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.
- TokenTracker · ph · 2026-09-10 · 1 upvotes · similarity 0.44
- SecAIQ Watch · ph · 2026-09-21 · 68 upvotes · similarity 0.44
- Kaiku · ph · 2026-09-25 · 78 upvotes · similarity 0.42
- SkillGrill · ph · 2026-09-22 · 2 upvotes · similarity 0.41
- Skills Janitor · ph · 2026-04-13 · 243 upvotes · similarity 0.40
- Pollymetric · ph · 2026-09-30 · 1 upvotes · similarity 0.39
- Harness Manager · ph · 2026-09-24 · 79 upvotes · similarity 0.39
- AIMarketly · ph · 2026-09-26 · 1 upvotes · similarity 0.39
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a observability & eval tool for Media & entertainment yet.