AgentLens

[](https://github.com/RogerReed/agentlens/actions/workflows/ci.yml) [](LICENSE)


Local monitoring and observability for agentic AI coding tools — see what's actually happening inside each run. Nothing leaves your machine.

AgentLens receives **OpenTelemetry traces** from Copilot, Claude Code, and Codex in real time, giving you span timing, time-to-first-token, per-tool latency, and file diffs. It also reads the **local session files** each agent writes automatically — including OpenCode's **SQLite database** — as a zero-config fallback that backfills history from before you set anything up. Both sources appear in one dashboard; OTEL takes precedence when available.

Two things it does that a usage dashboard doesn't:

• Catches agents that are stuck. Five named loop and malfunction patterns — identical tool calls repeated, edits oscillating between two states, the same error recurring, runaway scope, context accumulating while progress collapses — each with a correction prompt you can paste straight into the session. See the full list →
• Tells you what to fix in your instructions file. The Advisor reads across sessions and suggests concrete additions to your CLAUDE.md or AGENTS.md — including hot files the agent rediscovers from scratch on every run. More →

Getting Started

Local (OTEL and log files)

The fastest way to get started — run directly on your machine with no install required. Because it runs natively it has full access to your local session log files.

# One-off — always uses the latest published version
npx agentlens-dashb