Projects
Products, platforms, and experiments we've shipped. Each one solving a real problem we ran into ourselves.
Mogplex is a Slack, GitHub, and cloud agent for building, editing, and maintaining code. It turns issues, pull requests, Slack requests, schedules, and standing assignments into queued agent runs where Claude Code, Codex, and MCP tools write, test, and ship changes through configurable gates. The web app and CLI give teams a place to dispatch work, inspect every run, and step in when a change needs approval or direction.
- Slack, GitHub, and cloud-triggered code work
- Build, edit, and maintain code with queued agent runs
- Per-run sandboxes for coding and test execution
- Claude Code, Codex, and MCP tool orchestration
- PR, check-run, and merge outputs behind configured gates
- CLI and web app for dispatching and inspecting work
Mogplex
Slack, GitHub, and cloud code agent
An agentic design canvas — describe what you want to create, and the AI agent builds the entire workflow on a node-based canvas. Extract color palettes, reverse-engineer animations, generate React components from screenshots, create brand kits from a logo. Powered by frontier models from Anthropic, OpenAI, and Google.
- Conversational workflow builder
- Color extraction and typography matching
- Component analysis and code generation
- Animation capture to CSS keyframes
- Brand kit and design system starter
- 8 prebuilt workflow templates
vMotif
AI-powered design workflows
The high-trust inference layer for teams that deploy at scale. Enterprise Inference runs the open-weight model you choose on dedicated single-tenant GPUs — the #1 Nemotron 3 Ultra provider on Artificial Analysis at 454 tokens/sec. The Blackbox Router connects one OpenAI-compatible endpoint to 300+ models with zero data retention enforced at the gateway. One per-token commit covers inference, routing, and the agent tooling — Agents API, AI-native IDE, VS Code extension, and CLI.
- #1 Nemotron 3 Ultra provider — 454 t/s, independently benchmarked
- Single-tenant Enterprise Inference on dedicated GPUs
- Router to 300+ models — one endpoint, one key, one bill
- Zero data retention enforced at the gateway
- PII removal before closed models, BYOK/CMK key management
- Agents API, AI-native IDE, VS Code extension, and CLI
Blackbox AI
Secure enterprise AI inference
Stop re-teaching your AI coding agents the same rules. Memories.sh is a local-first memory layer that stores context in a SQLite database with vector embeddings, then generates native config files for every major coding tool — Cursor, Claude Code, Copilot, Windsurf, Gemini, and more. Three commands: store, recall, generate.
- Durable local state with semantic recall
- 100MB on-device embedding model — no API calls
- Native config generation for 13+ tools
- Scoped memory (global vs. per-repo)
- Export to JSON/YAML anytime — zero lock-in
- Built-in MCP server for browser-based agents
Memories.sh
Durable state for coding agents
A chat-first creative studio where you describe what you want and AI builds it. Videos, images, memes, thumbnails, sprites — all generated through conversation. Includes a full suite of free cloud-powered utilities for video conversion, compression, background removal, and audio processing.
- AI-powered video editor with natural language control
- Chat-based Lab for end-to-end creation
- Image-to-video and text-to-video generation
- YouTube clip extraction and thumbnail generation
- Meme and social ad creator
- 15+ free utilities — no watermarks
Banan0
AI video & image studio
One search across 9 icon libraries — Lucide, Phosphor, Heroicons, Tabler, Feather, Remix, Hugeicons, Simple Icons, and Iconoir. Get React, Vue, Svelte, or raw SVG output. Available as an MCP server for AI coding agents, a CLI for your terminal, and a web UI for browsing. Normalize stroke widths across libraries for visual consistency.
- 9 icon libraries in one unified search
- React, Vue, Svelte, and SVG output
- MCP server for Cursor, v0, and Claude
- Starter packs (shadcn-ui, dashboard, ecommerce)
- Stroke normalization across libraries
- Bundle output — single file, 70% smaller
Unicon
Universal icon library
Credit Renew lets you fix errors on your credit report without a monthly repair company fee.
Connect a 3-bureau report or add one yourself. Review your scores and accounts in one place. Check late payments and negative items.
The AI Agent explains the details in your report and helps you choose the next step. Draft dispute letters for bureaus, creditors, and collectors. Test how each choice can affect your score. Set a budget and goals for what comes next.
- Reports from 3 bureaus with scores, accounts, and payment history
- AI Agent help with report details and next steps
- Letters for disputes with bureaus, creditors, and collectors
- Review of negative items and late payments
- Score simulator and trends for credit health
- Budget planner and credit goals
Credit Renew
Fix errors on your credit report yourself
