long-running-agent

What problem does it solve?

Long-running AI agents require persistent state across multiple sessions, enabling them to work on multi-hour or multi-day projects without losing progress.

Core Features & Use Cases

• Initializer Agent: sets up the environment, creates progress and feature-tracking artifacts, and boots the workflow for subsequent sessions.
• Coding Agent: performs incremental work with session awareness, reads progress, tests, and commits changes between sessions.
• Session Startup Sequence: a repeatable sequence to inspect the repo, review progress, and initialize the environment for the next feature.
• Progress & Handoff: centralizes context via claude-progress.txt, feature_list.json, and init.sh to enable clean handoffs between sessions.
• Use Case: teams building long-running AI projects that must maintain state over time and across sessions.

Quick Start

Run the two-agent workflow: initialize with the Initializer Agent, then proceed with Coding Agent sessions. Before each session, follow the session startup steps: pwd, cat claude-progress.txt, cat feature_list.json, git log --oneline -20, ./init.sh, run a basic test, select the next feature.