--- title: "future-agi vs gateway" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/future-agi-future-agi-vs-portkey-ai-gateway" tools: ["future-agi-future-agi", "portkey-ai-gateway"] --- # future-agi vs gateway *GraphCanon updated Sep 20, 2026* ## Verdict Pick future-agi if future-AGI is an open-source platform for evaluating and observing LLM and AI agent applications, offering features like tracing, evaluations, simulations, and guardrails. It is self-hostable and supports deployment via,; pick gateway if a high-performance AI Gateway named 'gateway', supporting over 1,600 LLM connections and featuring various guardrail mechanisms for safer utilization. [future-agi](https://futureagi.com) reports 2.0k GitHub stars, 627 forks, and 961 open issues, last pushed Sep 18, 2026. [gateway](https://portkey.ai/features/ai-gateway) has 13k stars, 1.3k forks, and 258 open issues, last pushed May 25, 2026. Figures are from public GitHub metadata via [future-agi's repository](https://github.com/future-agi/future-agi) and [gateway's repository](https://github.com/Portkey-AI/gateway). | | [future-agi](/tools/future-agi-future-agi.md) | [gateway](/tools/portkey-ai-gateway.md) | | --- | --- | --- | | Tagline | Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications | A high-performance AI Gateway connecting to over 1,600 LLMs with guardrails. | | Stars | 2,032 | 12,920 | | Forks | 627 | 1,293 | | Open issues | 961 | 258 | | Language | Python | TypeScript | | Adopt for | Future-AGI is an open-source platform for evaluating and observing LLM and AI agent applications, offering features like tracing, evaluations, simulations, and guardrails. It is self-hostable and supports deployment via, | A high-performance AI Gateway named 'gateway', supporting over 1,600 LLM connections and featuring various guardrail mechanisms for safer utilization. | | Persona | - | - | | Runtime | - | - | | License | Apache License 2.0, allowing for free use, modification, and distribution of the software, with the condition that any derivative works also be licensed under the same terms. | MIT | | Categories | AI Agents, Evaluation & Observability, LLM Frameworks | Evaluation & Observability, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [future-agi](/tools/future-agi-future-agi.md) | [gateway](/tools/portkey-ai-gateway.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Slowing (36%) | | Days since push | 0d | 104d | | Open issues (now) | 961 | 258 | | Stars delta | +473 (30d) | +252 (30d) | | Open issues delta | +365 (30d) | +16 (30d) | | Full report | [trust report](/tools/future-agi-future-agi/trust.md) | [trust report](/tools/portkey-ai-gateway/trust.md) | ## Decision facts: future-agi - **Pricing:** freemium - The core platform is free and open-source under the Apache License 2.0. However, for managed services or additional support, contact sales for pricing. - **Requirements:** Min 4 GB RAM; Requires Docker; Future-AGI requires Docker for deployment, with support for Docker Compose and upcoming Kubernetes and Helm support.; For production environments, a setup script is provided to generate secrets and pin image tags, ensuring a secure and reproducible deployment. - **Adopt for:** Future-AGI is an open-source platform for evaluating and observing LLM and AI agent applications, offering features like tracing, evaluations, simulations, and guardrails. It is self-hostable and supports deployment via, - **License detail:** Apache License 2.0, allowing for free use, modification, and distribution of the software, with the condition that any derivative works also be licensed under the same terms. ## Decision facts: gateway - **Pricing:** unknown - The service is open source and MIT licensed; specific pricing for related services (if any) not detailed in repository. - **Requirements:** Developed using TypeScript; no Docker requirement specified for operation or development. - **Adopt for:** A high-performance AI Gateway named 'gateway', supporting over 1,600 LLM connections and featuring various guardrail mechanisms for safer utilization. ## Choose when ### Choose future-agi if… - future-agi is primarily Python; gateway is TypeScript. - License: future-agi is Apache-2.0, gateway is MIT. - Pricing: The core platform is free and open-source under the Apache License 2.0. However, for managed services or additional support, contact sales for pricing.. - Requirements: Min 4 GB RAM; Requires Docker; Future-AGI requires Docker for deployment, with support for Docker Compose and upcoming Kubernetes and Helm support.; For production environments, a setup script is provided to generate secrets and pin image tags, ensuring a secure and reproducible deployment.. - Tags unique to future-agi: ai-agents, ai-evals, ai-optimization, ai-simulations. - Also covers AI Agents. - You need a self-hostable solution that does not phone home, ensuring full control over your data and evaluation logic. ### Choose gateway if… - gateway is primarily TypeScript; future-agi is Python. - License: gateway is MIT, future-agi is Apache-2.0. - Pricing: The service is open source and MIT licensed; specific pricing for related