MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Self-hosted AI agent that can't say "done" without proof — evidence-gated task contracts, self-distilled skills with auto-rollback, multi-channel.
Node.jsMIT★ 3Few starsNo key
Claude Code plugin: give every subagent a model and effort level sized to its task.
SkillMITFew starsNo key
Let Claude Code pick the reasoning effort for each task - a plugin that routes hard work to high/max-effort subagents.
SkillMITFew starsNo key
MemoryOS is a powerful personal knowledge base that combines traditional **RAG (Vector Search)** with a **High-Fidelity Knowledge Graph**. It doesn't just store your notes; it understands the structur
SkillMIT★ 1Few starsNo key
Autonomous multi-agent software factory with parallel task dispatch, Kanban pipeline, isolated Git worktrees, and automated code review.
SkillApache-2.0★ 2Few starsNo key
Generic Codex orchestration with deterministic TaskGraphs, bounded parallelism, model routing, and targeted review remediation.
SkillApache-2.0★ 7No key
A lightweight multimodal task runner for delegating text, image, and workspace work to Codex.
SkillMIT★ 3Few starsNo key
Local, host-agnostic adversarial code review for Claude Code -- auto-triggers on every prompt and task-list update, patches critical flaws in place, ignores nits.
SkillMIT★ 1Few starsNo key
Clickup toolkit for terminals, coding assistants, and bots.
Node.jsMITFew starsNo key
LeanRigor is an open-source control plane that classifies coding-task risk, selects a Fast, Standard, or Rigorous workflow, and enforces planning, approvals, validation evidence, review and safe integ
SkillMIT★ 1Few starsNo key
Quality-first model + effort routing for Claude Code: four pinned subagents, re-routed at every checkpoint mid-task
SkillMITFew starsNo key
Calibrated pairing with a peer LLM (Codex/GPT-5.x) for Claude Code — sizes the peer's model + reasoning effort to the task instead of always running at max.
SkillMITFew starsNo key
Task-monitoring notification plugin for DeepSeek Harness (dsh): turn/end alerts, human-confirmation with timeout escalation, SAPI voice, HTTP/A2A/MCP channels — zero-dependency build-free bundle
SkillMIT★ 2Few starsNo key
Architect-as-orchestrator plugin for Claude Code: Fable/Opus architect, Grok 4.5 default implementer with Sonnet rate-limit fallback, Opus per-task-effort lanes (fork of DannyMac180/fable-advisor)
SkillMIT★ 1Few starsNo key
Item-by-item inventory that reorders itself: per-SKU forecasts, automatic purchase orders, supplier email and delivery ETAs. REST API, MCP server, dashboard. Zero dependencies.
DockerMIT★ 1Few starsNo key
A Claude Code skill that runs code-changing tasks with reviewed plans, controlled multi-agent edits, and evidence-backed verification — no review theater.
SkillMIT★ 1Few starsNo key
The AI-powered workspace that automatically transforms raw Git commits into polished, platform-native release notes.
SkillApache-2.0★ 2Few starsNo key
Claude Code plugin that turns a plain-English request into a reviewed, executed, merged git branch — routes to specialist agents, runs adversarial review loops, decomposes into an independent task DAG
SkillMIT★ 1Few starsNo key
A PDF Editor w/Crypto Sign - 'am adding a self improving AI Agent, Simple Fill & Sign, MCP server, Browsing & Email Automations, File Worker...
Node.jsMITFew starsNo key
Ranks your installed Claude Code skills/agents for a task and routes to the best one — and learns from your ratings.
SkillMIT★ 1Few starsNo key
Ultra mode for GitHub Copilot CLI: maximum reasoning depth with automatic task delegation, modeled on Codex's ReasoningEffort::Ultra and Claude Code's /effort ultracode.
SkillMIT★ 1Few starsNo key
Effect gate for AI agents. An agent asks before it charges a card, ships a deploy, or sends the email, and gets back a durable decision — so the same real-world action is attempted at most once. Ratch
Node.jsApache-2.0Few starsNeeds a key
Intelligent 3-tier task routing and active uncertainty fallback (Antiback) for Google Antigravity IDE. Powered by native Kev-0.8B (System One) and deterministic heuristics.
SkillMIT★ 1Few starsNo key
mcp for https://tradingeconomics.com/calendar
PythonMIT★ 8No key
Who stands behind it
