Evaporate complexity
✅ v1.2.0 | 620 Tests | 100% Pass RateDevelopment Flows When Teams and AI Orchestrate
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 Overview
The 4 Problems It Solves
Context Switching
Developers jump between tools constantly. Vapora unifies everything in one intelligent system where context flows.
Knowledge Fragmentation
Decisions lost in threads, code scattered, docs unmaintained. RLM with hybrid search (BM25 + semantic) and chunking makes knowledge discoverable even in 100k+ token documents.
Manual Coordination
Orchestrating code review, testing, documentation and deployment manually creates bottlenecks. Multi-agent workflows solve this.
Dev-Ops Friction
Handoffs between developers and operations lack visibility and context. Vapora maintains unified deployment readiness.
How It Works
Specialized Agents
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.
Intelligent Orchestration
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.
Recursive Language Models (RLM)
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.
Agent-to-Agent (A2A) Protocol
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.
Knowledge Graph
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.
NATS JetStream
Reliable message delivery for agent coordination. JetStream streams for workflow events, task completion, and status updates. Graceful fallback when NATS unavailable.
SurrealDB
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.
Backend API & MCP Connectors
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.
Webhook Notifications
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.
Capability Packages
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.
Technology Stack
Available Agents
Ready for intelligent orchestration?
Built with Rust 🦀 | Open Source | Self-Hosted