services (if any) not detailed in repository.. - Requirements: Developed using TypeScript; no Docker requirement specified for operation or development.. - Tags unique to gateway: gateway, generative-ai, langchain, llm. - Use gateway when you need a versatile platform capable of connecting to more than 1,600 LLM providers. ## When NOT to use future-agi - You require immediate Kubernetes or Helm support, as these are not yet available, though they are in development. - You are seeking a managed service or a solution available through AWS Marketplace, as these options are not yet available, though they are planned for the future. - Your project is in a highly dynamic environment where frequent updates and vendor support are critical, as Future-AGI is a community-driven project with a focus on self-hosting and open-source. ## When NOT to use gateway - Avoid using gateway if your application only requires connection to a limited number of LLM providers, as its extensive provider support might introduce unnecessary complexity. - If you don't require sophisticated cost management features such as smart caching or usage analytics provided by the tool, consider simpler alternatives. ## Common questions ### What is the difference between future-agi and gateway? future-agi: Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. gateway: A high-performance AI Gateway connecting to over 1,600 LLMs with guardrails.. See the comparison table for live GitHub stats and shared categories. ### When should I choose future-agi over gateway? Choose future-agi over gateway when future-agi is primarily Python; gateway is TypeScript; License: future-agi is Apache-2.0, gateway is MIT; Pricing: The core platform is free and open-source under the Apache License 2.0. However, for managed services or additional support, contact sales for pricing.; Requirements: Min 4 GB RAM; Requires Docker; Future-AGI requires Docker for deployment, with support for Docker Compose and upcoming Kubernetes and Helm support.; For production environments, a setup script is provided to generate secrets and pin image tags, ensuring a secure and reproducible deployment.; Tags unique to future-agi: ai-agents, ai-evals, ai-optimization, ai-simulations; Also covers AI Agents; You need a self-hostable solution that does not phone home, ensuring full control over your data and evaluation logic. ### When should I choose gateway over future-agi? Choose gateway over future-agi when gateway is primarily TypeScript; future-agi is Python; License: gateway is MIT, future-agi is Apache-2.0; Pricing: The service is open source and MIT licensed; specific pricing for related services (if any) not detailed in repository.; Requirements: Developed using TypeScript; no Docker requirement specified for operation or development.; Tags unique to gateway: gateway, generative-ai, langchain, llm; Use gateway when you need a versatile platform capable of connecting to more than 1,600 LLM providers. ### When should I avoid future-agi? You require immediate Kubernetes or Helm support, as these are not yet available, though they are in development. You are seeking a managed service or a solution available through AWS Marketplace, as these options are not yet available, though they are planned for the future. Your project is in a highly dynamic environment where frequent updates and vendor support are critical, as Future-AGI is a community-driven project with a focus on self-hosting and open-source. ### When should I avoid gateway? Avoid using gateway if your application only requires connection to a limited number of LLM providers, as its extensive provider support might introduce unnecessary complexity. If you don't require sophisticated cost management features such as smart caching or usage analytics provided by the tool, consider simpler alternatives. ### Is future-agi or gateway more popular on GitHub? gateway has more GitHub stars (12,920 vs 2,032). Stars measure visibility, not whether either tool fits your constraints. ### Are future-agi and gateway open source? Yes - both are open-source projects on GitHub (future-agi: Apache-2.0, gateway: MIT). ### Where can I find alternatives to future-agi or gateway? GraphCanon lists graph-backed alternatives at [future-agi alternatives](/tools/future-agi-future-agi/alternatives) and [gateway alternatives](/tools/portkey-ai-gateway/alternatives) ([future-agi markdown twin](/tools/future-agi-future-agi/alternatives.md), [gateway markdown twin](/tools/portkey-ai-gateway/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/future-agi-future-agi-vs-portkey-ai-gateway.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, future-agi or gateway? future-agi: Very active. gateway: Slowing. 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 future-agi and gateway? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [future-agi trust report](/tools/future-agi-future-agi/trust); [gateway trust report](/tools/portkey-ai-gateway/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=future-agi-future-agi`](/api/graphcanon/graph?tool=future-agi-future-agi) - 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/_