Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
Repository
Repository di mvanhorn
A HTTP credential proxy and vault for AI agents
(1 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
mvanhorn/agentaTypeScript
The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
Disposable CLA-mode aggressive verification repo (plan 006). Archived after run.
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
Disposable DCO-mode aggressive verification repo (plan 006). Archived after run.
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
Plan 008 launch-dogfood test repo (CLA mode). Disposable; archived after run.
(1 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
DCO mode dogfood - U4
(1 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
Launch-readiness dry-run dogfood (plan 2026-04-28-003). Archived after evidence captured.
(1 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
Smoke test for agentcla.dev public-repo end-to-end run on 2026-04-26. Disposable; archived after run.
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
Your agent runs on a Mac that isn't your daily driver. agentcookie keeps its sessions in sync with the Mac you actually browse on, continuously, encrypted over Tailscale, so OpenClaw, Hermes, or any other agent runtime wakes up authenticated. macOS, peer-to-peer, no cloud middleman.
(775 star) (64 fork) (0 issue indicizzate) (0 good first issue aperte)
mvanhorn/agentevalsPython
Readymade evaluators for agent trajectories
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
mvanhorn/agentglassTypeScript
🛰 A loupe for your agents — a real-time Mission-Control dashboard and workspace for AI coding agents, across every provider and every project on your machine
(1 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
GitHub is for humans. AgentHub is for agents. First use case is for autoresearch but it's a lot more general than that. Exploratory project.
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
(1 star) (1 fork) (0 issue indicizzate) (0 good first issue aperte)
mvanhorn/agentkitTypeScript
Every AI Agent deserves a wallet.
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
Email gateway that opens a Claude Code session per inbound AgentMail message (cmux or Ghostty)
(48 star) (6 fork) (0 issue indicizzate) (0 good first issue aperte)
mvanhorn/agentmemoryTypeScript
#1 Persistent memory for AI coding agents based on real-world benchmarks
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
mvanhorn/agentpulseTypeScript
Real-time monitoring dashboard for AI coding agent sessions (Claude Code + Codex CLI)
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
mvanhorn/agentsPython
A framework for building realtime voice AI agents 🤖🎙️📹
(1 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)
AgentScope Java: Agent-Oriented Programming for Building LLM Applications
(0 star) (0 fork) (0 issue indicizzate) (0 good first issue aperte)