Skip to content
@adventurewave-labs

adventurewave-labs

Open-source developer tooling for the Claude and agentic AI ecosystem — the lab behind Turbo-Flow.
Adventure Wave Labs

Adventure Wave Labs Claude Rust License

We build open-source developer tooling for the Claude and agentic AI ecosystem.

Founded by the creator of turbo-flow — an autonomous multi-agent dev environment built to let one engineer operate like a full team.

Website LinkedIn YouTube X


What is Adventure Wave Labs?

Adventure Wave Labs (AWL) is the open-source lab behind Turbo-Flow and its supporting toolchain — CLIs, agentic loop runners, and code-intelligence engines that let a single engineer operate a full agentic development workflow on top of Claude Code. Everything here is Rust-first, MCP-native, and built to run in real terminals against real codebases — not demos.

What We Build

DevOps / Infrastructure

Autonomous agents and reliability tooling for Ansible-driven infrastructure. These projects sit between your CI/CD pipeline and your fleet — they watch, diagnose, and heal routine failures without human intervention.

ansible-heal-agent demo — heals a broken baseline in 7 seconds

ansible-heal-agent heals 3 seeded failures (stale hostname, removed apt_key, undefined nginx_port) and lands 3 conventional commits in 7 seconds.

Repo Lang What it does
ansible-heal-agent Python Autonomous agent that scans Ansible logs, diagnoses routine failures (stale hostname, removed module, undefined variable), patches the playbook / inventory / vars, commits via conventional commits, and re-runs the pipeline. LLM-first (GLM-4-Plus via z-ai-web-dev-sdk) with a deterministic rule-based fallback, YAML validation before write, and a full Markdown transcript for human audit. make demo heals a broken baseline end-to-end in about 7 seconds.

Developer Tooling

Repo Lang What it does
loopgen-rs Rust Agentic loop runner for Claude Code — compiles a goal into a structured harness and drives claude -p around a PLAN → ACT → VERIFY → REPORT cycle until a parsed LOOP_STATUS contract trips: DONE (optionally gated on a real verify command), BLOCKED, or a hard --max iteration cap
secret-scan Rust Regex-based secret scanner for CI pipelines
codescope Rust Single-binary code intelligence engine for AI coding agents — tree-sitter, MCP, CLI
preflight-integration-tester Python Pre-deploy integration test harness

In motion

loopgen rendering an agentic loop harness with --dry-run codescope indexing itself and answering blast-radius queries
loopgen-rs — agentic loop runner codescope — code intelligence for agents
secretscan finding 6 planted secrets in a demo repo preflight-integration-tester running a real readiness diagnostic — 97% GO, 3 middleware gaps found
secret-scan — CI secret scanner preflight-integration-tester — AI readiness diagnostic

Lab / Demos

Experiments, proofs of concept, and agentic demos.

Repo What it explores
agentic-powered-golden-path-demo NL → GitOps deployment via golden-path workflows (ArgoCD + OpenRouter)
AI-Kubernetes-API-Generator-Demo NL → Kubernetes API generation
agentic-devops-extravaganza · live demo Working demo of K8sGPT and Robusta running against a real Kubernetes API + GLM-4.5 LLM
agentic-platform-engineering-extravaganza · live demo Golden path + Score → Crossplane + real OPA policy gates + an authz-gated MCP server — 42 policy violations without a platform, 0 with one
aops-sre-pipeline · live demo Alert-driven autonomous SRE pipeline — Prometheus → n8n → Popeye → Dify-lite → Ollama → Slack
gitops-progressive-delivery-demo · live demo Argo CD + Argo Rollouts + Prometheus + K8sGPT progressive delivery — a canary trips an SLO violation, an AI SRE diagnoses it, and the rollout auto-rolls back in ~20s
moor · live demo Desired-state control plane for docker-compose — OBSERVE → DIFF → PLAN → ACT drift detection with real auto-remediation against the live Docker Engine API
cloudtrim · live demo 22-rule AWS cost-waste audit & remediation engine — read-only scan, verified fixes, and CUR-reconciled savings reporting demoed against a pinned AWS API emulator

FAQ

What is Adventure Wave Labs? An open-source lab building developer tooling for the Claude and agentic AI ecosystem — CLIs, agentic loop runners, and code-intelligence tools used alongside Claude Code.

What is Turbo-Flow? Turbo-Flow is AWL founder Marcus Patman's agentic development environment — 215+ MCP tools, cross-session memory, and per-agent git-worktree isolation, bootstrapped with one command on DevPod, Codespaces, or Rackspace Spot. See [mmarcuspat/turbo-flow.

