Now Open Source

Persistent Vector Memory
for AI Agents

One file per agent. MCP-native. Local-first.The intelligence layer for agent fleets.

$cargo install phorvec
Core Capabilities

Built for Multi-Agent Intelligence

Everything your AI agents need — from persistent memory and semantic search to fleet-scale operations and compliance.

Core Architecture

The foundation that makes phorvec different.

One File Per Agent

Each agent gets an isolated .avdb file — portable, composable, zero shared state. Move agents between machines by copying a single file.

Hybrid Search

Vector similarity + BM25 keyword search fused with Reciprocal Rank Fusion. Configurable alpha weighting, quoted-string auto-boost, debug output.

Knowledge Graphs

Automatic entity extraction with 8 built-in types. 5 graph tools for search, query, link, custom entities, and analytics.

Vector Quantization

Float32, Int8 (4x savings), and Binary (32x savings) quantization with automatic threshold transitions based on collection size.

Context & Memory

Complete lifecycle management for agent knowledge.

Context Branching

Create, switch, and merge context branches. Snapshots saved as portable .vlbrain bundles. Timeline replay with session filtering.

Context Decay & Optimization

Half-life decay with per-category formulas. Anchor exemption. Intelligent pruning keeps the most relevant context within token budgets.

Memory Consolidation

4-phase pipeline: dedup (>92% similar), compress old items, associate (create links), archive low-importance. Non-destructive — originals preserved.

Retention Policies

Active → Archived → PurgeQueue lifecycle zones. Configurable grace periods, sweep scheduling, and anchor exemption from all cleanup.

Security & Compliance

Enterprise-grade security built into every operation.

Audit Trails

Append-only JSONL logging with correlation IDs. Per-operation metadata: timestamp, type, duration, result status. Daily rotation, configurable retention.

Secret Detection

Pre-storage scanning for API keys, tokens, credentials, and PII. Configurable policies: reject (block) or redact (mask and store). Denied path patterns.

Air-Gapped Operation

Local ONNX embeddings (23MB model, zero API calls). All data on-device. .vlbrain bundles for offline transfer. No mandatory cloud sync.

Compliance Ready

SOC 2 and HIPAA-ready audit trails. PII detection. Retention policies for data lifecycle. RBAC via team sharing modes.

Multi-Agent & Teams

Coordinate fleets of agents with shared intelligence.

Team Memory

3 sharing modes: FULL (bidirectional), PROTECTED (read-only to team), ISOLATED (no sharing). Team-wide search, dispatch, and feed.

Conflict Detection

Automatic scanning for contradictory decisions across agents. Regex-based negation detection, severity levels, and dismissal — no LLM overhead. See the runnable demo in Docs.

Cross-Agent Insights (DRE)

Divergent Recombination Engine finds maximally distant compatible memories, blends them, and validates novelty. Creates knowledge no single agent had.

Geometric Failure Recovery

Computes repair vectors away from failure embeddings. Exclusion filtering rejects similar failures. Agents find new paths instead of retrying.

Enterprise Operations

Observe, govern, and manage agent fleets at scale.

Agent Health Monitoring

6 EMA-tracked metrics: coherence, contribution, prediction error, latency, success rate, and trend. Fleet-wide heatmap with threshold alerting.

Compute Governance

Per-agent token budgets with typed costs (retrieval=1, model_call=5, tool_exec=3). Reliability-based allocation. Denial counters for observability.

Agent Testing & QA

YAML test suites with IR metrics (precision, recall, F1). Baseline management, regression detection, and side-by-side benchmarking.

Skill Library

Cross-project knowledge persistence. Store and retrieve reusable error-fix pairs, patterns, and organizational knowledge bundles.

Data & RAG

Index, search, and retrieve from your entire codebase.

RAG Indexing

Index files and directories with language-aware chunking for Rust, Python, TypeScript, Go, Java, and more. .gitignore-aware, binary-safe.

140+ MCP Tools

Complete tool coverage: context, memory, search, teams, quantization, graphs, security, testing, governance, and utilities.

Query Cache & Analytics

Semantic query cache with configurable TTL. query_explain for search internals. query_profile for latency breakdowns. Full analytics dashboard.

Storage Management

Integrity verification, corruption repair, write buffer management, and LanceDB compaction. Configurable storage backends (LanceDB or Lite).

Cloud & Server

Self-hosted server with a Memory CMS dashboard, sync, and REST API.

Memory CMS Dashboard

Search, view, edit, and delete agent memories in a web UI. Auto-re-embeds on edit. Fix hallucinations in seconds — no code deploy needed.

Differential Sync

Optional cloud sync that transfers only changed memories. Vector clock conflict detection with 3-way merge resolution. Works across devices.

REST API & SDKs

Full REST API for agents, vectors, search, sync, and audit. TypeScript SDK included. API key auth with per-key rate limits and Argon2 hashing.

Docker & Air-Gapped Deploy

Ship as a single Docker container. Runs on localhost with zero login. Portable .avdb exports for air-gapped environments. No external DB required.

Quick Start

Up and Running in Minutes

Install, configure, and your agents have persistent memory.

1

Install

One command to get started.

step-1
$
2

Configure

Add to your MCP client.

step-2
3

Use

Your agents now have persistent memory.

step-3
$
See It In Action

Powerful Agent Memory in Action

Watch phorvec handle real agent workflows — from context storage to cross-agent knowledge synthesis.

Context Store

architecture / one-file-per-agent

Nexus Registry
nexus.json
code_agent
.avdb
test_agent
.avdb
review_agent
.avdb
Each .avdb file contains:
Vectors
Key-Value
Graph
Hybrid Search Flow
Query
Vector
BM25
RRF
Results
Why Phorvec

How Phorvec Compares

Purpose-built for AI agent memory, not general-purpose vector search.

