--- title: "agent-protocol vs core" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/agi-inc-agent-protocol-vs-cheshire-cat-ai-core" tools: ["agi-inc-agent-protocol", "cheshire-cat-ai-core"] --- # agent-protocol vs core *GraphCanon updated Aug 15, 2026* ## Verdict Pick agent-protocol if agent-protocol provides a standardized interface for interacting with various AI agents regardless of their underlying tech stack, aiming to ease development, deployment, and benchmarking; pick core if core is a Python-based AI microservice tool for building chatbots and integrating vector search. It supports conversational interfaces through the ag-ui-protocol. [agent-protocol](https://agentprotocol.ai) reports 1.5k GitHub stars, 185 forks, and 50 open issues, last pushed Apr 8, 2025. [core](https://cheshirecat.ai) has 3.1k stars, 409 forks, and 8 open issues, last pushed Jul 29, 2026. Figures are from public GitHub metadata via [agent-protocol's repository](https://github.com/agi-inc/agent-protocol) and [core's repository](https://github.com/cheshire-cat-ai/core). | | [agent-protocol](/tools/agi-inc-agent-protocol.md) | [core](/tools/cheshire-cat-ai-core.md) | | --- | --- | --- | | Tagline | Common interface for AI agents | AI agent microservice | | Stars | 1,458 | 3,081 | | Forks | 185 | 409 | | Open issues | 50 | 8 | | Language | Python | Python | | Adopt for | agent-protocol provides a standardized interface for interacting with various AI agents regardless of their underlying tech stack, aiming to ease development, deployment, and benchmarking. | core is a Python-based AI microservice tool for building chatbots and integrating vector search. It supports conversational interfaces through the ag-ui-protocol. | | Persona | - | - | | Runtime | - | - | | License | MIT | GPL-3.0 licenses the code base of the core repository. | | Categories | AI Agents | AI Agents, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agent-protocol](/tools/agi-inc-agent-protocol.md) | [core](/tools/cheshire-cat-ai-core.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Active (82%) | | Days since push | 484d | 16d | | Open issues (now) | 50 | 8 | | Stars delta | Unknown | +7 (30d) | | Open issues delta | Unknown | +1 (30d) | | Full report | [trust report](/tools/agi-inc-agent-protocol/trust.md) | [trust report](/tools/cheshire-cat-ai-core/trust.md) | ## Decision facts: agent-protocol - **Adopt for:** agent-protocol provides a standardized interface for interacting with various AI agents regardless of their underlying tech stack, aiming to ease development, deployment, and benchmarking. ## Decision facts: core - **Hosting:** self hosted - core can be self-hosted. - **Requirements:** Requires Python support due to being Python-based. - **Adopt for:** core is a Python-based AI microservice tool for building chatbots and integrating vector search. It supports conversational interfaces through the ag-ui-protocol. - **License detail:** GPL-3.0 licenses the code base of the core repository. ## Choose when ### Choose agent-protocol if… - License: agent-protocol is MIT, core is GPL-3.0. - Tags unique to agent-protocol: agents, ai-agent, api, auto-gpt. - When you want to ensure interoperability between different AI agents irrespective of the frameworks used by them. ### Choose core if… - License: core is GPL-3.0, agent-protocol is MIT. - core can be self-hosted. - Requirements: Requires Python support due to being Python-based.. - Tags unique to core: ag-ui-protocol, agent, ai, assistant. - Also covers Vector Databases. - For projects that require an open-source solution under GPL-3.0, because core's licensing aligns with this requirement ## When NOT to use agent-protocol - If you are developing an isolated system with no intention to communicate or integrate with other AI agents outside this scope. - When working in environments where specific, proprietary interfaces provide significantly better performance or features than adhering to a generic protocol could offer. ## When NOT to use core - If your project needs proprietary license terms, since core restricts use by GPL-3.0 which might not fit all commercial scenarios - In cases where you require a non-Python environment, as the tool may require significant custom code to adapt to another language ## Common questions ### What is the difference between agent-protocol and core? agent-protocol: Common interface for AI agents. core: AI agent microservice. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-protocol over core? Choose agent-protocol over core when License: agent-protocol is MIT, core is GPL-3.0; Tags unique to agent-protocol: agents, ai-agent, api, auto-gpt; When you want to ensure interoperability between different AI agents irrespective of the frameworks used by them. ### When should I choose core over agent-protocol? Choose core over agent-protocol when License: core is GPL-3.0, agent-protocol is MIT; core can be self-hosted; Requirements: Requires Python support due to being Python-based.; Tags unique to core: ag-ui-protocol, agent, ai, assistant; Also covers Vector Databases; For projects that require an open-source solution under GPL-3.0, because core's licensing aligns with this requirement. ### When should I avoid agent-protocol? If you are developing an isolated system with no intention to communicate or integrate with other AI agents outside this scope. When working in environments where specific, proprietary interfaces provide significantly better performance or features than adhering to a generic protocol could offer. ### When should I avoid core? If your project needs proprietary license terms, since core restricts use by GPL-3.0 which might not fit all commercial scenarios In cases where you require a non-Python environment, as the tool may require significant custom code to adapt to another language ### Is agent-protocol or core more popular on GitHub? core has more GitHub stars (3,081 vs 1,458). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-protocol and core open source? Yes - both are open-source projects on GitHub (agent-protocol: MIT, core: GPL-3.0). ### Where can I find alternatives to agent-protocol or core? GraphCanon lists graph-backed alternatives at [agent-protocol alternatives](/tools/agi-inc-agent-protocol/alternatives) and [core alternatives](/tools/cheshire-cat-ai-core/alternatives) ([agent-protocol markdown twin](/tools/agi-inc-agent-protocol/alternatives.md), [core markdown twin](/tools/cheshire-cat-ai-core/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/agi-inc-agent-protocol-vs-cheshire-cat-ai-core.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agent-protocol or core? agent-protocol: Dormant. core: 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-protocol and core? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-protocol trust report](/tools/agi-inc-agent-protocol/trust); [core trust report](/tools/cheshire-cat-ai-core/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=agi-inc-agent-protocol`](/api/graphcanon/graph?tool=agi-inc-agent-protocol) - 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/_