Problem How it works Features Integrations Pricing Sign in Start free trial
Open-source core · Beta preview

The memory layer
for AI agents

Give your agents durable, governed memory — vectors, graphs, documents, and events in one engine. Built on the open-source ProximaDB context database and the Victor agent framework; run managed in your cloud (AKS today, ECS / GKE next) with tenant isolation, usage metering, and MCP built in.

No credit card · 1 GB storage · 0.5 GB ingest · 0.1 GB embedding · 10 TB scan · 1 connector

AnvaiOps — Context Search
search >

Designed for engineering teams building with AI agents in these categories

Cloud Data PlatformsStreaming InfrastructureSearch & Observability Database VendorsDevOps & InfrastructureData Integration Developer ToolingWorkflow OrchestrationSecurity Platforms Analytics InfrastructureML & AI PlatformsAPI & Gateway Cloud Data PlatformsStreaming InfrastructureSearch & Observability Database VendorsDevOps & InfrastructureData Integration Developer ToolingWorkflow OrchestrationSecurity Platforms Analytics InfrastructureML & AI PlatformsAPI & Gateway

Your agents — and your engineers — re-solve the same problems every week

Agents start every session from zero, and teams lose weeks per quarter to tribal knowledge loss and repeated investigations — because nothing remembers what was already solved.

0%
of escalated tickets are incidents already solved before
0h
average MTTR for escalated infrastructure incidents
0mo
average ramp time for new support engineers
Days
of engineering time lost monthly to incidents already solved before
🔁

Repeated investigations

The same Kafka lag spike, Postgres connection pool exhaustion, or Kubernetes OOMKill gets investigated fresh every time it recurs — because the RCA from six months ago is buried in a comment thread nobody can find.

🧠

Tribal knowledge locked in heads

Your best engineers carry institutional knowledge no one else has. When they leave, go on vacation, or join a different team — that knowledge evaporates.

⏱️

Slow escalation paths

New engineers escalate everything because they don't know what's been solved before. Senior engineers spend hours on issues they've already fixed three times.

Operational memory in three steps

AnvaiOps connects to your existing tools and surfaces the right fix at the right moment — no workflow changes required.

01

Connect your stack

Authorize AnvaiOps to read from beta sources such as Jira, Slack, Teams, Confluence, PagerDuty, Datadog, GitHub, and ServiceNow. Access is read-only by default, with real-time webhook ingestion available where configured.

02

Index & embed

AnvaiOps ingests your historical tickets, threads, and runbooks. We extract RCAs, fixes, and owning teams using AI — then store them as a searchable knowledge index.

03

Search at incident time

When a new incident opens, engineers search in natural language. AnvaiOps returns relevant historical fixes, root causes, workarounds, and owning-team context with supporting metadata.

One memory layer, two flagship use cases

Open-source engine (ProximaDB), open-source agent framework (Victor), and a managed control plane that adds tenant isolation, governance, and metering on top.

Flagship use cases

🚨

Incident memory Beta

Your on-call agent remembers every incident. 20+ connectors (Jira, Slack, PagerDuty, Confluence…) stream your operational history into tenant-isolated hybrid search — vector + BM25 + metadata filters, one query.

🧬

Code memory 🔒 Preview

Your coding agent remembers your whole codebase. Code-property graphs + symbol-level embeddings (victor-codegraph), served to any agent over governed MCP.

Workspace & SQL GA

📓

Notebooks with ProximaSession

Jupyter-style notebooks that run inside the per-workspace pod and connect to ProximaDB through an embedded ProximaSession. Markdown + code cells, syntax-highlighted Monaco editor, cell interrupt.

⌨️

SQL bench

pgwire-compatible SQL bench wired directly to ProximaDB's federated SQL surface. Arrow result streaming, vector-aware result tables, automatic write-statement advisories.

📂

Git-backed workspace files

Every workspace gets an embedded Gitea repo: notebook history, SQL queries, scripts, and config land as commits. Branch, diff, restore — even on a free trial.

