Features
300-agent swarm orchestration
Long-horizon coding (12+ hour tasks)
End-to-end coding across Rust, Go, Python
Autonomous code optimization and refactoring
Visual agent with Python tool use
Deep research with multi-format reports
AI website builder from ideas, images, videos
AI slide generation from text, docs, images
AI sheet agent with formulas, pivots, charts
AI document creation, conversion, review
Agent swarm coordination with OpenClaw and Hermes
Terminal and IDE integration via Kimi Code
Kimi Claw for 24/7 AI agents
API access for custom integrations
Open-source model weights
Laguna XS.2 model (33B params, 3B active, on-device)
Laguna M.1 model (225B params, 23B active, via API)
256K context length for multi-step reasoning
Multi-agent orchestration with planning and tool use
Sandboxed agent execution environments
Developer surfaces: agents, TUI, IDE extensions, binaries
Custom foundation models deployed on-prem or in VPC
Data connectors to repos, databases, data warehouses
Role-based access control for humans and agents
Executive-grade governance and auditability
On-prem, VPC, and workstation deployment (defense only)
Forward Deployed Research Engineers embed with teams
Real-time observability with end-to-end traces
Air-gapped network support
Open-weight model weights available
