ai-job-search vs nanobot
Two of the top projects in Assistants, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
ai-job-search
Claude Code workflow that searches job boards and drafts tailored CVs and cover letters
nanobot
Self-hosted personal AI agent reachable from browser, terminal and chat apps
Verdict
ai-job-search ranks higher, 92 to 85. Of the 3 score parts we measure for both, ai-job-search leads on 2, nanobot on none and 1 is even.
- Adoptionai-job-search leads by 5 points, 91 to 86.
- FreshnessEven at 100.
- MaintenanceWe do not score ai-job-search on this; nanobot has 91.
- Easy to runWe do not score ai-job-search on this; nanobot has 83.
- Agent-readyai-job-search leads by 40 points, 70 to 30: a wide gap.
Pick ai-job-search if you are
Job seekers comfortable with Claude Code, git and LaTeX
- Drafter-reviewer pipeline compiles CV and cover letter PDFs with page-count and ATS checks
- Postings pass a deterministic integrity gate for hidden text and injected instructions
Pick nanobot if you are
Self-hosters wanting a chat-reachable personal agent with memory and automations
- Many channels: Telegram, Discord, Slack, WeChat, Email, Mattermost, Linear, Feishu, Teams
- Built-in MCP, cron automations, long-running goals and PDF/Office file tools
| What we compare | ai-job-search | nanobot |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 91, widely used | 86, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | Not scored for this kind | 91, healthy |
| Easy to run | Not scored for this kind | 83, very easy |
| Agent-ready | 70, partly | 30, minimal |
| Facts from GitHub and the README | ||
| Stars | 63.1k | 49.3k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Oct 2026 | Sep 2026 |
| Language | Python | Python |
| Docker | No | Yes |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Not stated | Mentioned |
ai-job-search
A Claude Code project you fork and fill in with your profile. Slash commands (/setup, /scrape, /rank, /apply, /interview, /outcome) search job portals, score postings against a fit framework, and draft a LaTeX CV and cover letter that a second reviewer agent critiques before final PDF compilation. Portal skills target Danish boards, plus LinkedIn and freehire.me.
Who it is for: Job seekers comfortable with Claude Code, git and LaTeX
Strengths
- Drafter-reviewer pipeline compiles CV and cover letter PDFs with page-count and ATS checks
- Postings pass a deterministic integrity gate for hidden text and injected instructions
- Tracks applications end to end: /outcome, /gmail-sync, /notion-sync, /html-report, /interview
- Portal CLIs are auto-discovered, and /add-portal scaffolds one for your own market
Weaknesses
- Requires Claude Code with a paid subscription or API credits; other agent tools only partly supported
- Most portal skills target Denmark; other markets rely on LinkedIn, freehire.me or a custom portal
- Needs Python 3.10+, Bun and a full LaTeX install, which is a heavy setup
- A public fork exposes personal data in tracked files; a private repo is needed
- no GPU
- Needs Claude Code, Python 3.10+, Bun, LaTeX (lualatex, xelatex), pypdf or poppler (optional)
- Models: Claude (via Claude Code)
nanobot
nanobot is a Python (3.11+) personal agent framework that you use through a bundled WebUI, a terminal client, or channels such as Telegram, Discord, Slack, Email and Mattermost. It works with files (PDF, docx, xlsx, pptx), shell, web fetch, MCP tools, cron automations, long-term memory (Dream) and multi-agent delegation. It needs an external model provider or local model server, and exposes a Python SDK and an OpenAI-compatible API.
Who it is for: Self-hosters wanting a chat-reachable personal agent with memory and automations
Strengths
- Many channels: Telegram, Discord, Slack, WeChat, Email, Mattermost, Linear, Feishu, Teams
- Built-in MCP, cron automations, long-running goals and PDF/Office file tools
- Also usable as a Python SDK and OpenAI-compatible HTTP API
- Platform wheels bundle the WebUI and a native terminal UI
Weaknesses
- Supplies no model; needs a provider account or local model server
- Background gateway does not restart after reboot or crash without an OS service
- Interrupted subagent tasks and missed scheduled runs are not replayed after restart
- Source install needs Git and Bun; stable and source docs differ
- no GPU
- Docker + Compose
- Needs Python 3.11+, model provider or local model server, Bun (source install only)
- Models: OpenAI-compatible APIs, local LLMs
- port 8765
More in Assistants
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.