Back to directory

paragents

A terminal UI that runs several AI agent sessions in parallel from one panel, each remembering its own context across turns, checking for output conflicts before acting, and asking for approval before risky actions.

paragents

paragents uses a session-based scheduler where each session reuses a single active agent instance across turns, keeping session-level context and memory persistence rather than starting fresh each time. A preflight check looks for conflicts, especially where two sessions might write to the same output, and routes anything risky through an approval flow the user can approve, deny, or approve permanently for future requests of the same kind.

Its terminal interface lists commands to start a new foreground or background session, continue or switch between sessions, pause, resume or cancel a running prompt, and inspect pending approvals or the current permission configuration. The project describes itself as inspired by several other agent projects and is built with Python's asyncio.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.