C

claude

Yet another software engineering agent orchestration system. This time with a mythical theme. Originally designed for Claude Code, now with support for OpenCode, Github Copilot, and OpenAI Codex.

My AI-generated web site, an ongoing experiment.

ADHD-friendly productivity app: brain-dump tasks, let AI break them into tiny steps, schedule to your calendar, focus with a Pomodoro style visual timer, and earn rewards & streaks.

Specification graph manager for AI-augmented projects, on the nomograph-claim substrate.

💬 Epic prompts to turbo-charge your LLM chatbots.

Run Claude Code in a Sublime Text panel with live highlighting of the files it edits, plus optional rsync-over-SSH project sync.

Local claude session sandbox: kind cluster plus per-session pods running the published config-baked sandbox image.

AI toolchain configuration as che profiles: claude, codex, ollama, the shared agent prose payload and the LLM-backed git wrappers.

Fix agent reliability issues in GitLab CI/CD across Claude Agent SDK, OpenAI Agents SDK, Google ADK, MCP, LangChain, LangGraph, CrewAI, AutoGen AG2, Pydantic AI, and Vercel AI. Gates pipelines on risk and severity.

https://github.com/trustabl/trustabl

My opinionated Claude Code config. No—I do not vibe code nor will I ever pay for these services, however some clients provide access and request that I work with it.

MCP-native browser automation server — 62 composite tools, 153 CLI subcommands, zero config. Give AI agents full browser control via the Model Context Protocol. Navigate, interact, extract text/HTML/screenshots, debug network, manage sessions, visual diffing, React inspection, auth vault, HAR recording. Works with Claude, Copilot, VS Code, Cursor. Built on Playwright/Chromium. The most comprehensive browser MCP server available.

Self-hosted MCP gateway. Connects Claude, ChatGPT, Codex and other AI agents to Jira, GitLab, Notion, Google Workspace and 25 more tools. Pre-integrated, GDPR-ready, with PII sanitization, write-safety, and audit logging.

ask multivac_

multivac.ulm0.com

Options trading analytics — backtest stats, walk-forward analysis, Monte Carlo, risk metrics. Web dashboard at tradeblocks.io | MCP server on npm | Docker: romeo345/tradeblocks-mcp

Local-first, provider-agnostic archive of AI conversations (ChatGPT, Claude, Gemini, Codex) — immutable, content-addressed, searchable evidence layer built in Elixir/Ecto.

Describe an AI agent, get a ready-to-run agent home with persona, memory and a growth loop. Build one agent or a whole collaborating team.

Claude Code in Docker. Drop-in OpenAI-compatible API, MCP server, Telegram bot, and CLI — five interfaces, one image. Persistent sessions, file ops, always-on skill injection, and a full dev toolchain (Go, Python, Node, K8s, Terraform, databases) or a minimal image with just the basics.

My personal Claude Code skills, kept in one repo so they're available in every project.

Pi extension wrapping Vladimir Glafirov's gitlab-ai-provider. Exposes GitLab Duo's AIGW catalog to Pi with two routing paths: agenticChat (full tool calling) and workflowChat (Bedrock + Vertex compliance routing of Claude).

Agent-shape testing harness that measures how an LLM-driven agent uses a tool's CLI, scored by an LLM judge.