ai-job-search vs nanobot
The two are close in size: 40.8k stars for ai-job-search, 47.7k for nanobot. Over the days we have tracked them ai-job-search moved +46.7% and nanobot +4.3%, so ai-job-search is growing faster right now.
nanobot leads on privacy and model freedom and setup ease. ai-job-search 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
Local-first, end-to-end job-application framework that scrapes portals, tailors LaTeX CVs/cover letters, runs a drafter–reviewer agent pipeline, and archives applications for repeatable, owned job hunting.
- Stars
- 40.8k
- Tracked growth
- +46.7%
- Maturity
- ●●●●●
- Last commit
- 1d ago
- Language
- Python
- License
- MIT
- Cost to run
- Requires Claude Code (Anthropic) CLI / third‑party access.
An ultra-lightweight, self-hosted personal agent runtime that pairs a small, readable core with built-in WebUI, persistent memory, automation, and flexible model routing for long-running workflows.
- Stars
- 47.7k
- Tracked growth
- +4.3%
- Maturity
- ●●●●●
- Last commit
- 18h ago
- Language
- Python
- License
- MIT
- Cost to run
- Your API key; optional paid hosting
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 | ai-job-search | nanobot |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Repo + documents | ●●●●● Diff + related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Reviewer + dedupe | ●●●●● Basic filters/config |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Templates & portals | ●●●●● Presets & automations |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Third-party cloud | ●●●●● Fully local possible |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Claude + others | ●●●●● Bring-your-own-key |
Setup ease What it takes to get a first useful run out of it. | ●●●●● CLI + deps | ●●●●● One-command start |
Which one to pick
Pick ai-job-search if…
Extensible end-to-end workflow — use it when you want a local CLI that orchestrates scraping, fit scoring, CV/cover-letter generation (LaTeX), and a reviewer agent to produce production-ready applications you control.
Pick nanobot if…
Self-hosted — run a lightweight, extendable personal agent locally (or with your own API keys) that includes WebUI, long-term memory, and automation for persistent workflows.
- Privacy: Fully local possible (5/5 against 2/5)
- Model freedom: Bring-your-own-key (5/5 against 3/5)
- Setup ease: One-command start (5/5 against 3/5)
What people want from each one
MadsLorentzen/ai-job-search
HKUDS/nanobot
Hacker News: Nanobot: Ultra-Lightweight Alternative to OpenClaw drew 257 points and 128 comments.
Questions people ask
Is ai-job-search better than nanobot?
nanobot leads on privacy and model freedom and setup ease. ai-job-search does not take any axis by a clear margin. ai-job-search is worth picking when extensible end-to-end workflow — use it when you want a local CLI that orchestrates scraping, fit scoring, CV/cover-letter generation (LaTeX), and a reviewer agent to produce production-ready applications you control.
Which of ai-job-search and nanobot keeps my code private?
ai-job-search: Third-party cloud (2/5). nanobot: Fully local possible (5/5).
What does each one cost to run?
ai-job-search: Requires Claude Code (Anthropic) CLI / third‑party access.. nanobot: Your API key; optional paid hosting.
Full profiles: MadsLorentzen/ai-job-search and HKUDS/nanobot. Everything else in Personal assistants.