29 agent skills for firewall and network-security work: parsing, auditing, converting and diffing Cisco, Fortinet, Palo Alto and Juniper SRX configs, SRX operational playbooks, compliance and STIG evidence mapping, plus Proxmox deployment guides.
Open source. Open possibilities.
Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONshadok-ai is a multi-agent cockpit for running parallel Claude Code sessions in isolated git worktrees, featuring scheduled prompts, Telegram integration, and deterministic guardrails.
A plugin that automatically processes Jira issues from branch creation through design, implementation, testing, review, and local merge inside Claude Code, recording each step to Jira. It runs multiple issues as a queue and isolates only failures for review via an exception report.
VibeCoder is an automated GitHub issue worker that monitors repositories, picks up issues, writes code using AI agents (Claude, Codex, Gemini), runs quality checks, and opens pull requests. It supports review feedback loops, self-healing, and cost optimization.
Hermes Agent is a self-improving AI agent from Nous Research. It creates and refines skills from experience, keeps persistent memory, searches past conversations, runs through CLI and messaging platforms, and works with any LLM provider.
A Python CLI and MCP server that reads a git diff against a CodeGraph index and returns a short ranked list of the user journeys a change could have broken, instead of re-running every test. Recall-first, driven by a journey registry and guarded against stale indexes.
CowAgent is an open-source AI assistant and agent harness that plans tasks, runs tools and skills, and builds memory and knowledge. It supports multi-agent teams, multiple LLM providers, and channels like Web, WeChat, Telegram and Slack, with one-line install.
postbag lets any two Claude Code or Codex sessions on the same machine exchange letters: each letter is delivered through the vendor's own wake-up door, recorded in one ledger, and counted against a human-set letter budget. Pure Python standard library, no daemon, polling or hooks.
Claude-first paid-media operations skill for Claude Code covering 12 ad platforms. Provides source-grounded audits, deterministic scoring, versioned JSON reports, and capability-gated account changes with read-only defaults and safety gates.