--- title: "minima vs localGPT" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/dmayboroda-minima-vs-promtengineer-localgpt" tools: ["dmayboroda-minima", "promtengineer-localgpt"] --- # minima vs localGPT *GraphCanon updated Aug 15, 2026* ## Verdict Pick minima if minima is an on-premises conversational RAG tool with flexible deployment options through Docker-compose configurations, catering to fully local setups (Ollama), custom LLMs, ChatGPT integration, and MCP usage; pick localGPT if localGPT allows users to chat with local documents using GPT models completely privately without internet access. [minima](https://github.com/dmayboroda/minima) reports 1.0k GitHub stars, 107 forks, and 14 open issues, last pushed Jan 22, 2026. [localGPT](https://github.com/PromtEngineer/localGPT) has 22k stars, 2.5k forks, and 24 open issues, last pushed Jul 18, 2026. Figures are from public GitHub metadata via [minima's repository](https://github.com/dmayboroda/minima) and [localGPT's repository](https://github.com/PromtEngineer/localGPT). | | [minima](/tools/dmayboroda-minima.md) | [localGPT](/tools/promtengineer-localgpt.md) | | --- | --- | --- | | Tagline | On-premises conversational RAG with configurable containers | Chat with your documents locally using GPT models | | Stars | 1,048 | 22,209 | | Forks | 107 | 2,467 | | Open issues | 14 | 24 | | Language | Python | Python | | Adopt for | Minima is an on-premises conversational RAG tool with flexible deployment options through Docker-compose configurations, catering to fully local setups (Ollama), custom LLMs, ChatGPT integration, and MCP usage. | localGPT allows users to chat with local documents using GPT models completely privately without internet access. | | Persona | - | - | | Runtime | - | - | | License | MPL-2.0 | MIT | | Categories | Data & Retrieval, Inference & Serving, Model Training | Data & Retrieval, Inference & Serving | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [minima](/tools/dmayboroda-minima.md) | [localGPT](/tools/promtengineer-localgpt.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Active (82%) | | Days since push | 204d | 21d | | Open issues (now) | 14 | 24 | | Stars delta | -4 (30d) | Unknown | | Open issues delta | 0 (30d) | Unknown | | Owner type | Organization | User | | Full report | [trust report](/tools/dmayboroda-minima/trust.md) | [trust report](/tools/promtengineer-localgpt/trust.md) | ## Shared compatibility - **Node.js**: [minima](/tools/dmayboroda-minima.md) - Node.js runtime; [localGPT](/tools/promtengineer-localgpt.md) - Node.js runtime ## Decision facts: minima - **Adopt for:** Minima is an on-premises conversational RAG tool with flexible deployment options through Docker-compose configurations, catering to fully local setups (Ollama), custom LLMs, ChatGPT integration, and MCP usage. ## Decision facts: localGPT - **Requirements:** Min 4 GB RAM; Requires Docker; Installation is currently tested only on macOS, though instructions for other operating systems are partially provided. - **Adopt for:** localGPT allows users to chat with local documents using GPT models completely privately without internet access. ## Choose when ### Choose minima if… - License: minima is MPL-2.0, localGPT is MIT. - Tags unique to minima: ai, claude, custom-gpts, docker. - Also covers Model Training. - - Use Minima for full local control over sensitive data in high-security environments where on-premises deployments are essential. ### Choose localGPT if… - License: localGPT is MIT, minima is MPL-2.0. - Requirements: Min 4 GB RAM; Requires Docker; Installation is currently tested only on macOS, though instructions for other operating systems are partially provided.. - Tags unique to localGPT: docker-support, document-chat, gpt models, local-inference. - localGPT ships Docker support for self-hosted deployment. - When absolute privacy is required since no data leaves the user's local device. ## When NOT to use minima - - Avoid using Minima if your organization requires strict adherence to a cloud-only deployment strategy. - - Do not choose Minima if you prefer tools that handle local file storage and security entirely through cloud services rather than on-premises configurations. ## When NOT to use localGPT - If you need to work across multiple devices seamlessly because localGPT requires installation on each device and does not synchronize state online. - In scenarios requiring frequent updates or model tuning from a cloud service; localGPT relies solely on locally available models which do not auto-update. ## Common questions ### What is the difference between minima and localGPT? minima: On-premises conversational RAG with configurable containers. localGPT: Chat with your documents locally using GPT models. See the comparison table for live GitHub stats and shared categories. ### When should I choose minima over localGPT? Choose minima over localGPT when License: minima is MPL-2.0, localGPT is MIT; Tags unique to minima: ai, claude, custom-gpts, docker; Also covers Model Training; - Use Minima for full local control over sensitive data in high-security environments where on-premises deployments are essential. ### When should I choose localGPT over minima? Choose localGPT over minima when License: localGPT is MIT, minima is MPL-2.0; Requirements: Min 4 GB RAM; Requires Docker; Installation is currently tested only on macOS, though instructions for other operating systems are partially provided.; Tags unique to localGPT: docker-support, document-chat, gpt models, local-inference; localGPT ships Docker support for self-hosted deployment; When absolute privacy is required since no data leaves the user's local device. ### When should I avoid minima? - Avoid using Minima if your organization requires strict adherence to a cloud-only deployment strategy. - Do not choose Minima if you prefer tools that handle local file storage and security entirely through cloud services rather than on-premises configurations. ### When should I avoid localGPT? If you need to work across multiple devices seamlessly because localGPT requires installation on each device and does not synchronize state online. In scenarios requiring frequent updates or model tuning from a cloud service; localGPT relies solely on locally available models which do not auto-update. ### Is minima or localGPT more popular on GitHub? localGPT has more GitHub stars (22,209 vs 1,048). Stars measure visibility, not whether either tool fits your constraints. ### Are minima and localGPT open source? Yes - both are open-source projects on GitHub (minima: MPL-2.0, localGPT: MIT). ### Where can I find alternatives to minima or localGPT? GraphCanon lists graph-backed alternatives at [minima alternatives](/tools/dmayboroda-minima/alternatives) and [localGPT alternatives](/tools/promtengineer-localgpt/alternatives) ([minima markdown twin](/tools/dmayboroda-minima/alternatives.md), [localGPT markdown twin](/tools/promtengineer-localgpt/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/dmayboroda-minima-vs-promtengineer-localgpt.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, minima or localGPT? minima: Slowing. localGPT: 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 minima and localGPT? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [minima trust report](/tools/dmayboroda-minima/trust); [localGPT trust report](/tools/promtengineer-localgpt/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=dmayboroda-minima`](/api/graphcanon/graph?tool=dmayboroda-minima) - 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/_