jazzyalex/agent-sessions

831 stars · Last commit 2026-08-31

Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across Codex, Claude Code, OpenCode, Cursor Agent, Hermes, OpenClaw, Copilot CLI, and more.

README preview

# Agent Sessions (macOS)

[![Build](https://github.com/jazzyalex/agent-sessions/actions/workflows/ci.yml/badge.svg)](https://github.com/jazzyalex/agent-sessions/actions/workflows/ci.yml)

<table>
<tr>
<td width="100" align="center">
  <img src="docs/assets/app-icon-512.png" alt="App Icon" width="80" height="80"/>
</td>
<td>

**Live per-session quota burn for Codex and Claude — see *which* session is eating your 5-hour and weekly limits, priced per model.**
Plus searchable transcripts across [Codex](https://jazzyalex.github.io/agent-sessions/guides/codex-local-history.html?campaign=github&ref=readme-guide), [Claude](https://jazzyalex.github.io/agent-sessions/guides/claude-code-jsonl-history.html?campaign=github&ref=readme-guide), [OpenCode](https://jazzyalex.github.io/agent-sessions/guides/opencode-sqlite-history.html?campaign=github&ref=readme-guide), [Cursor](https://jazzyalex.github.io/agent-sessions/guides/cursor-agent-local-history.html?campaign=github&ref=readme-guide), [GitHub Copilot CLI](https://jazzyalex.github.io/agent-sessions/guides/copilot-cli-local-history.html?campaign=github&ref=readme-guide), Pi, Kimi Code, Grok CLI, Qwen Code, Devin CLI, fx, [Antigravity CLI](https://jazzyalex.github.io/agent-sessions/guides/antigravity-cli-local-history.html?campaign=github&ref=readme-guide), [Hermes](https://jazzyalex.github.io/agent-sessions/guides/hermes-agent-state-db-history.html?campaign=github&ref=readme-guide), and [OpenClaw](https://jazzyalex.github.io/agent-sessions/guides/openclaw-local-agent-history.html?campaign=github&ref=readme-guide), with image browsing and one-click resume where the source supports them. macOS, local-only.

[**Session-Bench**](https://jazzyalex.github.io/agent-sessions/bench/?campaign=github&ref=readme): how ten agents' session formats score — 20 pass/fail gates, evidence behind every cell.

</td>
</tr>
</table>

View full repository on GitHub →