whereismyai
Agent
Agent is an agent built in Rust that manages persistent conversations and workers across hosts.
This software provides a command-line interface and terminal user interface built around Pi Durable and Rex. It maintains persistent conversations, manages workers, and connects to services like email, Slack, GitHub, and messages to handle tasks. The system coordinates tasks across hosts using named sessions and terminals, while preserving authorization and state. Users can interact with the main conversation through a terminal interface or an iOS application. It supports context management, background jobs, worktree cleanup, and search capabilities over saved history.
Agent at a glance
- Best for: Software engineer
- Runs on: CLI, macOS, Linux, iOS, self-hosted, open source
- Pricing: Free
- Released: October 2026
- Category: AI agent tool
- Website: github.com/jessfraz/agent
Key features
- Rust command-line interface
- Terminal user interface with Markdown rendering
- Persistent conversations and workers
- Background scheduled jobs
- Worktree inventory and cleanup
- SQLite history search
- iOS application support
Use it for
- Manage persistent AI conversations
- Run tasks across connected machines
- Process incoming messages and emails
- Clean up inactive worktrees
- Search saved conversation history
Alternatives to Agent
- thClaws — Runs locally in native Rust with zero cloud lock-in and multi-provider support.
- Agensh — Scales to 1,024 self-organizing agents without a central orchestrator.
- Discord CLI — Run Discord operations from shell scripts, cron jobs, CI, or AI agents using JSON output.
- Clai — Query twelve models and local Ollama directly from your terminal using unix pipes.
- browser-control — Shell-native design with stable element refs and no LLM or framework requirement.
- ZeroClaw — Own your AI infrastructure with no subscriptions or cloud dependencies.
- Alook — Connects existing local coding agents to team communication channels.
- OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
- Moltis — It runs locally as a single sandboxed binary with multi-provider LLMs and built-in channels.
- Comma — It operates 24/7 on a cloud computer to finish tasks independently.
- zerostack — Minimal memory footprint and high CPU efficiency compared to JS-based agents.
- BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
All Agent alternatives