How it works Features Compare Deployment Pricing Docs Sign up →
AI-native log analytics

Log analytics and
observability you
actually own.

Ask your logs questions in plain English. Get automatic root cause analysis the moment an alert fires. Run every AI feature on a local model inside your own network. One self-contained appliance — no SaaS, no data leaving the building.

keel.internal / log-search
"Show all errors from auth-service in the last hour"
↵ Ask
Generated query
SELECT timestamp, severity, service, message
FROM logs
WHERE service = 'auth-service'
  AND severity = 'ERROR'
  AND timestamp >= now() - INTERVAL 1 HOUR
ORDER BY timestamp DESC
127 results  ·  38ms
14:47:03 ERROR JWT validation failed — token expired for user_id 8821
14:46:51 ERROR Redis connection timeout after 5000ms — retrying (1/3)
14:46:48 WARN Rate limit threshold reached — 429 returned to 10.0.4.12
14:46:39 ERROR DB pool exhausted — 50/50 connections in use
Built for
Banking & Finance Government Healthcare Defence Critical Infrastructure Air-gapped Environments
The problem

Three reasons teams are moving
off their current log platform.

Whether it's the bill, the operational burden, or a compliance requirement — most teams are stuck with a tool that wasn't built for how they actually work.

💸

Cost that scales with your data

Volume-based licensing means your bill grows every time your infrastructure does. Mid-market teams regularly spend hundreds of thousands per year just on log ingestion — before any analytics or AI features.

⚙️

A platform that needs its own engineer

Self-managed open-source stacks were not designed to run themselves. Tuning, scaling, upgrades, and incident recovery often consume one or more full-time engineers to keep the observability platform alive.

🔒

Data that can't leave the network

For regulated industries, sending logs to a cloud platform is a compliance failure before any investigation begins. The answer can't be "don't use AI" — it has to be an on-prem platform that has AI built in.

Why Keel

Everything you need.
Nothing you have to manage.

Keel is a self-contained appliance — not a collection of open-source tools to wire together. Import the VM image, complete the setup wizard, and start querying your logs.

01 — Cost

A fraction of what you pay today

Keel is priced per appliance, not per gigabyte of ingest. As your log volume grows, your Keel bill stays flat. Teams migrating from volume-based platforms typically see 80–90% cost reductions.

02 — Sovereignty

Your data never leaves your network

Keel generates all secrets on first boot and requires no phone-home to operate. Logs, queries, and AI inference all stay inside your perimeter — including in fully air-gapped environments.

03 — AI

Three AI capabilities. All running inside your network.

Search in plain English. Ask any question and Keel translates it into a query and runs it — or write the query directly. Both in the same window.

Automatic root cause analysis. When an alert fires, Keel investigates automatically — it searches the surrounding logs, reads your runbooks, and delivers a root cause in plain English to Slack or PagerDuty. No analyst needed.

Fully on-prem AI. Every AI feature runs on a local model inside your network. No API calls to external services — not even for RCA. For regulated teams, this is the only viable option.

How it works

Ingest. Store. Ask. Act.

Four steps from raw log data to answered questions and resolved incidents.

📥

Ingest

Your logs arrive over open standards — no proprietary forwarder required.

OTLP gRPC OTLP HTTP Syslog Fluentd Cloud connectors
💾

Store

Logs are compressed and indexed for fast, cost-efficient search at any retention length.

High compression Fast search Configurable retention

Ask

Search in plain English or write a query directly — results in milliseconds either way.

Natural language Direct SQL RAG assistant
🔔

Act

Alert fires → Keel automatically investigates → root cause delivered to your team in plain English. No manual triage required.

Auto RCA Slack PagerDuty Email Webhook
Features

One appliance. Every capability.

Everything ships in the VM image — no add-ons, no separate clusters to run, no plugins to maintain.

Automatic root cause analysis

The moment an alert fires, Keel automatically investigates — it searches the surrounding logs, reads your uploaded runbooks and infrastructure docs, and delivers a root cause analysis in plain English to Slack, PagerDuty, or email. No analyst required. No manual triage.

Alert-triggeredReads your runbooksPlain English outputAuto-delivered

Natural language search

Ask your logs any question — "show all errors from the payment service in the last two hours" — and Keel translates it into a query and runs it instantly. Power users can also write queries directly. Both modes live in the same window.

Plain EnglishDirect queryMillisecond results
📚

Knowledge base & assistant

Upload your runbooks, architecture diagrams, and SOPs. Keel's AI reads them automatically during every RCA — so the root cause analysis references your own documentation, not generic advice. The same knowledge base powers a conversational assistant you can query directly at any time.

RunbooksArchitecture docsAuto-used in RCAConversational assistant
📥

OpenTelemetry-native ingest

OTLP gRPC and HTTP, syslog, and Fluentd out of the box — plus connectors for AWS, Azure, GCP, Datadog, Grafana, Prometheus, PagerDuty, and generic webhooks. No proprietary forwarder lock-in.

OTLPSyslogFluentdCloud connectors
🔄

Log pipelines

Configurable processing rules per source — parse, filter, enrich, and route logs before they're stored. Per-source isolation means adding or removing a source doesn't disrupt other ingest streams.

ParseFilterEnrichPer-source isolation
🔔

Alerting & incidents

Define alert rules on your log data. Firing alerts create incidents with a full timeline and linked log entries. Notifications route to Slack, PagerDuty, email, SNMP traps, or any webhook.

Alert rulesIncident trackerMulti-channel

High availability

3-node HA cluster — if a node fails, the remaining nodes continue serving ingest and search without manual intervention. Designed for stability in regulated environments where the observability platform itself cannot go down.

Active/passiveVirtual IP failoverAuto switchover
🔐

Security & access control

Role-based access control with teams and roles. SAML/OIDC single sign-on, multi-factor authentication, full audit logging, and TLS/SSL management — all managed from the dashboard.

RBACSAML / OIDCMFAAudit log
🖥️

Appliance operations

Guided first-run setup wizard, in-place upgrades and patching, backup and restore, network and storage administration — all from the web dashboard. No SSH required for routine operations.

Setup wizardIn-place upgradesBackup & restore
🔒

Fully on-prem AI — no external calls

Every AI feature in Keel — natural language search, automatic RCA, and the knowledge assistant — can run on a local LLM hosted entirely within your network. Connect any OpenAI-compatible endpoint: Ollama, vLLM, or any self-hosted model. For regulated teams, this means no AI data ever leaves the building — not even a single API call to an external service.

OllamavLLMAny local modelZero external callsAir-gapped ready
How it compares

The honest comparison.

Keel wins on cost and data sovereignty. There are areas where larger, mature platforms still lead — we'd rather you know that upfront than find out during a POC.

Capability Keel Splunk Elastic / ELK Datadog OSS ClickHouse tools
On-prem / air-gap ready ✓ Built for it ⚠ Heavy setup ✓ Yes ✗ SaaS only ✓ Yes
Cost per TB of logs ✓ Low ✗ High ⚠ Storage-heavy ✗ High ✓ Low
Packaged appliance + HA ✓ One VM image ⚠ Multi-tier ⚠ DIY n/a ⚠ DIY
AI / natural-language query ✓ Native ⚠ Add-on ⚠ Limited ⚠ Add-on ⚠ Varies
OpenTelemetry-native ✓ Yes ⚠ Partial ✓ Yes ✓ Yes ✓ Yes
SSO / RBAC / audit ✓ Yes ✓ Yes ✓ Yes ✓ Yes ⚠ Varies

⚠ = available with caveats or additional cost  ·  ✗ = not available

Deployment

Ships as a VM image.
Runs anywhere you run VMs.

Keel is delivered as a pre-configured appliance image for all major hypervisors. Import, power on, and complete the guided setup wizard — our team handles the initial configuration during your POC.

📦

VMware vSphere / ESXi

Deploy the OVA via File → Deploy OVF Template. Minimum 4 vCPU, 8 GB RAM, 100 GB disk. Separate data volume recommended for log storage.

🪟

Microsoft Hyper-V

Import the VHDX via New Virtual Machine → Use existing virtual hard disk. Generation 2, 8 GB RAM minimum. Attach to your existing virtual network.

🐧

KVM / QEMU / Proxmox

Import the QCOW2 image and define the VM via virt-install or the Proxmox UI. Same minimum spec applies.

✈️

Air-gapped delivery

No internet access required after setup. For fully isolated environments, Keel can be delivered on USB or via secure transfer — no dependency on any external registry or CDN.

Minimum specification

CPU4 vCPU
RAM8 GB
OS disk100 GB
Log storageSeparate volume — your disk, your call
OSUbuntu 22.04 LTS (pre-installed)
NetworkPort 443 for dashboard · OTLP 4317/4318 · Syslog 514
High availability3-node HA cluster · automatic failover
Image formatsOVA · VHDX · QCOW2
Pricing

Simple pricing.
Every feature, every plan.

One flat annual license per appliance. The only difference between plans is how much data you ingest per day — every feature is included at every tier.

