mantis vs plannotator
plannotator is much bigger: 8.4k stars against 935. Over the days we have tracked them mantis moved +10288.9% and plannotator +41.8%, so mantis is growing faster right now.
They split the axes: mantis leads on context depth and noise control and model freedom, plannotator on setup ease.
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 modular, stack-agnostic suite of security review skills that lets coding agents find, reproduce, dedupe, and patch vulnerabilities with sandboxed execution and a sequential pipeline.
- Stars
- 935
- Tracked growth
- +10288.9%
- Maturity
- ●●●●●
- Last commit
- 2d ago
- Language
- Python
- License
- Apache-2.0
- Cost to run
- Your API key; model/compute costs apply.
A local, browser-based review surface that plugs directly into many agent hooks so you can annotate plans, diffs, and HTML and send structured feedback back to the agent.
- Stars
- 8.4k
- Tracked growth
- +41.8%
- Maturity
- ●●●●●
- Last commit
- 1d ago
- Language
- TypeScript
- License
- Apache-2.0
- Cost to run
- Free, self-hosted; external agent API keys or accounts may be required
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 | mantis | plannotator |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Whole-repo analysis | ●●●●● Diff-focused |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Dedupe & filters | ●●●●● No noise controls |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Customizable prompts | ●●●●● Config file options |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Self-hostable |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-own-key | ●●●●● Multiple providers |
Setup ease What it takes to get a first useful run out of it. | ●●●●● Agent + API key | ●●●●● One-command install |
Which one to pick
Pick mantis if…
Security-first — pick Mantis when you need a focused, extensible toolkit of agent skills specialized for end-to-end vulnerability discovery, reproduction, and patching in isolated environments.
- Context depth: Whole-repo analysis (5/5 against 2/5)
- Noise control: Dedupe & filters (4/5 against 1/5)
- Model freedom: Bring-your-own-key (5/5 against 3/5)
Pick plannotator if…
Local and agent-integrated: pick Plannotator when you want a local browser UI to review agent plans and code diffs and to send feedback directly to the agent.
- Setup ease: One-command install (5/5 against 3/5)
What people want from each one
google/mantis
backnotprop/plannotator
Questions people ask
Is mantis better than plannotator?
They split the axes: mantis leads on context depth and noise control and model freedom, plannotator on setup ease. mantis is worth picking when security-first — pick Mantis when you need a focused, extensible toolkit of agent skills specialized for end-to-end vulnerability discovery, reproduction, and patching in isolated environments.
Which of mantis and plannotator keeps my code private?
mantis: Self-hostable (4/5). plannotator: Self-hostable (4/5).
What does each one cost to run?
mantis: Your API key; model/compute costs apply.. plannotator: Free, self-hosted; external agent API keys or accounts may be required.
Full profiles: google/mantis and backnotprop/plannotator. Everything else in Code review agents.