--- title: "kalliope vs agents-from-scratch" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/kalliope-project-kalliope-vs-pguso-agents-from-scratch" tools: ["kalliope-project-kalliope", "pguso-agents-from-scratch"] --- # kalliope vs agents-from-scratch *GraphCanon updated Aug 12, 2026* ## Verdict Pick kalliope if kalliope is an open-source Python framework designed for the development of customizable personal assistants, featuring robust speech recognition and synthesis capabilities; pick agents-from-scratch if agents-from-scratch is for those who want absolute control over their AI agent development using only local resources and Python, focusing on deep learning without relying on external frameworks or cloud dependencies. [kalliope](https://kalliope-project.github.io/) reports 1.8k GitHub stars, 231 forks, and 27 open issues, last pushed Jul 2, 2023. [agents-from-scratch](https://github.com/pguso/agents-from-scratch) has 954 stars, 240 forks, and 3 open issues, last pushed Jul 25, 2026. Figures are from public GitHub metadata via [kalliope's repository](https://github.com/kalliope-project/kalliope) and [agents-from-scratch's repository](https://github.com/pguso/agents-from-scratch). | | [kalliope](/tools/kalliope-project-kalliope.md) | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | | --- | --- | --- | | Tagline | A framework for creating personal assistants | Build AI agents locally without relying on frameworks or cloud APIs. | | Stars | 1,768 | 954 | | Forks | 231 | 240 | | Open issues | 27 | 3 | | Language | Python | Python | | Adopt for | Kalliope is an open-source Python framework designed for the development of customizable personal assistants, featuring robust speech recognition and synthesis capabilities. | agents-from-scratch is for those who want absolute control over their AI agent development using only local resources and Python, focusing on deep learning without relying on external frameworks or cloud dependencies. | | Persona | - | - | | Runtime | - | - | | License | GPL-3.0 | MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes. | | Categories | AI Agents, Speech & Audio | AI Agents, Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [kalliope](/tools/kalliope-project-kalliope.md) | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Active (82%) | | Days since push | 1124d | 18d | | Open issues (now) | 27 | 3 | | Owner type | Organization | User | | Full report | [trust report](/tools/kalliope-project-kalliope/trust.md) | [trust report](/tools/pguso-agents-from-scratch/trust.md) | ## Decision facts: kalliope - **Adopt for:** Kalliope is an open-source Python framework designed for the development of customizable personal assistants, featuring robust speech recognition and synthesis capabilities. ## Decision facts: agents-from-scratch - **Requirements:** Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs. - **Adopt for:** agents-from-scratch is for those who want absolute control over their AI agent development using only local resources and Python, focusing on deep learning without relying on external frameworks or cloud dependencies. - **License detail:** MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes. ## Choose when ### Choose kalliope if… - License: kalliope is GPL-3.0, agents-from-scratch is MIT. - Tags unique to kalliope: bot-creation, personal-assistant, speech-recognition, speech-synthesis. - Also covers Speech & Audio. - If you need to create a personal assistant with speech interaction capabilities on a Linux environment, especially using Raspberry Pi platforms. ### Choose agents-from-scratch if… - License: agents-from-scratch is MIT, kalliope is GPL-3.0. - Requirements: Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs.. - Tags unique to agents-from-scratch: agent-architecture, ai-agents, llm, local-llm. - Also covers Developer Tools. - You plan to teach yourself or others about the fundamentals of creating AI agents from ground zero with complete transparency into each layer of architecture. ## When NOT to use kalliope - In case proprietary or permissive licensing is required as Kalliope operates under GNU General Public License v3.0. - For projects lacking a Linux environment, particularly if hardware such as Raspberry Pi is not preferred or suitable for your needs. ## When NOT to use agents-from-scratch - You are working on an application that needs to be deployed quickly. The tool's approach from first principles can be time-consuming compared to using established frameworks. - If you need scalability or cloud capabilities such as easy scaling with demand, this tool will not provide these features since it strictly operates on local infrastructure. ## Common questions ### What is the difference between kalliope and agents-from-scratch? kalliope: A framework for creating personal assistants. agents-from-scratch: Build AI agents locally without relying on frameworks or cloud APIs.. See the comparison table for live GitHub stats and shared categories. ### When should I choose kalliope over agents-from-scratch? Choose kalliope over agents-from-scratch when License: kalliope is GPL-3.0, agents-from-scratch is MIT; Tags unique to kalliope: bot-creation, personal-assistant, speech-recognition, speech-synthesis; Also covers Speech & Audio; If you need to create a personal assistant with speech interaction capabilities on a Linux environment, especially using Raspberry Pi platforms. ### When should I choose agents-from-scratch over kalliope? Choose agents-from-scratch over kalliope when License: agents-from-scratch is MIT, kalliope is GPL-3.0; Requirements: Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs.; Tags unique to agents-from-scratch: agent-architecture, ai-agents, llm, local-llm; Also covers Developer Tools; You plan to teach yourself or others about the fundamentals of creating AI agents from ground zero with complete transparency into each layer of architecture. ### When should I avoid kalliope? In case proprietary or permissive licensing is required as Kalliope operates under GNU General Public License v3.0. For projects lacking a Linux environment, particularly if hardware such as Raspberry Pi is not preferred or suitable for your needs. ### When should I avoid agents-from-scratch? You are working on an application that needs to be deployed quickly. The tool's approach from first principles can be time-consuming compared to using established frameworks. If you need scalability or cloud capabilities such as easy scaling with demand, this tool will not provide these features since it strictly operates on local infrastructure. ### Is kalliope or agents-from-scratch more popular on GitHub? kalliope has more GitHub stars (1,768 vs 954). Stars measure visibility, not whether either tool fits your constraints. ### Are kalliope and agents-from-scratch open source? Yes - both are open-source projects on GitHub (kalliope: GPL-3.0, agents-from-scratch: MIT). ### Where can I find alternatives to kalliope or agents-from-scratch? GraphCanon lists graph-backed alternatives at [kalliope alternatives](/tools/kalliope-project-kalliope/alternatives) and [agents-from-scratch alternatives](/tools/pguso-agents-from-scratch/alternatives) ([kalliope markdown twin](/tools/kalliope-project-kalliope/alternatives.md), [agents-from-scratch markdown twin](/tools/pguso-agents-from-scratch/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/kalliope-project-kalliope-vs-pguso-agents-from-scratch.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, kalliope or agents-from-scratch? kalliope: Dormant. agents-from-scratch: 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 kalliope and agents-from-scratch? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [kalliope trust report](/tools/kalliope-project-kalliope/trust); [agents-from-scratch trust report](/tools/pguso-agents-from-scratch/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=kalliope-project-kalliope`](/api/graphcanon/graph?tool=kalliope-project-kalliope) - 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/_