Starter
$6,000
per year · billed annually
≤ 5 GB / day
Sign up
vs. $30K–80K/yr on legacy tools
MOST POPULAR
Growth
$14,800
per year · billed annually
≤ 50 GB / day
Sign up
vs. $80K–200K/yr on legacy tools
Business
$60,000
per year · billed annually
≤ 250 GB / day
Sign up
vs. $500K–$1M+/yr on legacy tools
Enterprise
Custom
annual contract
> 250 GB / day
Contact sales
Dedicated account manager & SLA

Every plan includes all features — no add-ons, no tiers

Natural language search — plain English or direct query
Automatic RCA — alert fires, AI investigates, root cause delivered
Knowledge assistant — answers questions using your own runbooks
Fully on-prem AI — runs on local LLM, zero external API calls
OpenTelemetry-native ingest (OTLP, syslog, Fluentd)
Cloud & tool connectors (AWS, Azure, GCP, Datadog…)
Configurable log pipelines & processing rules
Configurable retention — your disk, your call
Alert rules & incident tracking
Notifications — Slack, PagerDuty, email, SNMP, webhook
3-node HA cluster with automatic failover
SSO — SAML & OIDC identity providers
Teams & role-based access control (RBAC)
Audit logging — every action tracked
Multi-factor authentication (MFA)
Air-gapped deployment — no internet access required
TLS/SSL & firewall management
Guided setup wizard & in-place upgrades
Backup & restore
All software updates included

All plans billed annually  ·  30-day guided POC included — full-feature license, we handle setup  ·  Sign up →

30-day guided POC

Evaluate on your real data,
in your own environment.

We deploy Keel inside your network, connect your log sources, and walk your team through the platform. You get a full-feature 30-day license for the duration — no commitment, no credit card, nothing to cancel if it's not the right fit.

No credit card · No commitment · Full-feature license for 30 days · We'll reach out within 1 business day

✓ Request received

We'll be in touch within 1 business day. In the meantime, email us at [email protected].

FAQ

Common questions

Who is Keel for?
Keel is built for regulated, sovereign, or air-gapped organisations — defence, finance, healthcare, government, and critical infrastructure — where logs cannot leave the network. It's also a strong fit for mid-market engineering and security teams spending heavily on volume-based log platforms who want to reduce cost without giving up AI-native search.
What AI capabilities does Keel include?
Keel has three distinct AI capabilities — all of which can run on a local model inside your network:

Natural language search: Ask any question in plain English — "show all 5xx errors from the payment service in the last two hours" — and Keel translates it into a query and returns results in milliseconds. Power users can also write queries directly in the same window.

Automatic root cause analysis: When an alert fires, Keel investigates automatically. It searches the surrounding log data, reads your uploaded runbooks and architecture docs, and delivers a root cause analysis in plain English — directly to Slack, PagerDuty, or email. No manual triage. No analyst required.

Knowledge assistant: Ask questions about your own infrastructure in plain English. The assistant answers using your own uploaded runbooks and documentation as its source of truth.
Does Keel need internet access to run?
No. Keel generates all secrets on first boot and requires no phone-home to operate. For AI features in fully air-gapped environments, Keel supports any local LLM served via an OpenAI-compatible endpoint — Ollama, vLLM, or any model you host internally. No data leaves your network at any point.
What does the 30-day POC involve?
You get a full-feature 30-day license from day one. Our team handles the initial setup during Week 1 — we deploy the VM image inside your network, connect your log sources, and walk your team through the platform. By Week 2 you're searching real logs and testing alerting on your own data. By Week 4 you have enough to make a purchase decision. No commitment, no credit card, nothing to cancel if it's not the right fit.
How is log retention handled?
Retention is configurable and limited only by the storage you provision on the log data volume. There is no enforced cap. This matters for regulated industries with long compliance retention requirements — you decide how long logs are kept, not us.
What high availability options are available?
Keel supports a 3-node HA cluster with automatic failover. If a node fails, the remaining nodes continue serving ingest and search without manual intervention. The 3-node configuration is required for stability — it ensures a quorum is always maintained so the cluster can make consistent decisions without split-brain risk. HA is available on the Business and Enterprise plans.
Can Keel receive logs from our existing tools?
Yes. Keel is OpenTelemetry-native and supports OTLP gRPC, OTLP HTTP, syslog, and Fluentd. It also has connectors for AWS, Azure, GCP, Datadog, Grafana, Prometheus, and PagerDuty. Per-source isolation means you can add Keel alongside your existing platform and migrate gradually — adding or removing a source doesn't disrupt other ingest streams.
How is pricing structured?
Keel is priced as a flat annual subscription per appliance, banded by daily ingest volume — $6,000/yr for up to 5 GB/day, $14,800/yr for up to 50 GB/day, and $60,000/yr for up to 250 GB/day. Every feature is included at every tier with no add-ons. You're not charged per gigabyte — the bill stays flat even as log volume fluctuates day to day. Most customers migrating from volume-based platforms see an 80–90% reduction in their annual spend.