#5 · Primary category: AI Usage & Cost Monitoring

agentsview

Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.

Project last updated:08/29/26

GitHub Stars

5.5K

Forks

624

Contributors

134

License

MIT

Why we included this project

Keeping track of token usage across several coding agents usually means digging through each tool's own logs, and that gets messy fast. AgentsView pulls session history from Claude Code, Codex, and more than 20 other agents into a single local SQLite database, then serves a dashboard you can browse and full-text search. The daily cost summaries and breakdowns by project, model, and tool give you a concrete view of where tokens actually go, without needing to read raw conversation files. It runs as one binary with no account, and you can point it at S3-compatible object storage if you want one central instance to read sessions from other machines. That's a useful setup for solo developers and small teams who want visibility into agent spending without uploading session data anywhere.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category