caveman vs pi
The two are close in size: 113.8k stars for caveman, 116.6k for pi. Over the days we have tracked them caveman moved +7.6% and pi +53.9%, so pi is growing faster right now.
caveman leads on noise control and setup ease. pi does not take any axis by a clear margin.
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
Compresses both what the agent writes (a caveman-style skill) and what it reads (a local proxy) to cut token usage while keeping originals accessible.
- Stars
- 113.8k
- Tracked growth
- +7.6%
- Maturity
- ●●●●●
- Last commit
- 1d ago
- Language
- Go
- License
- Apache-2.0
- Cost to run
- Free to install — uses your AI provider's billing
An open-source, self-extensible coding agent harness that bundles a unified multi-provider LLM API, agent runtime, CLI and terminal UI in one project.
- Stars
- 116.6k
- Tracked growth
- +53.9%
- Maturity
- ●●●●●
- Last commit
- 17m ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Your API key for cloud models
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 | caveman | pi |
|---|---|---|
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 | ●●●●● Diff + related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Basic filters & dry-run | ●●●●● None mentioned |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Configurable rules & modes | ●●●●● Config & extensions |
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. | ●●●●● Many specific providers | ●●●●● Multiple providers |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-command install | ●●●●● Config + API key |
Which one to pick
Pick caveman if…
Token-savings — use Caveman when you want an easy, local install that meaningfully reduces model input and output tokens without changing correctness.
- Noise control: Basic filters & dry-run (3/5 against 1/5)
- Setup ease: One-command install (5/5 against 3/5)
Pick pi if…
Privacy-friendly — can run locally or in a container while supporting multiple LLM providers via a unified API.
What people want from each one
JuliusBrussee/caveman
earendil-works/pi
Questions people ask
Is caveman better than pi?
caveman leads on noise control and setup ease. pi does not take any axis by a clear margin. caveman is worth picking when token-savings — use Caveman when you want an easy, local install that meaningfully reduces model input and output tokens without changing correctness.
Which of caveman and pi keeps my code private?
caveman: Self-hostable (4/5). pi: Self-hostable (4/5).
What does each one cost to run?
caveman: Free to install — uses your AI provider's billing. pi: Your API key for cloud models.
Full profiles: JuliusBrussee/caveman and earendil-works/pi. Everything else in CLI coding agents.