Trytet
@bneb
About Trytet
Wasm sandbox runtime for AI agent code execution. Executes JavaScript, regex, JMESPath, and SQL inside fuel-metered WebAssembly cartridges. Infinite loops trap in microseconds instead of hanging — deterministic failure for LLM-generated code.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"trytet": {
"command": "tet",
"args": [
"mcp"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Trytet?
Trytet is a deterministic WebAssembly sandbox for agentic workloads. It ensures that agents calling solvers never hang, using fuel-bounded traps, live state migration, and O(1) teardown. Built in Rust with sub‑200µs cold starts, it targets developers who need safe, high‑performance execution of untrusted agent code.
How to use Trytet?
Install the CLI with curl -sL https://trytet.io/install.sh | bash. Run tet mcp for an interactive demo, or build and execute your own agent with tet build agent.ts -o agent.tet followed by tet up agent.tet --fuel 1000000. A dashboard is available at http://localhost:3000/console.
Key features of Trytet
- Neuro‑Symbolic Cartridges: deterministic Wasm solvers in fuel‑bounded sub‑sandboxes.
- Teleportation: serialize agent state into
.tetartifacts for P2P transfer. - Copy‑on‑Write VFS: isolated vector file system with sub‑1µs reads.
- Market Scheduling: elastic resource market using Fuel Vouchers.
- Fuel Determinism: strict instruction‑level fuel limits trap infinite loops.
- Consensus Locks: O(1) multi‑phase commit prevents double‑execution during migration.
- Path Jailing: host filesystem isolation and OOB bounds checking.
Use cases of Trytet
- Run untrusted agent solvers with guaranteed deterministic execution.
- Migrate live agent state between nodes without downtime.
- Execute inference or constraint‑checking workloads under strict fuel budgets.
- Build high‑density agent sandboxes with 5MB per‑agent overhead.
FAQ from Trytet
How does Trytet prevent infinite loops?
Strict instruction‑level fuel limits trap infinite loops instead of timing them out, ensuring deterministic teardown.
What is teleportation in Trytet?
Teleportation serializes the full agent state into a .tet artifact, transfers it over P2P, and revives it on a remote node.
How do I install Trytet?
Run curl -sL https://trytet.io/install.sh | bash to install the CLI, then use tet commands.
What is the cold start time?
Trytet achieves sub‑200µs cold start, significantly faster than Docker or V8 isolates.
What language is Trytet built in?
Trytet is built in Rust using the Component Model for WebAssembly.
More AI & Agents MCP servers
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
Gemini MCP Server
aliargunMCP server implementation for Google's Gemini API
Unreal Engine Generative AI Support Plugin
prajwalshettydevUnreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti
MCP-LLM Bridge
patruffBridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
Sequential Thinking Multi-Agent System (MAS)
FradSerAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
Comments