Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
PythonMIT★ 5No key
Multi-model agent harness with orchestration, Claude Code compatibility, local LLM support, and live agent monitoring.
PythonMIT★ 3Few starsNo key
PythonMIT★ 4Few starsNo key
Async, Reliable Operations — async Python library for Check Point management/monitoring with a database-backed caching layer
PythonMIT★ 3Few starsNo key
Multi-agent fleet fabric on top of Hermes — A2A protocol + NATS event bus + Temporal durable workflows + Tier 2 VPS spawning. Run a fleet of specialist agents from one Telegram bot.
SkillMIT★ 3Few starsNo key
Controlled rolling-context conversation runtime for Claude. Stop your agent from running away with your bill.
PythonMIT★ 5No key
orchestrate AI coding agents as tmux nodes with a live dashboard. Spawn parallel workers, delegate tasks via API, monitor status with per-step activity logs. Supports OpenCode / Claude Code / bash age
SkillMIT★ 9No key
Jupyter notebook management and code execution backend
PythonBSD-3-Clause★ 7No key
MCP server for Juniper/JUNOS — show, upgrade with rollback, config push (commit confirmed) with safe dry-run defaults, RSI/SCF collection
PythonApache-2.0★ 1Few starsNo key
PythonMIT★ 2Few starsNo key
Research Prompt Optimization, Research Execution, Reconciliation
SkillApache-2.0★ 4Few starsNo key
AgentOS — a research operating system exploring skill composition in multi-agent systems: agents discover, compose, and adapt reusable skills into dependency-aware execution graphs, with OS-inspired p
SkillMIT★ 1Few starsNo key
A tool to scan skills files for dangerous patterns & malicious intent
SkillMIT★ 1Few starsNo key
PythonMIT★ 1Few starsNo key
Architected a Recursive Language Model (RLM) framework in LangGraph, using a Prime Agent supervisor to decompose complex queries into multi-hop execution trees.
PythonMIT★ 1Few starsNo key
PythonMIT★ 3Few starsNo key
Multi-agent orchestration framework: parallel research, consensus voting (ACE), and DQ scoring. 212 tests, pip-installable.
PythonMITFew starsNo key
ὅραμα: The complete agent methodology for solving impossible problems with elegance.
SkillMITFew starsNo key
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
PythonMIT★ 4Few starsNo key
Graph-based workflow orchestration with a Model Context Protocol server
PythonMITFew starsNo key
A clean, modular framework for building AI agents with Claude, featuring MCP integration, web search capabilities, and Google Drive integration
PythonMIT★ 1Few starsNo key
Who stands behind it