LiveAgent vs skill-recorder
The two are close in size: 2.0k stars for LiveAgent, 3.8k for skill-recorder. Over the days we have tracked them LiveAgent moved +12926.7% and skill-recorder +224.4%, so LiveAgent is growing faster right now.
They split the axes: LiveAgent leads on context depth and customization and privacy and model freedom, skill-recorder on noise control.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
A local‑first desktop AI agent that actually performs file-system operations, runs bash/managed processes, and extends via an MCP/Skills ecosystem with an optional remote Gateway.
- Stars
- 2.0k
- Tracked growth
- +12926.7%
- Maturity
- ●●●●●
- Last commit
- 3h ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Use your API key or third‑party relays for external models; desktop app is local-first
Converts a single on-screen recording (clicks, window switches, URLs, and optional narration) into a generalized, reusable Skill or scheduled Automation using the GitHub Copilot CLI.
- Stars
- 3.8k
- Tracked growth
- +224.4%
- Maturity
- ●●●●●
- Last commit
- 1d ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Requires GitHub Copilot access
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | LiveAgent | skill-recorder |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Diff + related files | ●●●●● Recording only |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● None mentioned | ●●●●● Manual review/edit |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Extensible skills & prompts | ●●●●● Manual edits only |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Copilot cloud required |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-own-key | ●●●●● Copilot only |
Setup ease What it takes to get a first useful run out of it. | ●●●●● Desktop installers | ●●●●● One-command install |
Which one to pick
Pick LiveAgent if…
Privacy-first — run a fully functional agent on your desktop with local key storage and extensible Skills while optionally routing models via your own endpoints.
- Context depth: Diff + related files (3/5 against 1/5)
- Customization: Extensible skills & prompts (5/5 against 2/5)
- Privacy: Self-hostable (4/5 against 2/5)
- Model freedom: Bring-your-own-key (5/5 against 1/5)
Pick skill-recorder if…
Privacy-aware — captures and processes recordings locally and only uploads event data and images to GitHub Copilot when you explicitly choose Analyze, making it easy to create real-world reusable agent skills from one run.
- Noise control: Manual review/edit (3/5 against 1/5)
What people want from each one
Stack-Cairn/LiveAgent
microsoft/skill-recorder
Questions people ask
Is LiveAgent better than skill-recorder?
They split the axes: LiveAgent leads on context depth and customization and privacy and model freedom, skill-recorder on noise control. LiveAgent is worth picking when privacy-first — run a fully functional agent on your desktop with local key storage and extensible Skills while optionally routing models via your own endpoints.
Which of LiveAgent and skill-recorder keeps my code private?
LiveAgent: Self-hostable (4/5). skill-recorder: Copilot cloud required (2/5).
What does each one cost to run?
LiveAgent: Use your API key or third‑party relays for external models; desktop app is local-first. skill-recorder: Requires GitHub Copilot access.
Full profiles: Stack-Cairn/LiveAgent and microsoft/skill-recorder. Everything else in Computer use.