Tamper-evident audit trail for AI agents with verifiable records
Stage
Not given
Not given
Founded
2017
Not given
Based in
US
GB
Pricing model
Not given
Freemium
Pricing
Not given
Free: £0, no card required, 1 user, 25,000 live records a month. Solo: £19/month or £190/year, 1 user, 100,000 live records a month (then £5 per 100,000). Team: £49/month or £490/year, unlimited users with roles, 250,000 live records a month (then £5 per 100,000, or £3 above 10 million). Enterprise:
Key features
LLM trace logging with 40+ integrations
Automatic error detection and diagnostics
Ollie agent for code fix recommendations
Test Suites and 40+ LLM-as-a-judge evaluation metrics
Production dashboards and alerts for agents
Prompt playground and optimization
Agent Playground for local agent development
Cost intelligence for Claude Code and Codex tracking
Agent signs each record with its own Ed25519 key
Service co-signs records and chains them to prevent edits or gaps
Public timestamp bounds each record with hourly verification
Only salted hashes sent to service; inputs and outputs stay on your machine
Open verifier code allows independent verification
Python and TypeScript SDKs for wrapping agent tools
Verification reports in HTML or PDF format with compliance mapping
Compliance packs for EU AI Act, ISO/IEC 42001 and SOC 2
99.5% uptime guarantee on hosted witness in Google Cloud London
What makes it different
Truly open-source platform with enterprise-grade infrastructure
Traces appear almost instantly even at high volumes
Flexible hosting options including self-hosted, cloud, and custom deployments
Easy integration with just a few lines of code
Opik automatically turns trace data and eval results into code fixes
Records are verifiable offline and survive service shutdown
Independent co-signature and public time bounds provide proof beyond your control
Content remains private on your machine in hash-only mode
Compliance-ready evidence for regulators and auditors