kimiclawKimiClaw: Power your OpenClaw with Kimi K2.5 — the free, Anthropic-compatible coding model. One config change to run Claude Code, spawn coding agents, or cha...
Install via ClawdBot CLI:
clawdbot install jack-yang-ai/kimiclawGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://www.kimi.com/code/consoleAudited Apr 17, 2026 · audit v1.0
Generated Oct 6, 2026
A solo developer wants to use Claude Code without paying Anthropic API costs. By exporting ANTHROPIC_BASE_URL and ANTHROPIC_API_KEY for Kimi K2.5, they get a working Claude Code CLI experience at zero marginal cost. This is ideal for hobby projects, learning, and prototyping.
An OpenClaw user configures Kimi as the default ACP runtime so that every spawned coding agent runs on Kimi K2.5. They can delegate tasks like refactoring auth modules to JWT without manual API setup per session. This enables cheap, parallel agent workflows.
A small team builds an internal chat interface using the Anthropic-compatible /v1/messages endpoint backed by Kimi K2.5. Since the model is free, they can offer unlimited conversational assistance to employees. They use the Python stdlib example for a zero-dependency integration.
Instructors teach students how to call an Anthropic-compatible API without incurring charges. Students use the curl and Python examples against Kimi's endpoint to learn about headers, streaming SSE, and prompt formatting. The free tier removes cost barriers to practice.
A startup prototypes a multi-agent pipeline where agents spawn Claude Code subprocesses with the Kimi backend. They validate orchestration logic, prompt chaining, and task decomposition without provisioning paid API credits. Once proven, they can swap in other providers.
Kimi offers free, Anthropic-compatible coding model access to attract developers into the Kimi platform. Once integrated into workflows via OpenClaw or Claude Code, users are likely to upgrade to paid tiers for higher rate limits or premium models. The free tier acts as a low-friction acquisition channel.
Kimi positions itself as a drop-in backend for popular tools like OpenClaw and Claude Code, creating mutual value with tool vendors. Partnerships or referral arrangements can drive traffic to Kimi's console for API key creation. This expands reach without building a competing IDE or agent framework.
Even with a free coding model, Kimi monetizes through API call volume once users exceed free thresholds or require priority throughput. The Anthropic-compatible endpoint makes switching from paid Anthropic trivial, capturing cost-sensitive workloads. Complex prompts with longer timeouts and larger max_tokens drive more billable compute.
💬 Integration Tip
Simply set the provider type to "anthropic" in openclaw.json or export ANTHROPIC_BASE_URL with your sk-kimi key — no code changes needed. Remember the request model is kimi-k2.5 but responses return kimi-for-coding, and set timeouts to at least 120 seconds for complex prompts.
Scored Oct 6, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.