Banana Code vs Agent Lab

Banana Code is a mobile AI coding agent. Pick a GitHub repo, describe the changes you want in plain English, choose any LLM model, and get a pull request with working code. All from your phone. HOW IT WORKS 1. Connect your GitHub account 2. Select a repository (public or private) 3. Type what you want changed ("Add error handling to the payment module") 4. Pick a model (ANY model!) 5. Watch the agent work in real time 6. Review the PR and merge when ready The agent clones your repo, creates a branch, makes changes across multiple files, and opens a pull request. Sessions run on a dedicated server, so you can close the app and come back later to get your PR. BRING YOUR OWN KEY Unlike tools that lock you into one model at $20+/month, Banana Code lets you use your own API key from OpenRouter, Anthropic, or OpenAI. Sign in with your ChatGPT subscription and use models you already pay for. The app is just $5/month. FEATURES - Any LLM model via OpenRouter (hundreds of options with live pricing) - Real-time streaming so you can watch the agent think and code - Full GitHub integration: clone, branch, commit, push, and PR creation - Attach screenshots to give the agent visual context - Session history with full conversation logs - Supabase integration (beta): run SQL, inspect schemas, write migrations - Dark theme with zero distractions YOUR CODE STAYS YOURS Repos are cloned to a temporary workspace and deleted after each session. API keys are encrypted at rest using device-level secure storage. You can revoke GitHub access or delete your account and all data at any time from Settings. AI-generated code should always be reviewed before merging. Banana Code is a tool for developers, not a replacement for code review. REQUIREMENTS - GitHub account (free) - API key from OpenRouter, Anthropic, or OpenAI (pay-per-use, typically pennies per session) - Internet connection required SUBSCRIPTION - $5/month after a 3-day free trial - Cancel anytime from Settings or your Apple ID subscriptions - Payment charged to Apple ID account at confirmation of purchase - Subscription auto-renews unless cancelled at least 24 hours before the end of the current period Privacy Policy: https://bananacode.ai/privacy Terms of Service: https://bananacode.ai/terms

Agent Lab is a learning and experimentation playground for AI agents, built for AI learners, agent developers, and product managers. It doesn't just run agents — it makes every step of an agent's execution visible, so you can finally understand how agents actually work. Unlike an ordinary AI chat app, Agent Lab is about learning, experimenting, debugging, and visualization. On every run you can see the prompts, tool calls, retrieval, tokens, and latency — nothing is hidden. Get started fast · On-device local models: download a small Qwen model on first use (Wi-Fi recommended), then run it fully offline — no API key and no second machine required. Cost is always 0, and tokens and latency are shown for real. · Download on demand: grab other open-source models your device can actually run, with capability gating based on your chip and memory. · Cloud models: works with Chat Completions-compatible APIs (DeepSeek, Moonshot, OpenRouter, and more) and Anthropic Claude — just enter your key, base URL, and model. Three built-in demos · Customer Support Agent — demonstrates tool calling and workflow with a built-in mock order system, no real backend needed. · RAG Knowledge Base — comes with curated reference docs (LangGraph, MCP, LLM APIs, Python) and lets you upload your own PDF / Markdown / TXT, then inspect the retrieved chunks, similarity scores, and final answer. · Research Agent — shows how an agent plans on its own: Planner → Search → Read → Summarize → Answer. Unified visual debugging Every demo offers three views: · Timeline — the full step-by-step sequence of LLM and tool calls · Graph — the workflow graph, highlighting the active node as it runs · Console — expand any step to see System / User / Assistant prompts, the complete LLM request and response JSON, tool requests and responses, tokens, estimated cost, latency, and errors Security and privacy · API keys are stored encrypted on-device via the system Keychain — local only, never uploaded to any server. · Uploaded knowledge-base files and the vector indexes built from them stay on your device and can be deleted anytime. · On-device inference runs fully offline; your data never leaves the device. No sign-up, no login — open it and go. Make every step an agent takes visible.