Self-improving AI workflow system. Crystallize requirements before execution with Socratic interview, ambiguity scoring, and 3-stage evaluation.
Cancel stuck or orphaned executions
Evaluate execution with three-stage verification pipeline
Start or monitor an evolutionary development loop
Full reference guide for Ouroboros commands and agents
Socratic interview to crystallize vague requirements
Automatically converge from goal to A-grade Seed and execute it
Scan and manage brownfield repository/worktree defaults for interviews
Cancel stuck or orphaned executions
Evaluate execution with three-stage verification pipeline
Start or monitor an evolutionary development loop
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Automatically update your running Docker containers to the latest available image.
Ouroboros will monitor your running Docker containers and update them to the latest available image โ similar to Watchtower but with additional features like Prometheus metrics, notifications, and flexible scheduling.
docker run -d --name ouroboros \
-v /var/run/docker.sock:/var/run/docker.sock \
pyouroboros/ouroboros
version: '3'
services:
ouroboros:
image: pyouroboros/ouroboros
container_name: ouroboros
restart: unless-stopped
volumes:
- /var/run/docker.sock:/var/run/docker.sock
environment:
- CLEANUP=true
- INTERVAL=600
- LOG_LEVEL=info
- SELF_UPDATE=true
- NOTIFIERS=
Personal note: I changed
INTERVALto600(10 minutes) in the example above. The default 5-minute polling felt too aggressive for my home setup and was generating unnecessary registry traffic.
Ouroboros can be configured via environment variables or command-line arguments.
| Environment Variable | CLI Flag | Default | Description |
|---|---|---|---|
INTERVAL | --interval | 300 | Polling interval in seconds |
CRON | --cron | None | Cron expression for scheduling |
LOG_LEVEL | --log-level | info | Logging level (debug/info/warn/error) |
SELF_UPDATE | --self-update | False | Update ouroboros itself |
CLEANUP | --cleanup | False | Remove old images after update |
MONITOR | --monitor | [] | Containers to monitor (default: all) |
IGNORE | --ignore | [] | Containers to ignore |
NOTIFIERS | --notifiers | [] | Apprise notification URLs |
REPO_USER | --repo-user | None | Registry username |
REPO_PASS | --repo-pass | None | Registry password |
METRICS_PORT | --metrics-port | 8080 | Prometheus metrics port |
See .env.example for a full list of configuration options.
When enabled, Ouroboros exposes a Prometheus metrics endpoint at http://localhost:8080/metrics.
Available metrics:
containers_updated_total โ Total number of container updatescontainers_scanned_total โ Total number of containers scannedouroboros_up โ Whether Ouroboros is runningOuroboros uses Apprise for notifications. Set the NOTIFIERS envi
npx claudepluginhub alv0992amurray/ouroborosHarness-native ECC plugin for engineering teams - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Evidence-gated AI coding workflow: scan โ analyze โ plan โ TDD โ execute โ fix โ verify โ review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques