonomous execution.
Coverage · 100/100
MiniMax
Token Plan is a distinct subscription and routing path with its own keys, quotas, integrations and traffic rules, so it should be tracked separately from the general MiniMax API Platform.
Best fit · Individual developers running frequent MiniMax-powered coding agents, long-context repository tasks and multimodal workflows.
Coverage · 100/100
ByteDance / Volcano Engine
Coding Plan has its own subscription tiers, quota behavior, tool integrations and model-routing surface, so it should be tracked separately from the general BytePlus or Volcano Engine ModelArk API.
Best fit · Developers who want one BytePlus subscription for switching among several Chinese coding models inside mainstream agents and IDE tools.
Coverage · 100/100 · backfill: sources
ByteDance / Volcano Engine
Seed GR-3 belongs in LLM & API because it is a model-family signal on the official Seed page, not a standalone application.
Best fit · Teams tracking Chinese robotics foundation models and long-horizon vision-language-action systems.
Coverage · 98/100 · backfill: sources
ByteDance / Volcano Engine
Seed GR-RL belongs in LLM & API because it is a robotics-model family entry on the Seed page rather than a consumer product.
Best fit · Teams evaluating robotics reinforcement-learning approaches inside ByteDance Seed's public model roadmap.
Coverage · 98/100 · backfill: sources
iFlytek
Spark is strategically important for speech and vertical applications, while overseas consumer readiness remains limited.
Best fit · Teams evaluating Chinese speech AI, education, healthcare or voice-heavy assistant workflows.
Coverage · 98/100 · backfill: sources
StepFun
Step Plan deserves a separate AI Coding entry because it is toolchain- and agent-workflow specific, not just a model API.
Best fit · Developers who want a predictable subscription quota for coding agents, long-context repository work and tool-calling automation.
Coverage · 100/100
Xiaomi MiMo
MiMoCode is a distinct coding-agent product rather than another MiMo model card: it packages memory, orchestration, tools and provider routing into an installable open-source CLI.
Best fit · Developers who want an open terminal coding agent focused on durable project memory, long-running tasks and configurable model providers.
Coverage · 100/100