MCP servers and skills: search, filter by where they run, and compare.
A desktop AI coding assistant. Open a project folder, describe a task, and Patch reads the code, edits files, runs commands and checks its work, asking for your approval before it changes anything.
SkillApache-2.0★ 2Few starsNo key
#sinaida-skill ✨ multi-model claude plugin that routes creative and technical work to the ai model that fits each task
SkillApache-2.0★ 5No key
A Claude Agent Skill that humanizes AI-written marketing and long-form copy: landing pages, sales pages, e-books, case studies, founder notes. Removes AI tells and process bleed, de-slops prose, strip
SkillApache-2.0★ 9No key
Interface-independent task router for AI agents — directive-driven model routing with MCP + CLI
SkillApache-2.0★ 2Few starsNo key
Stop burning your AI limits. MCP server that delegates coding and sysops work to any cheaper agent or local LLM via durable background queues — git-worktree isolation, server-enforced guardrails, clar
PythonApache-2.0★ 2Few starsNo key
One engine under your coding agents — Claude Code, Antigravity & OpenCode with a shared brain, a Conductor that routes each task to the best model, and one session history across desktop, terminal, an
SkillApache-2.0★ 2Few starsNo key
An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.
Node.jsApache-2.0★ 1.5kNo key
Installer for Claude Code per-model commands, agents and skills
SkillApache-2.0★ 2Few starsNo key
The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s done. You come back to a receipt of every step, every decis
Node.jsApache-2.0★ 62No key
Vigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't b
SkillApache-2.0★ 41No key
Cost governance for Massive Intelligence (IM) agent orchestration: hard per-request, per-task, and per-day USD budgets with depletion events, pre-flight cost forecasting, prefix-cache break-even plann
Node.jsApache-2.0★ 1Few starsNo key
Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)
SkillApache-2.0★ 97No key
Independently-verified multi-agent delivery for any task. A Caster picks the crew, and every workstream passes a mandatory honesty gate. Runs on Claude Code, Codex, Gemini, and CodeWhale.
SkillApache-2.0★ 5No key
Who stands behind it
