Jakub Hecht
2
Launches
0
Followers
15
Upvotes
🔥 1
Day streak
Achievements 3
All badgesBadge Bearer
First Launch
Upvote Pioneer
Products by Jakub
2 total
KyttoMCP
Automation-tools
Managing multiple Model Context Protocol servers across different AI coding tools creates a fragmented configuration nightmare. Developers end up with scattered settings across JSON and TOML files, unable to see the complete picture of what's active where. KyttoMCP directly addresses this coordination problem with a focused control panel designed around the specific workflows of teams using Claude, Cursor, VS Code, and other compatible clients. The product's core strength is its unified matrix view. Rather than hunting through configuration files, users can see at a glance which MCP servers are enabled across each client and toggle them from one interface. This single source of truth eliminates the most immediate friction point in managing multi-server setups. Beyond visibility, KyttoMCP includes practical operational safeguards. It estimates the context window cost of each server's tool definitions, letting users optimize their configuration without accidentally bloating context usage. Before any configuration change, the tool creates timestamped backups. Changes themselves are written atomically, preventing the corrupted or truncated files that plague JSON editing. These design choices reflect a philosophy of "built for trust"—the application prioritizes data safety and user confidence over aggressive feature expansion. The local-first architecture reinforces this positioning. Configuration files remain on the user's computer; there's no cloud account, no sync service, no third-party intermediary between the user and their settings. This stands out against the industry trend toward cloud-hosted management tools and appeals directly to users who value control and privacy. The pricing model is equally straightforward. KyttoMCP is free throughout its beta phase with no account required. Installation is platform-specific: a DMG file for macOS and a Windows installer, with documented launch procedures including handling for unsigned-developer warnings. The product targets a specific segment: developers and teams managing MCP complexity across multiple tools. It doesn't attempt to abstract away MCP servers themselves or add entirely new functionality. Instead, it solves a genuine coordination problem that emerges as MCP adoption grows. For teams already juggling multiple AI clients and MCP server configurations, KyttoMCP eliminates a category of repetitive maintenance work. Its strength lies in this focused scope and its commitment to safety and transparency.
NativeCode
Ai-code-editors
Privacy-conscious developers have few good options when it comes to AI-assisted coding tools. Most either bundle Chromium into their downloads, inflating file sizes to 150 MB or more, or require uploading projects to cloud servers. NativeCode addresses both issues by offering a compact, local-first alternative that keeps code on your machine while maintaining a minimal footprint. The product pairs a VS Code-inspired interface built on Monaco with your choice of local models running in Ollama, LM Studio, or any OpenAI-compatible server. The macOS download weighs just 7.11 MB because it leverages the system WebView built into modern operating systems — WKWebView on macOS, WebView2 on Windows — rather than shipping its own copy of Chromium. This design decision translates to meaningful storage savings without sacrificing functionality. Version 2.0 Beta, the latest release, significantly strengthens the core agent. It introduces plan mode for safe refactoring, project memory, reusable skills, pinned context, and self-review capabilities. The agent handles automatic context compaction and can access the web when needed. File and shell tool access is explicitly guarded, revealing a commitment to security over convenience. The tool supports every model its backend reports, with the ability to stream reasoning separately for models that provide it. Users can adjust thinking effort, switch backends or models without restarting conversations, and attach screenshots directly to vision-capable models. This flexibility removes friction when experimenting with different approaches or scaling up to more capable models. The business model is straightforward. NativeCode is free with no subscription requirement, no account creation, and no telemetry. The founder built this specifically because existing options either shipped unnecessary bloat or invaded privacy — frustrations many developers share. What emerges from these choices is a product designed around developer autonomy. It assumes users want control over their models, their data, and their tools, without paying for that privilege through subscriptions or data harvesting. For developers already running local LLM infrastructure or willing to set it up, NativeCode removes a major friction point: the need to choose between privacy, cost, and capability. Whether this approach catches on depends partly on whether developers embrace local inference as a default rather than a niche preference.