Yes. The Community tier gives you the full core engine — vector storage, hybrid search, knowledge graphs, context management, memory consolidation, RAG indexing, and 140+ MCP tools. It supports up to 3 projects with 3 agents each. The core library is MIT licensed and the MCP server is BSL 1.1 — free for internal production use.

Phorvec uses dual-track pricing. The MCP Dev-Tool track (Community, MCP Pro, MCP Max) is flat monthly pricing for individual developers and small teams. The Infrastructure track (Team, Enterprise) is per-project pricing for production agent systems that need higher scale limits.

MCP Pro ($19/mo) unlocks solo productivity features: agent testing suites with YAML scenarios, baselines, and regression checks, plus the skill library for publishing, syncing, and ingesting cross-project patterns. You also get unlimited projects, 10 agents per project, and 500K vectors per agent.

MCP Max ($39/mo) unlocks full team coordination: team memory with FULL, PROTECTED, and ISOLATED sharing modes, conflict detection across agents, cross-agent search, team workflows and dispatch, and team personas. You get 15 agents per project, 1M vectors, and up to 5 teams with 5 members each.

Move to Team ($49/project/mo) when you need infrastructure-scale limits: 50 agents per project, 5M vectors per agent, 20 teams with 10 members each, and 10 GB storage. It's designed for production systems that have outgrown the MCP dev-tool limits. Additional projects are $29/mo each.

Enterprise adds fleet-scale operations: the Divergent Recombination Engine for cross-agent insight discovery, geometric failure recovery, compute governance with energy ledger, health monitoring with fleet dashboards, Memory CMS dashboard, differential sync, REST API with TypeScript SDK, audit trails, secret detection, air-gapped Docker deployment, encryption (AES-256), RBAC, compliance certifications (GDPR/HIPAA/SOC 2), and SLA-backed support with a dedicated account manager.

A project is a directory where phorvec stores agent data — identified by a nexus.json file. If you have a monorepo, that's one project. If you have separate repos for separate services, each is a project. Community allows 3 projects, MCP Pro and MCP Max are unlimited, and Team starts at 10.

The MCP Dev-Tool track (Pro/Max) is flat monthly because it's individual tooling. The Infrastructure track (Team/Enterprise) is per-project because the value scales with how many agent systems you run, not how many humans are on your team — adding a new developer costs nothing.

Yes. Phorvec uses local ONNX Runtime for embeddings — no API calls, no data leaves your machine. You can transfer agent knowledge via .vlbrain bundles (file-based) without any network connectivity. The embedding model downloads once (23MB) and is cached locally.

Phorvec works with any MCP-compatible client including Claude Code, Cursor, Windsurf, Cline, and more. It supports stdio, SSE, and HTTP transport protocols.

Prices are displayed in USD for international clarity, but payments are processed in South African Rand (ZAR) at the prevailing exchange rate at the time of purchase. Your bank may apply a small currency conversion fee.

Yes. All paid tiers are available at a 20% discount when billed annually. Contact us for Enterprise annual pricing.

Unlike Pinecone, Weaviate, or Qdrant, phorvec is purpose-built for AI agent memory — not general-purpose vector search. It's local-first, one-file-per-agent, and includes agent-specific features like team memory, conflict detection, knowledge synthesis, audit trails, and compute governance that general vector DBs don't offer.