Epoptes

Epoptes is an open-source tool that runs long autonomous AI sessions with a live dashboard and human oversight.

Epoptes runs long autonomous AI sessions for tasks like overnight builds and research sweeps using Claude Code, Codex, or pi. Users describe goals in a chat, and the agent interviews them to build a structured plan. The tool runs tasks as a series of fresh-context cycles until completion or time limits, maintaining a live dashboard and report. It provides human oversight through approval prompts, pause controls, and live feedback while the process operates in the background. Designed for developers managing extended AI tasks, it keeps runs efficient with small state files, cheap models for mechanical work, and strict time boxes. Supported models include Claude Code, Codex CLI, and pi.

Epoptes at a glance

Best for: Software engineer
Runs on: Linux, macOS, CLI, open source
Pricing: Free
Released: October 2026
Category: AI agent tool
Website: github.com/ramigb/epoptes

Key features

Fresh context execution cycles for long tasks
Live dashboard for tracking progress and viewing events
Approval system for pausing and reviewing actions
Integration with Claude Code, Codex CLI, and pi
Automated report generation at task completion
Local brain memory for learning from past runs

Use it for

Running overnight software builds
Conducting large research sweeps
Performing data clean-up tasks
Writing extensive documentation guides

Alternatives to Epoptes

MyAgent — It features built-in permission controls, long-term memory, and skill self-evolution.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
OpenBot — Runs AI agents locally using existing subscriptions or local models.
BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
OpenHarness — Manages Claude Code, Codex, and Hermes from a single command center.
AGiXT — Builds autonomous agents with integrated memory and web capabilities.
Beeuni — Agents retain context and improve skills over time through a controlled review process.
OpenCode — Works with 75+ model providers, local models, and existing subscriptions
OmniAgent — It evolves skills in real-time and dynamically hardens security during task execution.
OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
pstack — Improves AI coding agent outcomes with rigorous workflows.
CodePilot — Consolidates multiple AI agents and local model connections in one workspace.

All Epoptes alternatives