Codag – Visualize and share LLM workflows in VS Code
I built Codag because I kept getting lost in my own AI code. You're chaining 3 LLM calls across 5 files. A prompt change breaks something downstream. Which call? Which branch? You grep for "openai.chat", open 8 tabs, trace the flow manually. Codag automates this: - Point it at your codebase and it extracts every LLM call, decision branch, and processing step - Renders an interactive and shareable DAG with clickable nodes that link back to source - Live updates as you edit using tree-sitter — no waiting for re-analysis Supports OpenAI, Anthropic, Gemini, LangChain, LangGraph, CrewAI, and…
What it does
In the maker’s words, at launch
I built Codag because I kept getting lost in my own AI code. You're chaining 3 LLM calls across 5 files. A prompt change breaks something downstream. Which call? Which branch? You grep for "openai.chat", open 8 tabs, trace the flow manually. Codag automates this: - Point it at your codebase and it extracts every LLM call, decision branch, and processing step - Renders an interactive and shareable DAG with clickable nodes that link back to source - Live updates as you edit using tree-sitter — no waiting for re-analysis Supports OpenAI, Anthropic, Gemini, LangChain, LangGraph, CrewAI, and more. Works with Python, TypeScript, Go, Rust, Java, and more. It's a VS Code extension + self-hosted backend (Gemini 2.5 Flash for analysis). Open source, MIT licensed.
Does the same job
all alternatives →- CMCodeflowmap – map a codebase's read/write/auth data flowsJun 2026 · github.com · ▲7
I've been vibe-coding tools to automate chunks of my consulting work, fell down a rabbit hole, and started building actual products. Suddenly I'm in a world of unknown-unknowns and known-unknowns. One of the bigger things to solve was understanding code the LLM generated that I didn't fully grasp. What does it touch? What reads and writes where? Is the auth path where I think it is? So I built codeflowmap. Point it at a repo and it maps the dependency and call graph, then surfaces the read / write / auth paths between files and functions. Connect a local model (Ollama) or any…
- WCWe create visual codebase maps that scale (static analysis and LLMs)2025 · github.com · ▲6
Hi all, I'm Ivan, and together with Alex, we're building a diagram visualization tool for codebases. Alex and I are devs, and we've noticed that recently we've been super productive at writing code (prompting :D). But when it comes to understanding big systems, prompting doesn't work that well — for that, diagrams are best imo. Most tools out there don't scale to big projects (e.g. PyTorch), so we're building CodeBoarding — a recursive visualizer for codebases. It starts from the highest level of abstractions and lets you dive deeper. We use static analysis and LLM agents. The control-flow…
- CLCaptureFlow – LLM codegen/bugfix powered by live application context2024 · github.com · ▲6
Hi Hacker News, As a dev extensively using GPT-4 for coding, I've realized its effectiveness significantly increases with richer context (e.g., code samples, execution state - props to DevinAI for famously console.logging itself). This inspired me to push the idea further and create CaptureFlow. This tool equips your coding LLM with a debugger-level view into your Python apps, via a simple one-line decorator. Such detailed tracing improves LLM coding capabilities and opens new use cases, such as auto-bug fix and test case generation. CaptureFlow-py offers an extensible end-to-end pipeline…
- CVCodebase visualizer (I'll build the diagram for the first 20 repos)2025 · pie-crepe-38f.notion.site · ▲8
I worked as a software engineer at Amazon, SAP, and on open source. In all 3 places I have struggled with the friction of understanding codebases before I can make a contribution. I think this brain-fatiguing process can be improved. I am trying to solve it with a tool I built over the last 4 years called CodeCanvas: https://docs.code-canvas.com CodeCanvas visualizes codebases through interactive diagrams linked directly to source code. Users can record 'simulations' to demonstrate data flow and business logic. I’ve also recently added an LLM chat where it takes only the relevant…
- LFLLM Function Calling Library to Interact with File, Shell, Git and Code2024 · swekit.dev · ▲5
Hey HN, I built SWE-Kit, LLM toolkit (Function callable tools) which makes building agents specialised in coding like Devin very easy. I noticed a typical pattern while building local agents: creating & perfecting LLM tools to interact with system or codebase was the repeated and time-consuming. We created a layer that simplifies building agents that can interact with code, file system, git, shell and allows you to quickly solve for a wide variety of coding agent use cases. Aren’t there open coding agents already? Well, yes, but most folks would want to solve their specific use case like a…
- BABenchmark AI on your actual code (GPT-5, Claude, Grok, Gemini, o3)Oct 2025 · codelens.ai · ▲7
I built CodeLens.AI - a tool that compares how 6 top LLMs (GPT-5, Claude Opus 4.1, Claude Sonnet 4.5, Grok 4, Gemini 2.5 Pro, o3) handle your actual code tasks. How it works: - Upload code + describe task (refactoring, security review, architecture, etc.) - All 6 models run in parallel (~2-5 min) - See side-by-side comparison with AI judge scores - Community votes on winners (blind voting) - Each evaluation gets reflected in the overall AI model leaderboard, showing us best ones Why I built this: Existing benchmarks (HumanEval, SWE-Bench) don't reflect real-world developer tasks. I wanted to…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
