AgentSight

AgentSight is an open-source, local-first observability and profiling harness for AI coding agents developed by the Eunomia project. Operating similarly to system tools like top or strace, it correlates high-level prompts, model calls, and tool decisions with kernel- and OS-level effects on the local host, including process spawns, file modifications, and network connections. In practical use, AgentSight operates directly from the terminal. Developers run commands such as `agentsight top` for a live interactive TUI ranking active agent sessions by model, token consumption, health, process family, and tool activity. It inspects running agents non-invasively by capturing plaintext LLM traffic at SSL/TLS boundaries and hooking system events, recording runs to local SQLite databases or exporting them via OpenTelemetry. It supports closed-source and open-source agents alike, including Claude Code, Codex, Gemini CLI, OpenCode, and OpenClaw. Unlike application-level observability platforms (such as Langfuse, LangSmith, or Phoenix) or API proxy gateways that require SDK instrumentation or traffic rerouting, AgentSight uses Linux eBPF to trace agents externally. This enables full observability into closed-source CLI binaries, uninstrumented subprocesses, and agent-spawned scripts that bypass standard framework loggers. AgentSight is written in Rust and licensed under the MIT license. It is available as a standalone CLI binary and as a Rust crate (`agentsight-capture`). Linux systems with kernel 4.1+ support full eBPF monitoring, while macOS, Windows, and Linux can parse agent-native session files directly for offline inspection and visualization.

Tags: AI, ai agent, cli, coding agent, developer tools, OpenSource

Visit AgentSight

Key features

  • Zero-SDK eBPF Tracing — Observes arbitrary CLI binaries, subprocesses, and plaintext SSL/TLS model payloads without code changes, SDK wrappers, or network proxies. - Interactive Process Monitor (top) — Provides a live terminal UI displaying real-time agent sessions, token usage, tool invocations, and system resource consumption. - Repository Replay (agentsight vis) — Visualizes file creation, editing, renaming, and deletion sequences across Git worktrees into self-contained HTML or animated GIF replays. - Semantic Profiling (agentpprof) — Generates flamegraphs of agent call stacks to pinpoint slow steps, retry loops, and token-heavy model interactions. - Local SQLite & OpenTelemetry Output — Stores recorded sessions locally in structured SQLite files (agentsight-*.db) and supports exporting traces through standard OpenTelemetry collectors. - Broad CLI Agent Compatibility — Out-of-the-box monitoring and log ingestion for Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw, and custom shell commands.

Use cases

Use Case: Diagnosing Closed-Source Agent Failures Developers running compiled or closed-source coding agents (such as Claude Code or Gemini CLI) can monitor active runs to identify why a task stalled, correlating LLM tool-calling output with exact operating system error codes and failed subprocesses.

Use Case: Auditing File and Network Side Effects Security engineers and developers can audit autonomous coding agent executions by reviewing precise file reads, writes, and network destinations, ensuring the agent did not access sensitive files outside the repository boundary.

Use Case: Token and Execution Performance Optimization Engineers building or tuning agent workflows can generate semantic flamegraphs via agentpprof to detect redundant context re-sends, slow tool execution loops, and compute bottlenecks across multi-step agent runs.

Who it is for

AgentSight is built for software engineers, security auditors, and AI infrastructure teams who execute autonomous coding agents locally or in CI environments and require low-level visibility into agent system behavior. It is not intended for teams looking for managed cloud web dashboards for simple chat completions without local process execution.

Install guide

Installation Install AgentSight using Cargo, Linux Homebrew, or prebuilt binaries: bash # Via Cargo cargo install agentsight # Via Homebrew (Linux x86_64) brew tap eunomia-bpf/tap brew install eunomia-bpf/tap/agentsight # Or download the prebuilt binary wget https://github.com/eunomia-bpf/agentsight/releases/latest/download/agentsight chmod +x agentsight sudo mv agentsight /usr/local/bin/

First Run AgentSight requires no API keys or configuration files to begin observing local agent sessions. Launch the live dashboard (running with sudo enables eBPF tracing on Linux): bash sudo agentsight top

Example Session To generate an interactive replay of recent agent edits across your current Git repository: bash # Navigate to your project directory cd /path/to/your/project # Generate an HTML visual replay of Claude/Gemini/Codex file interactions agentsight vis -o output/agent-nebula.html # Query recorded SQLite sessions agentsight report

Part of CLI Coding Agents

Categories: AI Coding Agents, Developer Tools

Related CLI agents

  • Headroom — Headroom is an open-source agent orchestration harness and proxy runtime developed by Headroom Labs. Engineered in Rust with multi-language bindings,…
  • Zosma QA — Zosma QA is an open-source testing-focused agent harness and orchestration framework created by Zosma AI. It provides scaffolding, structured prompt…
  • OpenCode — OpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.…
  • SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
  • OpenHands — OpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environment…
  • Plandex — Plandex is an open-source terminal-based AI coding agent designed to handle complex, multi-file engineering tasks in large codebases. Created by…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories