--- title: "core vs agents-from-scratch" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/cheshire-cat-ai-core-vs-pguso-agents-from-scratch" tools: ["cheshire-cat-ai-core", "pguso-agents-from-scratch"] --- # core vs agents-from-scratch *GraphCanon updated Sep 20, 2026* ## Verdict Pick core if cheshire Cat AI, an AI agent microservice, is built in Python and supports function-calling and vector search, making it suitable for projects that require conversational AI capabilities with these features; 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. [core](https://cheshirecat.ai) reports 3.1k GitHub stars, 409 forks, and 11 open issues, last pushed Jul 29, 2026. [agents-from-scratch](https://github.com/pguso/agents-from-scratch) has 1.0k stars, 251 forks, and 4 open issues, last pushed Jul 25, 2026. Figures are from public GitHub metadata via [core's repository](https://github.com/cheshire-cat-ai/core) and [agents-from-scratch's repository](https://github.com/pguso/agents-from-scratch). | | [core](/tools/cheshire-cat-ai-core.md) | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | | --- | --- | --- | | Tagline | AI agent microservice | Build AI agents locally without relying on frameworks or cloud APIs. | | Stars | 3,086 | 1,017 | | Forks | 409 | 251 | | Open issues | 11 | 4 | | Language | Python | Python | | Adopt for | Cheshire Cat AI, an AI agent microservice, is built in Python and supports function-calling and vector search, making it suitable for projects that require conversational AI capabilities with these features. | 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, which is a copyleft license requiring that any derivative works be released under the same license. | MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes. | | Categories | AI Agents | AI Agents, Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [core](/tools/cheshire-cat-ai-core.md) | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | | --- | --- | --- | | Days since push | 50d | 56d | | Open issues (now) | 11 | 4 | | Stars delta | +5 (30d) | +63 (30d) | | Open issues delta | +3 (30d) | +1 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/cheshire-cat-ai-core/trust.md) | [trust report](/tools/pguso-agents-from-scratch/trust.md) | ## Decision facts: core - **Pricing:** freemium - The code is free and open-source under GPL-3.0, but any derivative works must also be open-source. - **Requirements:** Min 2 GB RAM; Requires Docker; Requires Docker for deployment. - **Adopt for:** Cheshire Cat AI, an AI agent microservice, is built in Python and supports function-calling and vector search, making it suitable for projects that require conversational AI capabilities with these features. - **License detail:** GPL-3.0, which is a copyleft license requiring that any derivative works be released under the same license. ## 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 core if… - License: core is GPL-3.0, agents-from-scratch is MIT. - Pricing: The code is free and open-source under GPL-3.0, but any derivative works must also be open-source.. - Requirements: Min 2 GB RAM; Requires Docker; Requires Docker for deployment.. - Tags unique to core: ag-ui-protocol, agent, ai, assistant. - Use Cheshire Cat AI when you need a microservice that supports function-calling and vector search, as it is specifically designed with these features. ### Choose agents-from-scratch if… - License: agents-from-scratch is MIT, core 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 core - Avoid using Cheshire Cat AI if your project requires proprietary licensing, as it is licensed under GPL-3.0, which may not be compatible with proprietary software. - Do not use it if your project does not require or benefit from function-calling or vector search capabilities, as these are core features of Cheshire Cat AI. ## 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 core and agents-from-scratch? core: AI agent microservice. 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 core over agents-from-scratch? Choose core over agents-from-scratch when License: core is GPL-3.0, agents-from-scratch is MIT; Pricing: The code is free and open-source under GPL-3.0, but any derivative works must also be open-source.; Requirements: Min 2 GB RAM; Requires Docker; Requires Docker for deployment.; Tags unique to core: ag-ui-protocol, agent, ai, assistant; Use Cheshire Cat AI when you need a microservice that supports function-calling and vector search, as it is specifically designed with these features. ### When should I choose agents-from-scratch over core? Choose agents-from-scratch over core when License: agents-from-scratch is MIT, core 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 core? Avoid using Cheshire Cat AI if your project requires proprietary licensing, as it is licensed under GPL-3.0, which may not be compatible with proprietary software. Do not use it if your project does not require or benefit from function-calling or vector search capabilities, as these are core features of Cheshire Cat AI. ### 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 core or agents-from-scratch more popular on GitHub? core has more GitHub stars (3,086 vs 1,017). Stars measure visibility, not whether either tool fits your constraints. ### Are core and agents-from-scratch open source? Yes - both are open-source projects on GitHub (core: GPL-3.0, agents-from-scratch: MIT). ### Where can I find alternatives to core or agents-from-scratch? GraphCanon lists graph-backed alternatives at [core alternatives](/tools/cheshire-cat-ai-core/alternatives) and [agents-from-scratch alternatives](/tools/pguso-agents-from-scratch/alternatives) ([core markdown twin](/tools/cheshire-cat-ai-core/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/cheshire-cat-ai-core-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, core or agents-from-scratch? core: Steady. agents-from-scratch: Steady. 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 core and agents-from-scratch? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [core trust report](/tools/cheshire-cat-ai-core/trust); [agents-from-scratch trust report](/tools/pguso-agents-from-scratch/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=cheshire-cat-ai-core`](/api/graphcanon/graph?tool=cheshire-cat-ai-core) - 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/_