#claude-code

Zero-dep agent workflows with structured approval gates and adversarial review.

Quality-gated autonomous mission completion loop for Claude Code and Codex (plan, execute, review, score, iterate).

A cli for loops

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

Repo-native content governance for AI agents. Extract, review, and deliver UI text, docs, and structured content from Git.

Anti-hallucination AI agent kit for Cursor, Windsurf & Antigravity. 27 specialist agents, 17 slash commands, 8 Tribunal reviewers. Install: npx tribunal-kit init

Capture a logged-in browser task once — replay it forever at zero LLM tokens. Local-first browser-automation MCP for Claude Code, Cursor & any MCP host; credentials never leave your machine.

Remotely view and control local Claude Code / Codex terminal sessions on a mobile device.

Unified Claude Code conversation history scanner

A drop-in engineering loop for coding agents: task contracts, verification reports, reviewer handoffs, and repo-level safety policies.

Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents.

AI memory brain for Claude Code, Cursor, Copilot & Windsurf — 120+ MCP tools. Persistent sessions, lessons learned, semantic search, Team Brain, managed Valkey/Redis. Free tier.

AI agent configuration security auditor - find misconfigurations in Claude Code, Cursor, and other AI tools

Containerised Debian-slim dev environment bundling Claude Code, Codex, cloud CLIs (gcloud/azure/oci/cf), kubectl/helm/tofu, Docker, Node/Bun/pnpm, Python/uv and Playwright. Managed by a Go CLI that handles the container lifecycle with a single command.

AI code review pipeline that turns agent-written PRs into merge-ready patches

OpenCode plugin to use your Claude Max/Pro subscription with OpenCode via Meridian

Monitor all your coding agents from one terminal - Claude Code, Cursor, OpenCode, pi and more

Multi-agent orchestration, persistent memory, and intelligent workflows for AI coding assistants. Supports Claude Code, OpenCode and Codex.

Workflow discipline inside the agent tools you already use — Claude Code, Codex, Kiro, GitHub Actions. A Kontour product built on Flow and Veritas.

Merge autonomy for AI-authored code. Turn your repo's standards into evidence-backed readiness reports the agent reads back.

Context provider for data agents (MCP + REST + CLI): metrics, golden queries, and interpretation knowledge. Google Cloud native (Cloud Run + Cloud SQL), secret-zero.

Git-anchored decentralised intent(conversation) ledger for teams who build with AI

A tiny, dependency-light Go daemon that hosts a remote Claude Code session over SSH: CLI-version manager + process supervisor + JSON-RPC multiplexer (with a replay buffer) over an AF_UNIX socket. Clean-room, cross-platform, no telemetry.

A single-binary, themeable Claude Code statusLine — flat colored segments, smooth gradients, Nerd Font icons, and 7 built-in themes including Anthropic's own brand palette.

Agent workflows with full observability and time travel: watch every step live, rewind, fork, replay any run. Claude Code, Codex, Gemini, any model or harness.

pick any past Claude Code session via fzf, then resume it from the right cwd

Sync AI coding-agent configs (Claude Code, OpenCode, Codex, and more) from one canonical, committable source.

Vendor-neutral control plane for AI coding agents. Deterministic CLI surface for context fetch, verify, and progress. Stable in v1.0 for claude-code / codex / generic; cursor / gemini-cli experimental.

OpenSpec + Playwright Test Agents integration for automated E2E verification

Read-only VMware vCenter/ESXi monitoring — code-level enforced safety, zero destructive operations