Features
RL-trained code search subagent
Isolated context window for search results
~3.8 steps average to find code
8 parallel tool calls per turn
Reduces context rot by 70%
Speeds coding tasks by 40%
MCP integration for Claude Code, Codex, OpenCode
OpenAI-compatible SDK (TypeScript, Python)
Auto-detects and configures editors (Claude Code, Cursor, Codex, VS Code)
One-command setup via npx
Search across entire codebase with natural language
Zero search reruns due to context overflow
Trained exclusively on production code for maintainability
Supports COBOL, Fortran, Verilog, Rust, SQL
Terminal-native CLI with local-to-remote execution
External tool access via MCP
Multi-agent orchestration via Cosine Swarm
Cosine Cloud for parallel tasks and shared projects
Scout model: on-device, post-trained from Devstral 123B
Outpost model: 59.3% on Niche-Bench, post-trained from Kimi K2.6
Frontier model: coming soon for frontier-scale reasoning
Air-gapped deployment option
Managed single-tenant cloud
Credit-based usage metering
CLI built-in search (v1.16)
Lumen Sovereign coalition for sovereign AI
