--- title: "agent-starter-pack vs tma1" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/googlecloudplatform-agent-starter-pack-vs-tma1-ai-tma1" tools: ["googlecloudplatform-agent-starter-pack", "tma1-ai-tma1"] --- # agent-starter-pack vs tma1 *GraphCanon updated Sep 20, 2026* ## Verdict Pick agent-starter-pack if agent-starter-pack offers built-in CI/CD, evaluation tools, and observability for deploying generative AI agents on Google Cloud with Python; pick tma1 if tMA1 is specialized in local-first observability by tracking every LLM call and routing this information to the next agent turn via hooks and MCP. [agent-starter-pack](http://goo.gle/agents-cli) reports 6.6k GitHub stars, 1.5k forks, and 49 open issues, last pushed Jul 21, 2026. [tma1](https://tma1.ai/) has 117 stars, 14 forks, and 5 open issues, last pushed Sep 10, 2026. Figures are from public GitHub metadata via [agent-starter-pack's repository](https://github.com/GoogleCloudPlatform/agent-starter-pack) and [tma1's repository](https://github.com/tma1-ai/tma1). | | [agent-starter-pack](/tools/googlecloudplatform-agent-starter-pack.md) | [tma1](/tools/tma1-ai-tma1.md) | | --- | --- | --- | | Tagline | Ship AI Agents to Google Cloud in minutes with built-in CI/CD, evaluation, and observability | Local-first observability for AI agents with LLM call tracking | | Stars | 6,558 | 117 | | Forks | 1,500 | 14 | | Open issues | 49 | 5 | | Language | Python | Go | | Adopt for | agent-starter-pack offers built-in CI/CD, evaluation tools, and observability for deploying generative AI agents on Google Cloud with Python. | TMA1 is specialized in local-first observability by tracking every LLM call and routing this information to the next agent turn via hooks and MCP. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | TMA1 is available under the Apache-2.0 license, allowing for broad usage with attribution. | | Categories | AI Agents, Evaluation & Observability | AI Agents, Evaluation & Observability | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agent-starter-pack](/tools/googlecloudplatform-agent-starter-pack.md) | [tma1](/tools/tma1-ai-tma1.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Very active (96%) | | Days since push | 60d | 0d | | Open issues (now) | 49 | 5 | | Stars delta | +21 (30d) | +2 (30d) | | Open issues delta | 0 (30d) | -10 (30d) | | Full report | [trust report](/tools/googlecloudplatform-agent-starter-pack/trust.md) | [trust report](/tools/tma1-ai-tma1/trust.md) | ## Decision facts: agent-starter-pack - **Requirements:** Depends on Python 3.10+.; Requires the Google Cloud SDK for interacting with GCP services.; Terraform is needed for deployment purposes.; Make utility should be installed for development tasks. - **Adopt for:** agent-starter-pack offers built-in CI/CD, evaluation tools, and observability for deploying generative AI agents on Google Cloud with Python. ## Decision facts: tma1 - **Pricing:** freemium - Free open-source tool with no initial cost to use or modify according to its Apache-2.0 license. - **Requirements:** TMA1 requires an installation script that auto-configures and sets up GreptimeDB.; Operational requirements are platform-independent, as it supports macOS/Linux install scripts and a PowerShell one for Windows. - **Adopt for:** TMA1 is specialized in local-first observability by tracking every LLM call and routing this information to the next agent turn via hooks and MCP. - **License detail:** TMA1 is available under the Apache-2.0 license, allowing for broad usage with attribution. ## Choose when ### Choose agent-starter-pack if… - agent-starter-pack is primarily Python; tma1 is Go. - Requirements: Depends on Python 3.10+.; Requires the Google Cloud SDK for interacting with GCP services.; Terraform is needed for deployment purposes.; Make utility should be installed for development tasks.. - Tags unique to agent-starter-pack: agents, gcp, gemini, genai-agents. - You are working with Google Cloud and wish to deploy generative AI agents quickly using production-ready templates that come with integrated CI/CD pipelines. ### Choose tma1 if… - tma1 is primarily Go; agent-starter-pack is Python. - Pricing: Free open-source tool with no initial cost to use or modify according to its Apache-2.0 license.. - Requirements: TMA1 requires an installation script that auto-configures and sets up GreptimeDB.; Operational requirements are platform-independent, as it supports macOS/Linux install scripts and a PowerShell one for Windows.. - Tags unique to tma1: agent-observability, claude-code, codex, greptimedb. - Use TMA1 if you are operating self-hosted