ProximaDB capabilities

Statuses below mirror ProximaDB upstream — see the pricing matrix for which tier ships each capability and RELEASE_TAXONOMY.md for the contract.

🔍

Vector search GA

Canonical vector CRUD + similarity search over REST v2 / gRPC v2. Production SLA, full semver compatibility.

Hybrid retrieval Beta

Tantivy-backed BM25 fused with vector similarity via RRF or weighted scoring. REST v1 hybrid facade today; gRPC parity in progress.

🧮

Federated SQL Beta

VECTOR_SEARCH, GRAPH_QUERY, DOCUMENT_QUERY, LOGS, METRICS table-valued functions in one SQL plane.

🕸️

ORION graph Beta

Node / edge CRUD, traversal, neighbors, shortest-path APIs. Native graph storage, not a relational fake-out.

📈

Time-series (TST) Beta

Time-stamped tables with ASOF joins, downsampling, and OHLC aggregations. Designed for high-cardinality observability and trading workloads.

⏱️

Distributed OLAP (DataFusion) Experimental

Ballista-orchestrated DataFusion MPP over cataloged Arrow snapshots. Available on Enterprise; Private Preview on Pro / Business.

Ops & cloud GA

🏢

One account, one cloud

Each account is bound to one cloud at signup (Azure, AWS, GCP). Data, workspaces, kernels, files — all in your tenancy, never traversing AnvaiOps infra.

🌐

Multi-region workspaces

One account can run workspaces in multiple regions within its cloud — workspace-scoped region picker on creation, immutable thereafter.

🔐

Entra SSO + MFA

Bring-your-own Entra tenant. Multi-tenant app reg, app roles, scoped API audience, MFA enforced at the edge.

📊

Observability + cost controls

Tiered allowances on storage / ingest / embedding / scan with per-tier soft caps. Prometheus metrics for every meter; the calculator below mirrors the runtime gates.

🚀

Flexible deployment

Managed AnvaiOps SaaS, private VPC, or fully air-gapped on-prem. Three ProximaDB transports — REST, gRPC, Arrow Flight — fit isolated environments.

💬

Use case · Incident knowledge

The original AnvaiOps workload: connect every incident to its resolution. Slack & Teams bots, 21 ITSM / observability / messaging connectors, hybrid retrieval over tickets and threads. Still a first-class use case, no longer the only one.

🧬

Use case · Code intelligence

Code-graph as a service (in private preview): index your repositories into a correlated substrate — one symbol = one graph node + one vector + one relational row. Query impact_analysis (blast radius), transitive callers, and semantic fusion_search over code.

Beta, Experimental, Private Preview

AnvaiOps mirrors ProximaDB's four-state release ladder. We never claim a status above the engine's upstream value — see ADR-0014 for the contract.

GA Supported

Production SLA, semver compatibility, full support contract. Vector CRUD & similarity search is the canonical Supported surface today.

🟦

Beta Beta

Functional and API-stable; no production SLA yet. Federated SQL, hybrid retrieval, ORION graph, observability runtime, security runtime, TST time-series, event sourcing.

🟧

Experimental Experimental

Scaffolded; partial implementation. Distributed cluster execution, full SQL parity, external tables (Iceberg / Delta / Hudi), DataFusion OLAP, Trino / Spark adapters.

🔒

Private Preview

Per-account grant for Beta or Experimental capabilities not included in your tier by default. Operator-driven for design partners; request access via the sign-up form.

P Built on ProximaDB

AnvaiOps is powered by ProximaDB — an open-source multi-model database that unifies the indexes and data planes our knowledge layer depends on. The engine is public and auditable. The intelligence layer is what we build on top.

Multi-model engine

One engine for the multiple index types modern knowledge retrieval requires — unified under a single query plane. No separate search infrastructure to operate or pay for.

🔒

Three deployment modes

Server: standalone service — cloud, on-prem, or intranet-isolated. Managed: process lifecycle handled for you. Embedded: single-binary in-process for air-gapped environments. Same engine, three topologies.

