Sunil Khedar | True Sparrow

@TechieKedar and I go under the hood to show you how Sirji agents communicate using the messaging protocol. We show how the agent pseudocode gets converted into a chain of messages/function-calls between Sirji and the LLM. We talk about agent call stack and how that helps forward the message to the appropriate agent. @sirji_ai

How to write a @sirji_ai agent? How many agents do you need to, let’s say, create a node.js API? @TechieKedar and I also discussed why our agents need scratchpads.

Looking inside a @sirji_ai agent and recipe with @TechieKedar.

LLMs (and some new AI tools) do a decent job at generating code for a new project. But they struggle with existing codebases. Why? 1. Existing Architecture: New projects don't have the baggage of existing architecture and design patterns that AI needs to understand and fit into. 2. Project-Specific Conventions: Existing projects come with unique coding standards and conventions. LLMs fail to follow these without explicit and detailed guidance. 3. Contextual Awareness: Understanding the full context of the existing codebase, including why certain decisions were made, is critical. LLMs lack this context. But then if you really want to build a tool that developers will use for their everyday dev tasks, it needs to be able to work with existing codebases and not just create new shiny projects. It's hard but not impossible. That’s what we are trying to do with @Sirji_ai.

We have been using #Sirji to create new APIs and test cases for Raised (one of our side projects). This is an existing repository with 100+ files. It took @TechieKedar 10 minutes while working with Sirji to write a new API and the corresponding test cases. It took 20 minutes more to manually review the code and to make two minor edits. Without Sirji, this task would have taken him 5-6 hours. That’s a 10x productivity boost!

How is #Sirji different from github copilot workspace? So while I haven’t got access to github copilot workspace yet, the main difference is that with Sirji you can write custom agents. (1/n) 🧵

Do you know why “Enter number: ” is not shown on my terminal (i.e. stdout), but instead in error.log (i.e. stderr)? File user_input.py: num = input(“Enter number: “) print(num) command:  python user_input.py 2> error.log #sirji #buildinpublic

#Sirji Update: Possible solutions to equip the Executor with debugging capabilities: 1. Use tee command 2. Use “vscode.window.onDidWriteTerminalData” 3. Use just the stdout stream Are there any other solutions that we can explore? For more details: github.com/sirji-ai/sirji…

#sirji #buildinpublic I wanted to share my proposal to enhance Sirji's capabilities to navigate and work with GitHub repositories. Strategy: Initial shortlisting of files, guided by directory structure, followed by incremental deep dive. Details 👉 github.com/sirji-ai/sirji…

📊 86% voted in favor of a VS Code extension for #Sirji yesterday over a web app. That’s telling. Sirji as a VS Code extension means: * Your code won't be shared with any 3rd party servers or apps, except with models and embeddings. * Familiarity with the tooling. VS Code has an integrated environment that includes an editor, terminal, and browser with which you are already familiar. Sirji will reuse these components. * Reduced context switching, as you can use Sirji without leaving your IDE. We are on it. Targeting the first VS Code extension and the related PyPI packages by the coming Monday. Check out the quick POC that @dakshbhardwaj25 put together on the VS Code capabilities and integration flows. Link in the comment.

Happy Holi, Sirji!

#sirji #buildinpublic Sirji’s chat GUI got built today. It helps the user to enter the problem statement and give feedback on the solution.

Prompt for Sirji: Create an express app. Use PostgreSQL as database and Sequelize as ORM. Create migration files and model files by understanding the DBML file. Create API routes in modular files by understanding the OpenAPI specs file. See the magic happen!

Attn devs: Sirji's dogfood release is done. What's in dogfood: * Chat interface for the user to enter the problem statement. The user can interact with Sirji by providing change requests and enhancements. * Message protocol implemented for various agents - Planning Agent, Coding Agent, Research Agent, and Executor Agent. * The Planning Agent: Takes in a problem statement and breaks it down into steps. * The Coding Agent: Sequentially generates code to solve the problem programmatically. * The Research Agent: Utilizes RAG and gets trained on URLs and search terms. Later, it can use the training knowledge to answer the questions asked by the Coding Agent. * The Executor Agent: Responsible for creating the code files, running commands, and installing dependencies. You can see what's possible with the dogfood release in the demo videos. Link in my comment. Now onwards to the next release: Visual Studio Code IDE as the user interface.

Would you prefer #Sirji as a VS Code extension or a web application?

@nishithshah Dogfood release tag: github.com/sirji-ai/sirji… Please share your feedback here: github.com/orgs/sirji-ai/…

And here we go… Sirji’s first successful run. 🚀 I wouldn’t say we are done with dogfood release yet. This was just one run. We will be testing with a variety of different problem statements. The main functionality remaining for this release is adding debugging capabilities (including user feedback & interaction).

@TechieKedar Alongside, @rachinkapoor is already exploring Sirji’s eventual IDE and why he’s drawn towards solutions like codespace.

#sirji #buildinpublic @TechieKedar talks about what you can expect from the dogfood version (ETA: this Friday) of Sirji. It’s going to be a basic command line interface with terminal windows with logs from various agents.

#sirji We have standardized the system prompts for each of the agents, and created a simple protocol for inter-agent communication. Here's @sunilkhedar's update on the messages & prompts packages.