FeaturePhorvecMem0CogneeInterloom
Local-first / air-gapped
One file per agent
Hybrid search (Vector + BM25 + RRF)
Knowledge graphs
Cross-agent knowledge synthesis
MCP-native
Audit trails & secret detection
Air-gapped / offline operation
Agent health monitoring
Compute governance
Geometric failure recovery
Open source core
Team memory & sharing
Agent testing & regression
Memory CMS dashboard
Differential sync & conflict resolution
REST API & TypeScript SDK

Phorvec is the only solution offering cross-agent knowledge synthesis, geometric failure recovery, and compute governance.

Pricing

Dual-Track, Developer-Friendly Pricing

Start free with the full core engine. Scale solo productivity with MCP Pro & Max. Move to per-project pricing for infrastructure-scale teams.

Prices shown in USD. Billed in ZAR at the current exchange rate.

MCP Dev-Tool Track — flat monthly

Community

Free

Full core engine for individual developers.

  • 3 projects, 3 agents per project
  • Full vector engine + hybrid search
  • Knowledge graphs
  • Context management (branching, snapshots, timeline)
  • Memory consolidation & GC
  • RAG indexing (100 files)
  • 140+ MCP tools
  • Local ONNX embeddings
  • 500 MB storage per project
  • Community support (GitHub Issues)
Get Started
Most Popular

MCP Pro

$19/mo

Solo productivity — agent testing & skill management.

  • Everything in Community, plus:
  • Unlimited projects, 10 agents per project
  • 500K vectors per agent
  • 10K context items
  • 2K RAG indexed files
  • Agent testing suite (YAML, baselines, regression)
  • Skill library (publish, sync, ingest)
  • 2 GB storage per project
  • Priority email support (24h response)
  • Early access to new features
Subscribe

MCP Max

$39/mo

Full team unlock — coordination & conflict detection.

  • Everything in MCP Pro, plus:
  • 15 agents per project
  • 1M vectors per agent
  • 25K context items, 5K RAG files
  • Team memory (FULL / PROTECTED / ISOLATED)
  • Conflict detection across agents
  • Cross-agent search & team workflows
  • Team personas & dispatch
  • 5 teams, 5 members each
  • 5 GB storage per project
Subscribe

Infrastructure Track — per-project

Team

$49/project/mo

Infrastructure-scale limits for production agent systems.

  • Everything in MCP Max, plus:
  • 10 projects (+$29/mo each additional)
  • 50 agents per project
  • 5M vectors per agent
  • 100K context items, 25K RAG files
  • 20 teams, 10 members each
  • 10 GB storage per project
  • Priority email support (24h response)
Subscribe

Enterprise

Custom

For production agent fleets at scale.

  • Everything in Team, plus:
  • Unlimited projects, agents & storage
  • Cross-agent insight discovery (DRE)
  • Geometric failure recovery
  • Compute governance (energy ledger)
  • Agent health monitoring & fleet dashboard
  • Memory CMS dashboard
  • Differential sync with conflict resolution
  • REST API with TypeScript SDK
  • Audit trails & secret detection
  • Air-gapped deployment (Docker)
  • Encryption (AES-256) + RBAC
  • GDPR / HIPAA / SOC 2 compliance
  • SLA-backed support (1h / 4h / 24h tiers)
  • Dedicated account manager
Contact Sales

Detailed Feature Comparison

FeatureCommunityMCP ProMCP MaxTeamEnterprise
Limits
Projects3UnlimitedUnlimited10 (+$29/ea)Unlimited
Agents per project3101550Unlimited
Vectors per agent50K500K1M5MUnlimited
Context items1K10K25K100KUnlimited
RAG indexed files1002K5K25KUnlimited
Teams520Unlimited
Team members510Unlimited
Storage per project500 MB2 GB5 GB10 GBUnlimited
Core Engine
Vector storage + hybrid search
Knowledge graphs
Context branching & snapshots
Memory consolidation & GC
RAG indexing (file & directory)
140+ MCP tools
Vector quantization (Float32/Int8/Binary)
Local ONNX embeddings
Agent Testing & Skills
Agent testing suite (YAML scenarios)
Baselines & regression checks
Agent benchmarking
Skill library (publish, sync, ingest)
Multi-Agent Collaboration
Team memory (FULL/PROTECTED/ISOLATED)
Conflict detection across agents
Cross-agent search
Team workflows & dispatch
Team personas & skills
Enterprise Operations
Cross-agent insight discovery (DRE)
Geometric failure recovery
Compute governance (energy ledger)
Agent health & fleet monitoring
Memory CMS dashboard
Differential sync with conflict resolution
REST API with TypeScript SDK
Org patterns & retention management
Security & Compliance
Audit trails (append-only JSONL)
Secret detection (reject/redact)
Air-gapped deployment (Docker)
Encryption at rest (AES-256)
RBAC & access control
GDPR / HIPAA / SOC 2 compliance
Support
Community support (GitHub Issues)
Priority email support (24h)
SLA-backed support (1h / 4h / 24h)
Dedicated account manager

Works With Your Stack

Phorvec integrates with any MCP-compatible client. Use it with your favorite AI development tool.

CC
Claude Code
Cu
Cursor
Ws
Windsurf
Cl
Cline
140+
MCP Tools
3
Transport Protocols
MIT
Licensed Core
<5ms
Search Latency

Give Your AI Agents
Persistent Memory

Get started in under a minute. Free and open source.

$cargo install phorvec