Is this tooling used in production? The toolchain is dogfooded daily inside Turbo-Flow, and most repos have their own CI (see each repo's Actions badge). preflight-integration-tester is explicitly marked pre-alpha in its own README — it's a real, working tool, just not yet positioned as a production dependency for outside teams.


Stack

Rust · Shell · Python · Claude Code · MCP · Kubernetes · Terraform

Founder-published crates on crates.io:

secretscan downloads cargo-forge downloads netrain downloads cargocrypt downloads k8s-netinspect downloads file-hasher downloads


Built & Presented by Adventure Wave Labs

Built by Marcus Patman — Principal Agentic Engineer LATAM AI solutions at creandotumatrix-labs

📧 marcus@adventureonthewave.com · adventurewavelabs.space · LinkedIn · X @marcuspat · YouTube

Pinned Loading

  1. secret-scan secret-scan Public

    Rust secret scanner CLI — 50 patterns, entropy analysis, Base64/hex obfuscation detection. cargo install secretscan

    Rust 10 1

  2. turbo-flow-wizard turbo-flow-wizard Public

    Interactive setup wizard that generates project-specific CLAUDE.md configuration files for Claude Code integration. Supports 12 app types, 7 development methodologies, and 19 feature sets.

    Shell 6

Repositories

Showing 10 of 24 repositories
  • cloudtrim Public

    Productized AWS cost audit engine — fixed-fee one-week audits that cut cloud spend 30% with zero downtime. Real boto3 + Terraform + CUR pipeline; full portable demo runs in a Codespace; self-contained landing page in docs/.

    adventurewave-labs/cloudtrim's past year of commit activity
    TypeScript 0 0 0 0 Updated Sep 9, 2026
  • moor Public

    Moor — a desired-state control plane for docker-compose. Kubernetes-style drift detection and auto-remediation for the stacks everyone actually runs. Includes the full PRD, cited research, and a 100% real end-to-end demo.

    adventurewave-labs/moor's past year of commit activity
    Python 0 MIT 0 0 0 Updated Sep 9, 2026
  • .github Public

    Organization profile for adventurewave-labs — profile/README.md renders on the org's GitHub page.

    adventurewave-labs/.github's past year of commit activity
    0 MIT 0 0 0 Updated Sep 9, 2026
  • agentic-devops-extravaganza Public

    AI-assisted Kubernetes triage you can run yourself: real k8sgpt + kubectl against a writable mock API (8 findings, then 0), plus a real kind cluster with real Robusta and Prometheus.

    adventurewave-labs/agentic-devops-extravaganza's past year of commit activity
    Python 0 MIT 0 0 1 Updated Sep 8, 2026
  • gitops-progressive-delivery-demo Public

    Real k3s + Argo CD + Argo Rollouts + Prometheus: a broken canary trips its SLO, an LLM writes the RCA, auto-rollback in ~20s.

    adventurewave-labs/gitops-progressive-delivery-demo's past year of commit activity
    TypeScript 0 MIT 1 0 1 Updated Sep 8, 2026
  • aops-sre-pipeline Public

    Automated Off-the-shelf Pipeline SRE — Prometheus → n8n → Popeye-compatible scanner → LLM agent → Slack, with allowlist-gated remediation. Fixtures or a live kind cluster.

    adventurewave-labs/aops-sre-pipeline's past year of commit activity
    Python 0 MIT 0 0 1 Updated Sep 8, 2026
  • agentic-platform-engineering-extravaganza Public

    42→0: a real policy gate (OPA/Conftest) takes an AI agent's Kubernetes manifests from 42 violations to zero. Golden paths, Crossplane, an authz-gated MCP server.

    adventurewave-labs/agentic-platform-engineering-extravaganza's past year of commit activity
    Python 0 MIT 0 0 1 Updated Sep 8, 2026
  • secret-scan Public

    Rust secret scanner CLI — 50 patterns, entropy analysis, Base64/hex obfuscation detection. cargo install secretscan

    adventurewave-labs/secret-scan's past year of commit activity
    Rust 10 MIT 1 0 0 Updated Sep 3, 2026
  • cloop Public

    Agentic loops for Claude Code — zero-dependency Rust CLI that wraps `claude --print` in a configurable loop until tests pass, a marker appears, or N iterations.

    adventurewave-labs/cloop's past year of commit activity
    Rust 0 MIT 0 0 0 Updated Sep 3, 2026
  • aria Public

    RAG knowledge assistant — FastAPI + LangChain + ChromaDB with API-key auth, structured logging, CORS allowlist.

    adventurewave-labs/aria's past year of commit activity
    Python 1 MIT 0 0 0 Updated Aug 31, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…