agentlens
Active·★ 24·MIT·Updated 2026-10-18
AgentLens is an open-source observability tool designed for AI agents, capturing every LLM call, tool invocation, and decision. It stands out with a tamper-evident audit trail, cryptographically verifying events to ensure compliance and data integrity.
#Observability#AI Agents#Audit Trail#Tamper-evident#LLM Tracking#OpenTelemetry#Cost Management#Session Replay
01
Features
01Python Auto-Instrumentation for 9 LLM providers
02Tamper-Evident Audit Trail with SHA-256 hash chains
03Real-Time Web Dashboard for monitoring and analytics
04LLM Call Tracking, cost aggregation, and latency measurement
05Cost Optimization with model recommendation engine
06Session Replay to step-through past agent runs
02
Compatibility
Python
Runtime
Verified via docs
Node.js
Runtime
Verified via docs
Docker
Deployment
Verified via docs
OpenTelemetry
Integration
Verified via docs
OpenAI API
LLM Provider
Verified via docs
Anthropic API
LLM Provider
Verified via docs
03
Quick start
1
$ docker run -p 3400:3400 -e AUTH_DISABLED=true -e JWT_SECRET=dev-secret ghcr.io/agentkitai/agentlens
04
Use cases
↳Monitoring and debugging AI agent runs in real-time.
↳Ensuring compliance with regulations like EU AI Act Article 12 through verifiable audit logs.
↳Tracking and optimizing LLM costs and performance across agents and models.
↳A/B testing and benchmarking different agent variants for improved performance.
↳Analyzing past agent sessions with full context reconstruction for understanding behavior.
05
Alternatives
ZizkaDB★ 144
Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support EU AI Act Article 12 record-keeping. Drift detection, MCP, Python & TypeScript SDKs. Self-host or cloud.
preflight★ 65
Observability for AI coding assistants — cost tracking, efficiency scoring, and anti-pattern detection for Claude Code, Cursor, Copilot, and more. Local-first; New Relic optional.
mcpsnoop★ 362
Wireshark for MCP. A transparent proxy that shows every real tool call between your AI client and your MCP servers, live in your terminal.
lakevision★ 52
Lakevision is a tool which provides insights into your Apache Iceberg based Data Lakehouse.
uptimepage★ 47
Hosted uptime monitoring and public status pages for teams. Multi-region checks, automatic incidents, on-call alerts (Slack/Telegram/webhook/+), subscribers, REST API, Terraform provider, MCP server. Eight check types including browser login flows, cron heartbeats, DNS, TLS and domain expiry. AGPL source, self-host the same build.
Comments
Log in to leave a comment
No comments yet. Be the first!