🌐

Open and auditable

Security-conscious enterprise buyers can inspect the open-source engine. No black-box indexing path, no hidden retention layer. Fork it, audit it, trust it.

Works with your existing stack

No migration, no workflow changes. AnvaiOps reads from your tools and makes them smarter.

🎯
Jira
Beta
🏢
ServiceNow
Beta
🎫
Zendesk
Beta
🆘
Freshdesk
Beta
🚨
PagerDuty
Beta
🔔
OpsGenie
Beta
📋
Linear
Beta
📊
Datadog
Beta
🔭
New Relic
Soon
🔍
Splunk
Soon
💬
Slack
Beta
💼
Microsoft Teams
Beta
📄
Confluence
Beta
📝
Notion
Beta
🗂
SharePoint
Beta
📁
Google Drive
Soon
☁️
Salesforce
Soon
🧩
HubSpot
Soon
🐙
GitHub
Beta
🦊
GitLab
Beta
📊
Smartsheet
Soon
Beta connector available now Soon on the near-term roadmap Timelines vary — ask us about a specific source.

Built for measurable impact

MTTR
Measurable reduction in time-to-resolution — tracked for every design partner
6+
Data modalities unified — vector, graph, document, relational, logs, and metrics
RO
Read-only connector posture — ingestion is designed without writes back to source systems
OSS
Auditable engine — ProximaDB's core source is public for technical review

Pay for what you search

No search infrastructure to size. Connect your support stack, choose async or sync ingest, and pay for indexed knowledge, retrieval, and outbound transfer.

Capability badges below — GA Beta Experimental 🔒 Preview — follow our release taxonomy. We never claim a status above the engine's upstream value.

