Agenvoy

Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and s…

LLM Mart 0 views 5 listing impressions
Transport
Not stated
Package
—
Registry id
—

No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.

Agenvoy is a self-hosted AI agent harness that builds, tests, and reuses tools from a single sentence. The agent automatically generates a tool when none exists, writing and testing the script in a sandbox before registering it. In server mode, Agenvoy shares all sandboxed tools with MCP clients like Claude Code and Codex, which can also auto-build new tools.

All commands and scripts are executed in an OS-native sandbox, using bubblewrap on Linux and sandbox-exec on macOS. The agent rewrites failed tools, sandbox-tests the fix, and retains the outcome across sessions. Agenvoy supports eleven model providers and any OpenAI-compatible endpoint, with automatic routing to the best model.

Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.

Related servers

Semantic search over free-to-use stock photos from 9 libraries: by words, image, or similar.

25 views

Korean apartment data: 45,000+ complexes, official prices, jeonse ratios, AI forecasts.

25 views

Universal MCP Server with advanced AI memory capabilities and semantic search.

24 views

Let Codex orchestrate external coding agents through their native harnesses.

23 views