Terradev

MCP.Pizza Chef: theoddden

Terradev is a command-line tool that helps you manage and run AI training, inference, and other workloads across different cloud GPUs and providers. You can use it to create AI agents, manage vector databases, and optimize resource use. It works by running commands in your terminal and does not require external accounts. Setup requires some technical skill, but it gives you control over complex AI tasks from one place.

Coding
Other

Use This MCP server To

Orchestrate AI model training across multiple cloud GPUs Run and manage AI inference services with cost analytics Create and chat with AI agents that remember past conversations Manage vector databases and perform similarity searches Run local optimized AI training with reduced VRAM usage Store and sync cloud API secrets securely for AI workflows Set up API gateways compatible with OpenAI and Anthropic

README

Terradev CLI v6.0.10

Cross-cloud GPU infrastructure CLI for training, inference, and AI workload orchestration with agent sandbox, mesh, and MCP subcommands.

Terradev Demo

License: Apache 2.0 - Free and open source for commercial and personal use.

https://terradev.cloud/

Terradev is a cross-cloud compute control plane for AI workloads, not just a provisioning wrapper.

Combines quoting, provisioning, topology optimization, training orchestration, inference tuning, and cost analytics in one CLI, with a Rust-accelerated idempotent runtime underneath.

Continued focus on lower cost, faster provisioning, and topology-aware execution with local credential storage.

Model agnostic. Dataset agnostic. GPU agnostic. Provider agnostic. The only thing Terradev is not agnostic about is correctness: it enforces topology, idempotency, and sequencing.

NOTES ON 6.0.8

  • New agent subcommands — terradev agent sandbox, terradev agent mesh, and terradev agent mcp are now real, dependency-resolving commands instead of placeholders:
    • terradev agent sandbox runs untrusted payloads with hardware-isolated runtimes (bwrap, runsc, firecracker, and Linux Landlock LSM), all discoverable/downloadable via DependencyManager.
    • terradev agent mesh creates a decentralized peer-to-peer agent mesh using real libp2p (go-libp2p-daemon + p2pclient), A2A HTTP, and WireGuard encrypted transports.
    • terradev agent mcp is a dynamic Model Context Protocol bridge with stdio and HTTP transports and a multi-server bridge.

NOTES ON 6.0.0

  • Unsloth (terradev train unsloth): optimized local LLM training, serving, and coding agents with 70% lower VRAM usage and faster training via Triton kernels. Subcommands: run, start, stop.

    • terradev train unsloth run --model unsloth/Llama-3.1-8B
    • terradev train unsloth run --model unsloth/Qwen3.6-7B-GGUF:Q4_K_M --port 8080
    • terradev train unsloth start claude --model unsloth/Llama-3.1-8B
    • terradev train unsloth stop
  • Weaviate (terradev database weaviate): vector database operations with local, embedded, cloud, and custom environments. Subcommands: up, list-collections, create-collection, delete-collection, insert, query, hybrid-search.

    • terradev database weaviate up --environment local
    • terradev database weaviate create-collection --name Article --vector-size 384
    • terradev database weaviate insert --collection Article --objects '[{"properties": {"title": "Hello"}, "vector": [0.1, ...]}]'
    • terradev database weaviate query --collection Article --vector '[0.1, ...]' --top-k 5
    • terradev database weaviate hybrid-search --collection Article --query "generative AI" --top-k 5
  • Letta (terradev agent letta): stateful agents with long-horizon memory across sessions. Subcommands: create, list, chat, status, delete, remember.

    • terradev agent letta create --name my-agent --model openai/gpt-4.1
    • terradev agent letta list
    • terradev agent letta chat --agent-id <id> --message "hello"
    • terradev agent letta remember --agent-id <id> --text "Our staging cluster is on us-east-1" --label fact
    • terradev agent letta status --agent-id <id>
    • terradev agent letta delete --agent-id <id>
  • Removed integrations: terradev ml databricks and terradev ml langsmith command groups, all related MCP tools, and Jaeger tracing endpoints in the Helm values have been removed.

  • Version bumped to 6.0.0 to reflect these breaking changes.

NOTES ON 5.7.10

  • Local Ollama integration (terradev ml ollama): list, pull, generate, chat, inspect, and check running models on a local Ollama server (list, pull, generate, chat, info, ps).
  • DeepEval integration (terradev ml deepeval): install, run test suites, list metrics, and evaluate single LLM outputs with metrics like AnswerRelevancyMetric, FaithfulnessMetric, and HallucinationMetric (install, init, run, metrics, evaluate).
  • MCP tool surface now at 237 tools, including ollama_* and deepeval_* tool definitions and handlers.

NOTES ON 5.7.7

Terradev FAQ

Can I use Terradev to manage AI training and inference workloads?
Yes — Terradev lets you orchestrate AI training, inference, and workload management across multiple cloud GPUs from a command line.
Can I use Terradev to run local AI agents with memory?
Yes — it supports creating and chatting with stateful agents that remember information across sessions.
Does Terradev require an API key or account to use?
No — Terradev is open source and runs locally or on your cloud infrastructure without needing external accounts.
Which apps or clients work with Terradev?
Terradev is a command-line tool primarily for developers; it does not directly integrate with consumer chat apps like ChatGPT or Claude.
How hard is it to set up Terradev?
Setup is developer-level — you need to install via pip and run commands in a terminal.
Can Terradev connect to multiple cloud providers?
Yes — it is cloud and GPU agnostic, supporting many providers for AI workloads.
Does Terradev support vector databases?
Yes — it can manage vector stores like Weaviate and perform searches from the CLI.