AI agents and require detailed observability over LLM calls that can be routed into subsequent turns for further action. ## When NOT to use agent-starter-pack - Your project is hosted on a cloud provider other than Google Cloud, as this tool is optimized for GCP services and uses Terraform specifically configured for deployment with it. - You do not need or want built-in CI/CD pipelines and evaluation tools, preferring to manage these components separately through different tools or self-configured setups. ## When NOT to use tma1 - Avoid TMA1 if you prefer cloud-based solutions or require real-time collaboration features that it does not inherently support due to its self-hosted nature. - Do not use TMA1 in environments sensitive to open ports, since it runs a local server and dashboard accessible at default localhost settings which may not suit all security policies. ## Common questions ### What is the difference between agent-starter-pack and tma1? agent-starter-pack: Ship AI Agents to Google Cloud in minutes with built-in CI/CD, evaluation, and observability. tma1: Local-first observability for AI agents with LLM call tracking. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-starter-pack over tma1? Choose agent-starter-pack over tma1 when agent-starter-pack is primarily Python; tma1 is Go; Requirements: Depends on Python 3.10+.; Requires the Google Cloud SDK for interacting with GCP services.; Terraform is needed for deployment purposes.; Make utility should be installed for development tasks.; Tags unique to agent-starter-pack: agents, gcp, gemini, genai-agents; You are working with Google Cloud and wish to deploy generative AI agents quickly using production-ready templates that come with integrated CI/CD pipelines. ### When should I choose tma1 over agent-starter-pack? Choose tma1 over agent-starter-pack when tma1 is primarily Go; agent-starter-pack is Python; Pricing: Free open-source tool with no initial cost to use or modify according to its Apache-2.0 license.; Requirements: TMA1 requires an installation script that auto-configures and sets up GreptimeDB.; Operational requirements are platform-independent, as it supports macOS/Linux install scripts and a PowerShell one for Windows.; Tags unique to tma1: agent-observability, claude-code, codex, greptimedb; Use TMA1 if you are operating self-hosted AI agents and require detailed observability over LLM calls that can be routed into subsequent turns for further action. ### When should I avoid agent-starter-pack? Your project is hosted on a cloud provider other than Google Cloud, as this tool is optimized for GCP services and uses Terraform specifically configured for deployment with it. You do not need or want built-in CI/CD pipelines and evaluation tools, preferring to manage these components separately through different tools or self-configured setups. ### When should I avoid tma1? Avoid TMA1 if you prefer cloud-based solutions or require real-time collaboration features that it does not inherently support due to its self-hosted nature. Do not use TMA1 in environments sensitive to open ports, since it runs a local server and dashboard accessible at default localhost settings which may not suit all security policies. ### Is agent-starter-pack or tma1 more popular on GitHub? agent-starter-pack has more GitHub stars (6,558 vs 117). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-starter-pack and tma1 open source? Yes - both are open-source projects on GitHub (agent-starter-pack: Apache-2.0, tma1: Apache-2.0). ### Where can I find alternatives to agent-starter-pack or tma1? GraphCanon lists graph-backed alternatives at [agent-starter-pack alternatives](/tools/googlecloudplatform-agent-starter-pack/alternatives) and [tma1 alternatives](/tools/tma1-ai-tma1/alternatives) ([agent-starter-pack markdown twin](/tools/googlecloudplatform-agent-starter-pack/alternatives.md), [tma1 markdown twin](/tools/tma1-ai-tma1/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/googlecloudplatform-agent-starter-pack-vs-tma1-ai-tma1.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agent-starter-pack or tma1? agent-starter-pack: Steady. tma1: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for agent-starter-pack and tma1? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-starter-pack trust report](/tools/googlecloudplatform-agent-starter-pack/trust); [tma1 trust report](/tools/tma1-ai-tma1/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=googlecloudplatform-agent-starter-pack`](/api/graphcanon/graph?tool=googlecloudplatform-agent-starter-pack) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_