Home / AI Trending / kenn-io/agentsview

agentsview — What is it?

agentsview is a local-first session intelligence and analytics tool for coding agents, providing detailed insights into AI coding agent usage and costs.

⭐ 3,225 Stars 🍴 263 Forks Go MIT Author: kenn-io
Source: per README View on GitHub →

Why it matters

agentsview is gaining attention due to its comprehensive session intelligence and analytics capabilities, addressing the pain points of tracking and understanding AI coding agent usage. Its unique technical choice of local-first architecture and support for multiple agents sets it apart.

Source: Synthesis of README and project traits

Core Features

Session Tracking

agentsview automatically discovers and tracks sessions from various AI coding agents, storing them in a local SQLite database for fast and secure access.

Source: per README
Cost Tracking

The tool provides detailed cost tracking for all coding agents, with over 100x faster query performance compared to traditional methods like ccusage.

Source: per README
Analytics Dashboard

agentsview offers an analytics dashboard with heatmaps, tool usage, velocity metrics, and project breakdowns, providing a comprehensive view of coding agent activity.

Source: per README

Architecture

The architecture of agentsview is inferred to be modular, with clear separation of concerns. It likely employs design patterns such as Dependency Injection for flexibility and maintainability. The data flow involves local-first storage and retrieval of session data, with a focus on security and performance.

Source: Code tree + dependency files

Project Knowledge Graph

Knowledge graph: project (center) + core features (inner hexagons) + key dependencies (outer chips) github.com/BurntSushi/tomlgithub.com/Bur… github.com/duckdb/duckdb-go/v2github.com/duc… github.com/jackc/pgx/v5github.com/jac… github.com/spf13/cobragithub.com/spf… github.com/spf13/pflaggithub.com/spf… Session Tracking Cost Tracking Analytics Dashboard agentsview Project Core feature Key dependency

Center: project; inner ring: core feature modules; outer ring: key dependencies. Auto-generated from core_features and tech_stack.key_deps.

Tech Stack

LanguageGoFrameworkCobra for CLI, DuckDB for analytics, PostgreSQL for database support
Key dependencies
github.com/BurntSushi/tomlgithub.com/duckdb/duckdb-go/v2github.com/jackc/pgx/v5github.com/spf13/cobragithub.com/spf13/pflag
Infrastructure / Deployment
Docker, with support for local and remote deployment
Source: Dependency files + code tree

Quick Start

```bash # macOS / Linux curl -fsSL https://agentsview.io/install.sh | bash # Windows powershell -ExecutionPolicy ByPass -c "irm https://agentsview.io/install.ps1 | iex" # Docker docker run --rm -p 127.0.0.1:8080:8080 \n -v agentsview-data:/data \n -v "$HOME/.claude/projects:/agents/claude:ro" \n -v "$HOME/.forge:/agents/forge:ro" \n -e CLAUDE_PROJECTS_DIR=/agents/claude \n -e FORGE_DIR=/agents/forge \n ghcr.io/kenn-io/agentsview:latest ```
Source: README Installation/Quick Start

Use Cases

agentsview is suitable for developers and technical teams working with AI coding agents. It is useful in scenarios where detailed tracking and analysis of AI coding agent usage and costs are required, such as in software development, research, or educational settings.

Strengths & Limitations

Strengths

  • Strength 1: Comprehensive session intelligence and analytics
  • Strength 2: Local-first architecture for security and performance
  • Strength 3: Support for multiple AI coding agents

Limitations

  • Limitation 1: Limited documentation on specific features
  • Limitation 2: May require technical expertise to set up and configure
Source: Synthesis of README, code structure and dependencies

Latest Release

v0.32.1 (2026-06-05): Show full tool call content with a show-more toggle. Skip `/usage` probe sessions so usage views stay focused on real activity. Recognize Codex. v0.32.0 (2026-06-04): Support Antigravity CLI SQLite sessions. Add token usage tracking for Copilot CLI sessions. Add a per-session usage REST endpoint. Add a Postg. v0.31.1 (2026-05-28): Add fallback pricing for Claude Opus 4.8 so cost estimates stay accurate when live pricing data is unavailable. v0.31.0 (2026-05-28): Parse decrypted Antigravity CLI trajectory sidecars for richer Antigravity session imports. Add vendor-aware secret detection rules, clearer scan. v0.30.1 (2026-05-26): Refresh model pricing from LiteLLM when usage includes unpriced models, improving cost estimates.

Verdict

agentsview is a valuable tool for anyone needing detailed insights into AI coding agent usage and costs. Its local-first architecture and support for multiple agents make it a standout choice for developers and technical teams in the AI coding space.

Frequently Asked Questions

What is agentsview?

agentsview is a local-first session intelligence and analytics tool for coding agents, providing detailed insights into AI coding agent usage and costs.

What are the main features of agentsview?

agentsview's core features include: Session Tracking, Cost Tracking, Analytics Dashboard.

Why is agentsview trending?

agentsview is gaining attention due to its comprehensive session intelligence and analytics capabilities, addressing the pain points of tracking and understanding AI coding agent usage.

What is agentsview used for?

agentsview is suitable for developers and technical teams working with AI coding agents. It is useful in scenarios where detailed tracking and analysis of AI coding agent usage and costs are required, such as in…

Transparency Notice
This page is auto-generated by AI (a large language model) from the following public materials: GitHub README, code tree, dependency files and release notes. Analyzed at: 2026-06-12 18:31. Quality score: 75/100.

Data sources: README, GitHub API, dependency files