The latest articles on DEV Community by Vikas Pandey (@vikas0686). https://dev.to/vikas0686 https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4046907%2F0b97cdbb-18b0-42fe-b873-ada5c6df86a3.jpg https://dev.to/vikas0686 en Vikas Pandey Sat, 25 Jul 2026 14:00:55 +0000 https://dev.to/vikas0686/building-aktilot-an-open-source-ai-workspace-for-engineering-teams-10jl https://dev.to/vikas0686/building-aktilot-an-open-source-ai-workspace-for-engineering-teams-10jl <p><strong>Aktilot</strong> is an open-source AI workspace designed for engineering teams. It connects platforms like GitHub, Jira, Confluence, Slack, and other enterprise tools into a single intelligent workspace. </p> <p>By combining <strong>Retrieval-Augmented Generation (RAG)</strong>, and both cloud and local LLMs, <strong>Aktilot</strong> enables developers to search organizational knowledge, understand codebases, answer technical questions, and automate engineering workflows—all from one place.</p> <p>Modern engineering knowledge is scattered across multiple tools.</p> <ul> <li>GitHub for code</li> <li>Jira for tasks</li> <li>Confluence for documentation</li> <li>Slack for discussions</li> <li>Google Drive for design documents</li> </ul> <p>When developers need answers, they often switch between all of these systems.</p> <p>I started building Aktilot to solve this problem.</p> <h2> What is Aktilot? </h2> <p>Aktilot is an open-source AI workspace that connects engineering tools and allows developers to ask questions in natural language.</p> <p>Instead of searching across multiple applications, developers can ask questions like:</p> <ul> <li>Where is this feature implemented?</li> <li>Which Jira ticket introduced it?</li> <li>Is there documentation for this API?</li> <li>Where was this discussed?</li> </ul> <h2> Architecture </h2> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2F54c34eq8jz4y8xemdvqf.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2F54c34eq8jz4y8xemdvqf.png" alt=" " width="640" height="426"></a></p> <p>Aktilot is built around four core components:</p> <p><strong>Connectors</strong> : GitHub, Jira, Confluence, Slack, Google Drive<br> <strong>Knowledge Engine</strong> : Collects, indexes, and retrieves information<br> <strong>AI Layer</strong> : Supports OpenAI and local LLMs like Ollama<br> <strong>Web UI</strong> : A single interface to search and interact with your<br> engineering knowledge</p> <h2> Current Features </h2> <ul> <li>✅ GitHub Connector </li> <li>✅ AI Chat Interface </li> <li>✅ OpenAI Support </li> <li>✅ Ollama (Local LLM) Support </li> <li>✅ Extensible Connector Framework</li> </ul> <h2> What's Next? </h2> <p>I'm currently working on:</p> <ul> <li>Jira Connector</li> <li>Confluence Connector</li> <li>Slack Connector</li> <li>Google Drive Connector</li> <li>More AI-powered engineering workflows</li> </ul> <h2> Why Open Source? </h2> <p>I wanted Aktilot to be self-hostable, extensible, and community-driven. My goal isn't just to build another chatbot—it's to create a workspace where AI can understand an engineering team's knowledge across different systems.</p> <p>The project is still evolving, and I'd love feedback from the community.</p> <p><strong>GitHub</strong>: <a href="https://github.com/your-org/aktilot" rel="noopener noreferrer">https://github.com/your-org/aktilot</a><br> <strong>website</strong>: <a href="https://aktilot.com" rel="noopener noreferrer">https://aktilot.com</a></p> ai opensource rag python