kimi-code
Kimi Code CLI — The Starting Point for Next-Gen Agents
Migrate from the legacy Node-SDK to the new Klient SDK architecture. Learn to replace RPC calls, initialize transport-agnostic, and adopt the v2 engine bootstrap pattern for seamless integration.
How Kimi Code's Wire Vocabulary System Handles Model Definitions and Cross‑ReducersDiscover how Kimi Code's wire vocabulary system uses defineModel and defineReducer for type-safe state containers and automatic updates. Learn about its dependency graph and cycle detection.
How Kimi-Code's Swarm Feature Enables Parallel Subagent ExecutionDiscover how Kimi-Code's swarm feature enables parallel subagent execution with its metadata-driven coordination and concurrent task dispatching for efficient workflows.
How to Debug Session Issues Using the Kimi Code Server Debug EndpointsDebug Kimi Code session issues effectively using kap-server debug endpoints. Inspect registries, invoke methods, and capture business state for faster problem resolution.
How Kosong's Provider Abstraction Layer Handles Multiple LLM Providers in Kimi CodeDiscover how Kosong's provider abstraction layer unifies multiple LLM backends via a single ChatProvider interface and provider-specific adapters, simplifying integration within Kimi Code.
Tree-Sitter-Bash Parser API: How to Use the MoonshotAI Parser SafelyExplore the Tree Sitter Bash parser API from MoonshotAI. Learn how to safely parse Bash code in TypeScript with the @moonshot-ai/tree-sitter-bash package. Discover best practices for secure usage.
How the MCP OAuth Flow Works for Authenticating External Servers in Kimi CodeUnderstand the MCP OAuth flow in Kimi Code. Learn how it securely authenticates external servers using temporary localhost servers and persistent disk storage for efficient token management.
How to Configure the Kimi-Code CLI Using Config Files and Environment VariablesLearn to configure the Kimi-Code CLI easily with config files or environment variables. Customize your settings for seamless integration with MoonshotAI.
How the Kimi-Code Telemetry Event System Works: Architecture, Client API, and Naming ConventionsExplore the kimi-code telemetry event system. Learn about its compile-time registry, TypeScript naming conventions, singleton client, and pluggable sinks for efficient event delivery.
How to Create Custom Features Using the `Feature` Base Class in agent-core-v2Learn to build custom features in agent-core-v2 by extending the Feature base class. Implement setup() for automatic discovery and management by FeatureManagerService.
How MiniDB Handles Snapshot and WAL Persistence in Kimi Code's Embedded JSON Document StoreDiscover how MiniDB ensures data durability and fast recovery in Kimi Code's embedded JSON store using WAL and snapshot persistence. Learn about its efficient design.
Agent-Core v1 vs v2 Architecture in Kimi Code: A Complete Technical ComparisonCompare Kimi Code's agent-core-v1 and agent-core-v2 architectures. Discover agent-core-v2s scoped DI engine and four lifecycle layers for production servers.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →