Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

SkillKeeper

Track your whole AI setup, from the menu bar

Details

External ID
1263386
Source
PH
Company
—
Product
SkillKeeper
Website domain
producthunt.com
Launched
Sept. 29, 2026
Cohort
—
Upvotes
3
Upvotes percentile
0.8905013897797733
Tags
Developer Tools, Artificial Intelligence, Menu Bar Apps
Fetched at
Sept. 30, 2026, 1 a.m.
Updated at
Sept. 30, 2026, 1 a.m.

Description

SkillKeeper shows which skills, agents, tools, MCP servers, commands, memory, hooks and plugins actually ran on your Mac, how many tokens each one spent, and what needs attention: loops, clashing triggers, skills that never fire. See how each skill is wired, catch what drifts from what you meant, and fine-tune it without opening a single file. Product Hunt visitors get 20% off with the code launch

Enrichment

Theme
utilities for Claude and Claude Code
Vertical
Horizontal
Function
Observability & eval
Audience
Developer
AI stance
AI feature
Project type
Commercial product
Normalized one-liner
menu bar monitor for local ai models and tools
Manually corrected
False

Could you build this?

Partial The menu bar UI is simple, but intercepting, tracing, and profiling heterogeneous local AI agent frameworks, MCP servers, and tool calls across arbitrary processes requires deep systems observability.

What it would actually take: Requires a native macOS app (Swift) combined with local daemon proxies or IPC observers (e.g., monitoring local unix domain sockets, stdin/stdout of spawned MCP processes, or standard OpenTelemetry trace collectors). Tracing token spend and tool collisions requires standardized middleware hooks into agent protocols (like Anthropic's MCP or LangChain). Low-level process monitoring and parsing disparate telemetry streams from different CLI tools is the core technical obstacle.

Competitors

Other products that read as similar to this one — 76 launches clear the similarity bar, closest 8 shown.

Attention rank: #19 of 77 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 313 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a observability & eval tool for Media & entertainment yet.