Agent Flow: A beautiful way to visualize Claude Code actions
Hey HN, Claude Code is powerful, but its execution is a black box. You see the final result, not the journey. Agent Flow makes the invisible visible in realtime: - Understand agent behavior: See how Claude breaks down problems, which tools it reaches for, and how subagents coordinate - Debug tool call chains: When something goes wrong, trace the exact sequence of decisions and tool calls that led there - See where time is spent: Identify slow tool calls, unnecessary branching, or redundant work at a glance - Learn by watching: Build intuition for how to write better prompts by observing how…
What it does
In the maker’s words, at launch
Hey HN, Claude Code is powerful, but its execution is a black box. You see the final result, not the journey. Agent Flow makes the invisible visible in realtime: - Understand agent behavior: See how Claude breaks down problems, which tools it reaches for, and how subagents coordinate - Debug tool call chains: When something goes wrong, trace the exact sequence of decisions and tool calls that led there - See where time is spent: Identify slow tool calls, unnecessary branching, or redundant work at a glance - Learn by watching: Build intuition for how to write better prompts by observing how Claude interprets and executes them It's also been really useful when building agents into your own product. Having a visual way to see how an agent actually behaves makes it much easier to iterate on prompts, tool design, and orchestration logic. It's also been invaluable when building agents into your own product. I've been using it every day to understand how the Anthropic Agent SDK behaves, and seeing agent orchestration visually makes it so much easier to iterate on prompts, tool design, and coordination logic. It's also interactive, and shows what's happening as Claude Code works: which agents are active, what tools they're calling, how they coordinate, and where time and tokens are being spent. You can pan, zoom, click into any agent or tool call to inspect it. It runs as a VS Code extension — opens as a panel right alongside your editor. What you can see: - Live agent spawning, branching, and completion - Every tool call with timing and token usage - Token consumption per task and per session - Parent-child agent relationships - File attention heatmaps (which files agents are reading/writing most) - Full transcript replay - Multi-session support for concurrent workflows Currently works with Claude Code. Codex support and iTerm2 integration are next on the roadmap. GitHub: https://github.com/patoles/agent-flow
Does the same job
all alternatives →
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
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
