Runtm
Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.
Updated
✨ Try AgentScout's free AI image generator →Good for: writing code, evaluating agents, running code safely
Use cases
About Runtm
Runtm is listed in our evals & observability category and is aimed at builders. Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software. Pricing, as the maker states it: See site. Maturity: Active. We last checked the official link on 2026-11-11.
Runtm at a glance
- Category: Evals & observability
- Built for: Developers and teams building with AI agents
- Pricing: Not verified yet: see the official site
- GitHub: runtm-ai/runtm · 304 stars (as of Nov 11, 2026)
- Official site: runtm.com
- Listed on AgentScout: Nov 11, 2026
Runtm FAQ
What is Runtm?
Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.
How much does Runtm cost?
AgentScout hasn't verified Runtm's pricing yet, so we don't list a price. Check the official site (runtm.com) for current plans.
Where can I find Runtm's source code?
On GitHub at runtm-ai/runtm, which had 304 stars as of Nov 11, 2026.
What are alternatives to Runtm?
Similar tools include Codeburn, Tokentelemetry, CoreWeave Forge, Plurai, Waku Agent and GEPA.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
Runtm ratings and reviews
Be the first to rate Runtm: tap 1 to 5 stars below. A written review is optional.
Runtm alternatives
Other evals & observability tools in our directory. See all evals & observability tools →
Codeburn
Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
Tokentelemetry
Token telemetry dashboard for AI autonomous and coding agents — tracks tokens, sessions, tool calls & reasoning across Hermes agent, Claude Code, Antigravity CLI, Codex & more. 100% local.
CoreWeave Forge
One product to run, observe, evaluate and post-train agents (W&B, OpenPipe, sandboxes).
Plurai
Plurai is a simulation and post-training layer that runs an agent through scenarios so later runs get sharper. The homepage shows a plugin install for Claude Code, GitHub Copilot CLI, OpenAI Codex and Cursor. Hosted use is offered through a demo rather than a public rate card, so this listing does not state a price.
Waku Agent
Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows
GEPA
GEPA is an MIT library for optimizing text you can score, including prompts, code and agent architectures, by letting a model reflect on what failed and searching for better variants. The docs site is the project homepage. GitHub listed 7,513 stars on gepa-ai/gepa on 20 Nov 2026.