--- title: "khoj vs incognide" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/khoj-ai-khoj-vs-npc-worldwide-incognide" tools: ["khoj-ai-khoj", "npc-worldwide-incognide"] --- # khoj vs incognide *GraphCanon updated Sep 20, 2026* ## Verdict Pick khoj if khoj is a self-hosted AI assistant that supports integration with multiple LLMs, enabling users to build custom agents and conduct deep research using both web and local documents; pick incognide if incognide is a TypeScript library for developing AI agents with integrated capabilities for llm-inference. [khoj](https://khoj.dev) reports 37k GitHub stars, 2.5k forks, and 150 open issues, last pushed Aug 2, 2026. [incognide](https://enpisi.com/incognide.html) has 471 stars, 50 forks, and 12 open issues, last pushed Sep 16, 2026. Figures are from public GitHub metadata via [khoj's repository](https://github.com/khoj-ai/khoj) and [incognide's repository](https://github.com/NPC-Worldwide/incognide). | | [khoj](/tools/khoj-ai-khoj.md) | [incognide](/tools/npc-worldwide-incognide.md) | | --- | --- | --- | | Tagline | Self-hostable AI second brain for personalized research and automation | Develops AI agents and integrates llms for inference | | Stars | 37,399 | 471 | | Forks | 2,484 | 50 | | Open issues | 150 | 12 | | Language | Python | TypeScript | | Adopt for | Khoj is a self-hosted AI assistant that supports integration with multiple LLMs, enabling users to build custom agents and conduct deep research using both web and local documents. | Incognide is a TypeScript library for developing AI agents with integrated capabilities for llm-inference. | | Persona | - | - | | Runtime | - | - | | License | Khoj is licensed under AGPL-3.0, which means it is free to use, modify, and distribute, but any derivative works must also be released under the same license. | MIT | | Categories | AI Agents, Data & Retrieval, Developer Tools, Inference & Serving, Model Training | AI Agents, Inference & Serving, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [khoj](/tools/khoj-ai-khoj.md) | [incognide](/tools/npc-worldwide-incognide.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Very active (96%) | | Days since push | 47d | 4d | | Open issues (now) | 150 | 12 | | Stars delta | +887 (30d) | +12 (30d) | | Open issues delta | +17 (30d) | -6 (30d) | | Full report | [trust report](/tools/khoj-ai-khoj/trust.md) | [trust report](/tools/npc-worldwide-incognide/trust.md) | ## Decision facts: khoj - **Pricing:** freemium - Khoj is free to use, but users may incur costs related to hosting and the LLMs they choose to integrate. - **Requirements:** Min 4 GB RAM; Requires Docker; Khoj requires Docker for setup and operation.; Users must have a Python environment and the necessary dependencies installed. - **Adopt for:** Khoj is a self-hosted AI assistant that supports integration with multiple LLMs, enabling users to build custom agents and conduct deep research using both web and local documents. - **License detail:** Khoj is licensed under AGPL-3.0, which means it is free to use, modify, and distribute, but any derivative works must also be released under the same license. ## Decision facts: incognide - **Adopt for:** Incognide is a TypeScript library for developing AI agents with integrated capabilities for llm-inference. ## Choose when ### Choose khoj if… - khoj is primarily Python; incognide is TypeScript. - License: khoj is AGPL-3.0, incognide is MIT. - Pricing: Khoj is free to use, but users may incur costs related to hosting and the LLMs they choose to integrate.. - Requirements: Min 4 GB RAM; Requires Docker; Khoj requires Docker for setup and operation.; Users must have a Python environment and the necessary dependencies installed.. - Tags unique to khoj: agent, ai, assistant, chat. - Also covers Data & Retrieval, Developer Tools, Model Training. - When you need a self-hosted solution for personalized research and automation that can integrate with a variety of LLMs, including GPT, Claude, Gemini, LLaMA, Qwen, and Mistral. ### Choose incognide if… - incognide is primarily TypeScript; khoj is Python. - License: incognide is MIT, khoj is AGPL-3.0. - Tags unique to incognide: agents, ai-agents, artificial-intelligence, llm-inference. - Also covers LLM Frameworks. - When you need a TypeScript-based solution to develop AI agents that integrate llm-inference features ## When NOT to use khoj - If you are looking for a cloud-based service without the need for self-hosting, Khoj may not be the best fit. - Khoj might not be ideal if you are seeking a tool that does not support a wide range of LLMs and requires a more specialized integration. - If your research and automation needs are simple and do not require deep integration with local documents or web sources, a more straightforward tool might be more appropriate. ## When NOT to use incognide - If your project requires languages other than TypeScript as the primary language - Not suitable if you are looking for ready-to-deploy production tools, given its focus on research and development phase ## Common questions ### What is the difference between khoj and incognide? khoj: Self-hostable AI second brain for personalized research and automation. incognide: Develops AI agents and integrates llms for inference. See the comparison table for live GitHub stats and shared categories. ### When should I choose khoj over incognide? Choose khoj over incognide when khoj is primarily Python; incognide is TypeScript; License: khoj is AGPL-3.0, incognide is MIT; Pricing: Khoj is free to use, but users may incur costs related to hosting and the LLMs they choose to integrate.; Requirements: Min 4 GB RAM; Requires Docker; Khoj requires Docker for setup and operation.; Users must have a Python environment and the necessary dependencies installed.; Tags unique to khoj: agent, ai, assistant, chat; Also covers Data & Retrieval, Developer Tools, Model Training; When you need a self-hosted solution for personalized research and automation that can integrate with a variety of LLMs, including GPT, Claude, Gemini, LLaMA, Qwen, and Mistral. ### When should I choose incognide over khoj? Choose incognide over khoj when incognide is primarily TypeScript; khoj is Python; License: incognide is MIT, khoj is AGPL-3.0; Tags unique to incognide: agents, ai-agents, artificial-intelligence, llm-inference; Also covers LLM Frameworks; When you need a TypeScript-based solution to develop AI agents that integrate llm-inference features. ### When should I avoid khoj? If you are looking for a cloud-based service without the need for self-hosting, Khoj may not be the best fit. Khoj might not be ideal if you are seeking a tool that does not support a wide range of LLMs and requires a more specialized integration. If your research and automation needs are simple and do not require deep integration with local documents or web sources, a more straightforward tool might be more appropriate. ### When should I avoid incognide? If your project requires languages other than TypeScript as the primary language Not suitable if you are looking for ready-to-deploy production tools, given its focus on research and development phase ### Is khoj or incognide more popular on GitHub? khoj has more GitHub stars (37,399 vs 471). Stars measure visibility, not whether either tool fits your constraints. ### Are khoj and incognide open source? Yes - both are open-source projects on GitHub (khoj: AGPL-3.0, incognide: MIT). ### Where can I find alternatives to khoj or incognide? GraphCanon lists graph-backed alternatives at [khoj alternatives](/tools/khoj-ai-khoj/alternatives) and [incognide alternatives](/tools/npc-worldwide-incognide/alternatives) ([khoj markdown twin](/tools/khoj-ai-khoj/alternatives.md), [incognide markdown twin](/tools/npc-worldwide-incognide/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/khoj-ai-khoj-vs-npc-worldwide-incognide.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, khoj or incognide? khoj: Steady. incognide: Very 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 khoj and incognide? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [khoj trust report](/tools/khoj-ai-khoj/trust); [incognide trust report](/tools/npc-worldwide-incognide/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=khoj-ai-khoj`](/api/graphcanon/graph?tool=khoj-ai-khoj) - 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/_