# Vapora page — Intelligent Development Orchestration Platform

# Hero
vapora-badge = ✅ v1.2.0 | 620 Tests | 100% Pass Rate
vapora-tagline = Evaporate complexity
vapora-page-title = Development Flows When Teams and AI Orchestrate
vapora-page-subtitle = Specialized agents orchestrate pipelines for design, implementation, testing, documentation and deployment. Agents learn from history and optimize costs automatically. 100% self-hosted on Kubernetes — no SaaS, complete control.

# Architecture diagram
vapora-architecture-title = Architecture Overview

# Problems section
vapora-problems-title = The 4 Problems It Solves
vapora-problem-1-title = Context Switching
vapora-problem-1-desc = Developers jump between tools constantly. Vapora unifies everything in one intelligent system where context flows.
vapora-problem-2-title = Knowledge Fragmentation
vapora-problem-2-desc = Decisions lost in threads, code scattered, docs unmaintained. RLM with hybrid search (BM25 + semantic) and chunking makes knowledge discoverable even in 100k+ token documents.
vapora-problem-3-title = Manual Coordination
vapora-problem-3-desc = Orchestrating code review, testing, documentation and deployment manually creates bottlenecks. Multi-agent workflows solve this.
vapora-problem-4-title = Dev-Ops Friction
vapora-problem-4-desc = Handoffs between developers and operations lack visibility and context. Vapora maintains unified deployment readiness.

# Features section
vapora-features-title = How It Works
vapora-feat-agents-title = Specialized Agents
vapora-feat-agents-desc = 71 tests verify agent orchestration, learning profiles, and task assignment. Agents track expertise per task type with 7-day recency bias (3× weight). Real SurrealDB persistence + NATS coordination.
vapora-feat-orchestration-title = Intelligent Orchestration
vapora-feat-orchestration-desc = 53 tests verify multi-provider routing (Claude, OpenAI, Gemini, Ollama), per-role budget limits, cost tracking, and automatic fallback chains. Swarm coordination with load-balanced assignment.
vapora-feat-rlm-title = Recursive Language Models (RLM)
vapora-feat-rlm-desc = Process 100k+ token documents without context limits. Hybrid search combines BM25 (keywords) + semantic embeddings via RRF fusion. Intelligent chunking (Fixed/Semantic/Code) with SurrealDB persistence.
vapora-feat-a2a-title = Agent-to-Agent (A2A) Protocol
vapora-feat-a2a-desc = Distributed agent coordination with task dispatch, status tracking, and result collection. NATS messaging for async completion. Exponential backoff retry with circuit breaker. 12 integration tests.
vapora-feat-knowledge-title = Knowledge Graph
vapora-feat-knowledge-desc = Temporal execution history with causal relationships. Learning curves from daily windowed aggregations. Similarity search recommends solutions from past tasks. 20 tests verify graph persistence and learning profiles.
vapora-feat-nats-title = NATS JetStream
vapora-feat-nats-desc = Reliable message delivery for agent coordination. JetStream streams for workflow events, task completion, and status updates. Graceful fallback when NATS unavailable.
vapora-feat-surrealdb-title = SurrealDB
vapora-feat-surrealdb-desc = Multi-model database with graph capabilities. Multi-tenant scopes for workspace isolation. Native graph relations for Knowledge Graph. All queries use parameterized bindings. SCHEMAFULL tables with explicit indexes.
vapora-feat-api-title = Backend API & MCP Connectors
vapora-feat-api-desc = 40+ REST endpoints (projects, tasks, agents, workflows, swarm). WebSocket real-time updates. MCP gateway for external tool integration. Prometheus metrics. 161 tests verify API correctness.
vapora-feat-webhooks-title = Webhook Notifications
vapora-feat-webhooks-desc = Real-time alerts to Slack, Discord, and Telegram — no vendor SDKs. ${VAR} secret resolution built into ChannelRegistry. Fire-and-forget hooks on task completion, proposal approval, and workflow lifecycle events.
vapora-feat-capabilities-title = Capability Packages
vapora-feat-capabilities-desc = Domain-optimized agent bundles — system prompt, preferred LLM, task types, and MCP tools pre-configured per role. Three built-ins (code-reviewer, doc-generator, pr-monitor) at startup. TOML overrides to swap model or prompt without code changes. 22 tests.

# Tech stack
vapora-tech-stack-title = Technology Stack

# Agents
vapora-agents-title = Available Agents
vapora-agent-architect-role = System design
vapora-agent-developer-role = Code implementation
vapora-agent-reviewer-role = Quality assurance
vapora-agent-tester-role = Tests & benchmarks
vapora-agent-documenter-role = Documentation
vapora-agent-marketer-role = Marketing content
vapora-agent-presenter-role = Presentations
vapora-agent-devops-role = CI/CD deployment
vapora-agent-monitor-role = Health & alerting
vapora-agent-security-role = Audit & compliance
vapora-agent-pm-role = Roadmap tracking
vapora-agent-decisionmaker-role = Conflict resolution

# CTA
vapora-cta-title = Ready for intelligent orchestration?
vapora-cta-subtitle = Built with Rust 🦀 | Open Source | Self-Hosted
vapora-cta-explore = Explore Git Repo
vapora-cta-visit = Visit vapora.dev