Claude Wrapped in the terminal, with a WASM raymarcher
Web AppClaude Code added a /stats command. The stats are cached in $HOME/.claude, so I made a fun program with Bun + WASM that pulls the stats (nonsensitive, nonidentifiable), posts them to a database, and lets you see where your usage lies.The code is here[^1] if anyone's interested in the
- Best for
- terminal-based interactive chat with claude, wasm raymarching for visual output
- Type
- Web App
- Score
- 27/100
- Best alternative
- Browser Use
Capabilities2 decomposed
terminal-based interactive chat with claude
Medium confidenceThis capability allows users to interact with the Claude AI model directly within a terminal interface, leveraging a WebAssembly (WASM) layer for efficient execution. The terminal wraps Claude's API calls, enabling real-time responses while maintaining a lightweight footprint. The integration of WASM ensures that the interaction is smooth and responsive, allowing for a seamless user experience without the overhead of a full GUI.
Utilizes a WASM layer to enhance performance and responsiveness of AI interactions in a terminal environment, which is uncommon in traditional AI interfaces.
More responsive than typical web-based AI interfaces due to the lightweight WASM execution model.
wasm raymarching for visual output
Medium confidenceThis capability employs a raymarching algorithm implemented in WebAssembly to generate 3D visuals directly in the terminal. It allows users to visualize complex geometric shapes and scenes in real-time, leveraging the computational efficiency of WASM for rendering. This approach provides an interactive graphical experience without needing a separate graphical application, making it unique for terminal-based environments.
Combines real-time raymarching with terminal interaction, which is rare and allows for unique visual experiences directly in command-line environments.
Offers a unique blend of terminal-based interaction and real-time graphics, unlike traditional graphical applications that require separate interfaces.
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with Claude Wrapped in the terminal, with a WASM raymarcher, ranked by overlap. Discovered automatically through the match graph.
BrowserOS – "Claude Cowork" in the browser
Hey HN! We're Nithin and Nikhil, twin brothers building BrowserOS (YC S24). We're an open-source, privacy-first alternative to the AI browsers from big labs.The big differentiator: on BrowserOS you can use local LLMs or BYOK and run the agent entirely on the client side, so your company&#x
Claude-replay – A video-like player for Claude Code sessions
I got tired of sharing AI demos with terminal screenshots or screen recordings.Claude Code already stores full session transcripts locally as JSONL files. Those logs contain everything: prompts, tool calls, thinking blocks, and timestamps.I built a small CLI tool that converts those logs into an int
Chat for Claude Code
Beautiful Claude Code Chat Interface for VS Code
crystal
(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, compare approaches & manage AI-assisted development workflows in one desktop app.
Claude(Claude for Visual Studio Code)
Claude integration for Visual Studio Code.
claude-code-guide
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks go from beginner to power user!
Best For
- ✓developers who prefer command-line interfaces for AI interactions
- ✓developers and artists interested in terminal-based graphics
Known Limitations
- ⚠Limited to text-based interactions; no graphical output or multimedia support
- ⚠Performance may vary based on terminal emulator capabilities
- ⚠Limited graphical fidelity compared to full-fledged 3D engines
- ⚠Dependent on terminal capabilities for rendering
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
About
Show HN: Claude Wrapped in the terminal, with a WASM raymarcher
Categories
Alternatives to Claude Wrapped in the terminal, with a WASM raymarcher
Most-starred open-source browser-agent library — agents drive real browsers via Playwright + any LLM.
Compare →Stripe's official agent SDK + MCP — payments, invoices, billing, and usage metering as agent tools.
Compare →Zapier's hosted MCP — 8,000+ app integrations exposed as allowlisted agent tools.
Compare →Atlassian's official hosted MCP — Jira + Confluence with OAuth, permission-bounded agent access.
Compare →Are you the builder of Claude Wrapped in the terminal, with a WASM raymarcher?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →