whereismyai
Agent Archive
Agent Archive is a command-line tool that backs up and transfers coding agent sessions between apps and machines.
Agent Archive allows developers to continue coding sessions across different agents and computers by moving conversation context between tools like Claude Code, Codex, and Cursor. It automatically uploads transcripts to a user-owned S3 or R2 bucket for backups and cross-machine access. Users can browse session history, filter by topic, project, branch, or PR number, and search conversation text using a private local index. The tool also tracks usage and estimated spend, broken down by agent, model, and project. It supports macOS and Linux through release binaries and integrates via background jobs and app hooks.
Agent Archive at a glance
Key features
- Continue sessions across different coding agents
- Upload transcripts automatically to S3 or R2 buckets
- Browse and filter session history by topic or project
- Search conversation text in a private local index
- Track token usage and estimated spend by model and project
- Hand off sessions using command-line interface commands
Use it for
- Switching a coding session from Claude Code to Codex
- Backing up agent transcripts to an S3 or R2 bucket
- Browsing session history across multiple coding agents
- Tracking token counts and estimated spend across projects
Companions
Tools that articles about Agent Archive recommend using with it, each with its job.
- Claude Code — Built to work with Claude Code.
- Codex — Built to work with Codex.
- Cursor — Built to work with Cursor.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Superpowers — Brainstorm, plan and execute skills for bigger tasks.
- Playwright MCP — Enables LLMs to interact with web pages using structured accessibility snapshots.
Alternatives to Agent Archive
- claude-mem — It shares persistent, searchable agent memory across sessions and devices.
- Agent Pets — Approve agent permission prompts and send replies directly from any browser tab
- Reviewer Agent — It uses a separate AI model to review code and prevent premature agent stopping.
- AGENTS.md — It separates agent-specific instructions from human-focused README files.
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- agent.reviews — Real tool reviews written directly by coding agents after task completion.
- Agent Skills — Encodes senior-engineer workflows and quality gates into 24 skills.
- Agents Anywhere — Manage and continue coding agent sessions across desktop, mobile and web.
- Ret — Manage multiple AI coding agents across projects from one unified desktop interface.
- Agent Relay — It carries turns between different AI agents and stops for human decisions.
- Runway — Control Claude Code and Codex sessions on local or cloud machines from any phone.
- HarnessRouter — One API to manage agent runtimes, sandboxes, and execution lifecycles.
All Agent Archive alternatives