AI coding agents generate substantial session data across projects. agentsview addresses this by providing a fast, local web application for browsing, searching, and analyzing these sessions. It supports numerous AI coding assistants, offering a centralized, searchable history and an analytics dashboard, benefiting developers and researchers by enhancing visibility into AI agent behavior and usage patterns.

How It Works

agentsview indexes AI coding agent sessions into a local SQLite database, leveraging FTS5 for full-text search. A web interface allows users to query this data, review agent behavior, and track usage patterns. The sync engine discovers and synchronizes session data from supported agents, populating the database and enabling features like activity heatmaps and tool usage metrics. Its local-first, single-binary design prioritizes data privacy and simplifies deployment.

Quick Start & Requirements

• Installation:
  • Bash: curl -fsSL https://agentsview.io/install.sh | bash
  • Windows PowerShell: powershell -ExecutionPolicy ByPass -c "irm https://agentsview.io/install.ps1 | iex"
  • Build from source: Requires Go 1.25+ (with CGO) and Node.js 22+. Commands: git clone https://github.com/wesm/agentsview.git, cd agentsview, make build, make install.
• Prerequisites: Go 1.25+ and Node.js 22+ are required for building from source.
• Documentation: Full documentation is available at agentsview.io, covering Quick Start, Usage Guide, CLI Reference, Configuration, and Architecture.

Highlighted Details

• Full-text search across all message content using FTS5 for instant retrieval.
• Analytics dashboard featuring activity heatmaps, tool usage, velocity metrics, and project breakdowns.
• Supports multiple AI agents: Claude Code, Codex, Copilot CLI, Gemini CLI, OpenCode, Amp, and VSCode Copilot.
• Live updates for active sessions via Server-Sent Events (SSE).
• Keyboard-first navigation, including vim-style controls.
• Options to export sessions as HTML or publish them to GitHub Gist.
• Local-first architecture ensures all data remains on the user's machine.

Maintenance & Community

The project is described as a "next-generation rewrite of agent-session-viewer in Go." No specific community channels (like Discord or Slack), notable contributors, or sponsorships are mentioned in the provided README.

Licensing & Compatibility

• License: MIT.
• Compatibility: The MIT license is permissive, generally allowing for commercial use and integration with closed-source projects.

Limitations & Caveats

The Tauri desktop wrapper is noted as experimental. Building from source requires specific, relatively recent versions of Go and Node.js. The configuration of session directories relies on environment variables, which may add complexity if default locations are not used.