🚫
No seat-based pricing
Add ten engineers to your support team — your platform bill doesn't move. Charges track compute consumption, not headcount.
Pooled by default
Lower tiers share compute while tenant data stays isolated and metered separately. Dedicated capacity is reserved for Enterprise isolation, private networking, or sustained high-volume workloads.
📥
Ingest is write-once
You pay once per GB ingested to index content. Bring your own vectors to skip managed embedding, or let AnvaiOps embed documents for you. That cost is amortized across every future retrieval that benefits from it.
🔍
Search billed on scanned data
Retrieval billing counts the gigabytes your queries physically read — not your total corpus. Two paths reduce your bill: split your corpus into multiple named indexes (route runbook queries to the runbook index, ticket queries to the ticket index) or add metadata filters (team, severity, date). Both cut scanned bytes proportionally.
Cloud platform:
ECS Fargate + S3
Estimate your monthly cost
Ingest data / month (KIU) 12 GB
500 MB100 GB+
Searchable storage (KSU) 30 GB
1 GB1 TB+
Scanned data / month (KRU) 300 TB
10 TB10 PB+
Connectors 6
121
Network scenario
Outbound data / month 10 GB
1 GB10 TB
+$49/mo Pro DR add-on
+33% on ingest — records searchable in under 2 seconds (Pro tier and above; lower tiers ingest async)
Estimates use GB-based meters. Actual KSU footprint varies with embedding model and dimension, metadata volume, chunking, data distribution, indexes, replicas, and schema. In SaaS, AnvaiOps manages the storage schema and operational layout; customers control source data, metadata, collection/index choices exposed by API, vector-import or managed-embedding options, filters, and ingest/query parameters.
Pro
~$199 / mo
Shared compute included · data meters apply
Platform: Pro · Compute: pooled AKS
Included: 30 GB storage · 300 TB scan budget · 6 connectors
Data meters: retrieval (GB scanned) · storage (GB-month) · ingest/indexing (GB) · embedding (GB) · network egress
Get exact quote
Free Trial
$0 / 30 days
Evaluate the workflow with capped usage and shared compute. No production SLA — built for fast proof-of-value before paid rollout.
  • 1 GB indexed storage included
  • 500 MB ingest/mo (write-once)
  • 100 MB managed embedding included
  • 10 TB/mo scan budget
  • 1 connector
  • Shared cluster — single region
  • Standard retrieval quality
  • Community docs + Slack forum
  • Expires after 30 days
ProximaDB capabilities
  • Vector Search GA
  • Hybrid Retrieval Beta
  • Federated SQL Beta
  • Document CRUD Beta
  • ORION Graph Beta
  • Observability Runtime Beta
  • Security Runtime Beta
  • Time Series (TST) Experimental
  • Event Sourcing Experimental
  • Distributed Compute Experimental
  • DataFusion OLAP Experimental
  • Code Embeddings Experimental
Start trial
Team
$19+ / mo
Self-serve on-ramp for solo engineers and small teams. Real connectors, real allowance, real workflow — at a try-it-yourself price.
  • 3 GB indexed storage included
  • 1.5 GB ingest/mo (write-once)
  • 300 MB managed embedding included
  • 30 TB/mo scan budget
  • 2 connectors
  • Async ingest only
  • Standard retrieval quality
  • Pooled cluster — single region
  • Self-serve docs + community forum
ProximaDB capabilities
  • Vector Search GA
  • Hybrid Retrieval Beta
  • Federated SQL Beta
  • Document CRUD Beta
  • ORION Graph Beta 🔒 Preview
  • Observability Runtime Beta 🔒 Preview
  • Security Runtime Beta
  • Time Series (TST) Experimental 🔒 Preview
  • Event Sourcing Experimental
  • Distributed Compute Experimental
  • DataFusion OLAP Experimental
  • Code Embeddings Experimental
Choose Team
Business
$599+ / mo
Production workflow at BU scale. All 21 connectors, real-time webhook ingestion, retrieval analytics, NBD response target.
  • 100 GB indexed storage included
  • 50 GB ingest/mo (write-once)
  • 10 GB managed embedding included
  • 1 PB (1,000 TB)/mo scan budget
  • All 21 connectors
  • Async + sync ingest ($8.25/GB sync embedding overage)
  • All 21 connectors
  • Enhanced retrieval quality (multilingual)
  • Pooled cluster — single region
  • DR add-on available (+$99/mo)
  • Real-time webhook ingestion (Slack + Teams)
  • Slack bot (/anvai command) + Teams bot
  • MTTR + retrieval analytics
  • Dedicated Slack support channel
  • Next-business-day response target
ProximaDB capabilities
  • Vector Search GA
  • Hybrid Retrieval Beta
  • Federated SQL Beta
  • Document CRUD Beta
  • ORION Graph Beta
  • Observability Runtime Beta
  • Security Runtime Beta
  • Time Series (TST) Experimental
  • Event Sourcing Experimental
  • Distributed Compute Experimental 🔒 Preview
  • DataFusion OLAP Experimental 🔒 Preview
  • Code Embeddings Experimental 🔒 Preview
Get started
Enterprise
$1,500+ / mo
Dedicated capacity for higher-scale or regulated environments. Private VPC, SSO, Managed Success, custom SLA.
  • 250 GB indexed storage included
  • 125 GB ingest/mo (write-once)
  • 25 GB managed embedding included
  • 2 PB (2,500 TB)/mo scan budget
  • All 21 connectors
  • Async + sync ingest — sync SLA negotiable
  • Premium retrieval quality · bring-your-own-model available
  • All 21 connectors
  • Dedicated AKS / EKS cluster
  • Cross-region DR included by default
  • Private VPC / intranet deployment
  • SSO (Okta, Azure AD)
  • Audit logs + RBAC
  • Managed Success included
  • Monthly optimization + retrieval quality reviews
  • Custom SLA
ProximaDB capabilities
  • Vector Search GA
  • Hybrid Retrieval Beta
  • Federated SQL Beta
  • Document CRUD Beta
  • ORION Graph Beta
  • Observability Runtime Beta
  • Security Runtime Beta
  • Time Series (TST) Experimental
  • Event Sourcing Experimental
  • Distributed Compute Experimental
  • DataFusion OLAP Experimental
  • Code Embeddings Experimental 🔒 Preview
Contact us
Consumption meters
Plan fees include shared compute and tier-appropriate support. Tenant-specific storage, search I/O, ingest, and outbound data are metered after included allowances.
MeterUnitRateWhat drives it
RetrievalPrimary per TB scanned $0.02 You're billed for the GB of corpus your queries physically read — not the total size of your knowledge base. Intelligent indexing skips blocks that don't match your query filters before retrieval runs. Example: 5,000 queries/mo, 2 GB corpus, 40% scan fraction = 4,000 GB scanned/mo = 4 TB scanned = $0.08/mo. Tighten further by splitting your corpus into multiple named indexes (route runbook queries to your runbook index only) or adding metadata filters (team, severity, date) — both physically reduce scanned bytes. Team includes 30 TB/mo scan budget; Pro includes 300 TB/mo scan budget; Business includes 1 PB (1,000 TB)/mo scan budget.
Storage per GB-month stored $0.25 Persistent searchable incident knowledge — indexes, metadata, and replicas in the primary region. Cross-region DR replication is billed only when selected or included by tier. Billed against the actual storage footprint so a 200KB Confluence page is billed fairly against a 20KB Jira ticket. This is managed searchable knowledge, not raw object storage.
Ingest / IndexingKIU per GB indexed $0.75
BYO vectors or document payload
Write, validate, index, and compact customer-supplied content or vectors. v1/v2 vector batch APIs accept embedded vectors; v3 documents can also carry vectors through ProximaDB.Included ingest scales by tier from 1.5 GB on Team to 50 GB on Business. Ongoing retention is covered by the storage meter.
Managed EmbeddingKEU per GB embedded $5.00
$8.25 sync · BGE -25% · large $26.25 / $52.50
Optional embedding performed by AnvaiOps when you send documents without vectors. Async uses batched OpenAI text-embedding-3-small by default; hosted BGE models are available at 25% below the comparable OpenAI lane. Sync is available on Pro and above for immediate searchability. Small managed embedding allowances are included by tier. Native document ingest is $5.75/GB async when KIU + OpenAI KEU are used together, or $4.50/GB with hosted BGE. OpenAI text-embedding-3-large is available as a premium managed embedding option. Teams that bring precomputed vectors skip KEU.
Extra Connector per connector / mo $39 Beyond the included connector count. Each adds a scheduled polling worker (every 2–12 hours depending on source). Real-time Slack and Teams webhook ingestion is included in the platform fee — not a per-connector charge. All connectors included on Enterprise. BYOC available for regulated or on-prem sources.
Network Egress per billable GB cloud nominal rate Outbound transfer for result exports, cross-cloud access, on-prem access, and selected DR replication. Provider free allowances and same-cloud paths are reflected in the calculator. Network transfer is tenant-specific even when compute is pooled.

Introductory rates use pooled compute to keep entry pricing low. Tenant data remains isolated and is billed through simple GB-based meters: retrieval (GB scanned), ingest/indexing (GB indexed), managed embedding (GB embedded), and storage (GB-month). No pass-through cloud bills. Dedicated Enterprise deployment starts at +$1,500/mo when isolation, private networking, or customer-controlled cloud is required.

🍾

We run AnvaiOps to support you

Our support team uses AnvaiOps the same way your engineers will. Every ticket we resolve for a customer gets indexed back into our own instance, so our institutional knowledge compounds with each interaction. That lets us include support in the platform fee while keeping response quality high.

Become a design partner

Start with a 30-day trial — 1 GB indexed storage, 0.5 GB ingest, 0.1 GB managed embedding, 10 TB scan budget, and one connector. If your agents (or your engineers) keep re-solving the same problems, we'll work with you directly and move you to a paid plan after the trial.

We respond promptly — typically within one business day. No spam, no sales cadence — just a real conversation.