nanobot vs career-ops
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.
nanobot
Self-hosted Python personal agent with WebUI, TUI and chat-app channels
career-ops
Job-search agent that scores postings against your CV and drafts applications
Verdict
nanobot ranks higher, 84 to 77. Of the 5 score parts we measure for both, nanobot leads on 1, career-ops on 3 and 1 is even.
- Adoptioncareer-ops leads by 10 points, 91 to 81.
- FreshnessEven at 100.
- Maintenancecareer-ops leads by 3 points, 94 to 91: close to even.
- Easy to runnanobot leads by 50 points, 83 to 33: a wide gap.
- Agent-readycareer-ops leads by 55 points, 85 to 30: a wide gap.
Pick nanobot if you are
Self-hosters wanting a personal agent in browser, terminal and chat apps
- Many channels: Telegram, Discord, Slack, WeChat, Email, Mattermost, Linear, Teams, Feishu
- Built-in long-term memory, cron automations and /goal long-running tasks
Pick career-ops if you are
Job seekers comfortable running an AI CLI in a terminal
- Drafts only: no auto-submit and no mail transport in the code, per the README
- No telemetry or backend; CV goes only to your chosen AI provider
| What we compare | nanobot | career-ops |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 81, widely used | 91, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 91, healthy | 94, healthy |
| Easy to run | 83, very easy | 33, some setup |
| Agent-ready | 30, minimal | 85, ready |
| Facts from GitHub and the README | ||
| Stars | 49k | 74.6k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Sep 2026 | Oct 2026 |
| Language | Python | JavaScript |
| Docker | Yes | Yes |
| GPU | Not needed | Optional |
| arm64 or Apple Silicon | Mentioned | Not stated |
nanobot
nanobot is a Python agent framework you run yourself and use from a browser WebUI, a terminal TUI, or chat apps such as Telegram, Discord, Slack and Email. It keeps session history and long-term memory (Dream), runs shell, web, MCP and cron tools, and supports long-running goals. It also exposes a Python SDK and an OpenAI-compatible API, and needs an external model provider or local server.
Who it is for: Self-hosters wanting a personal agent in browser, terminal and chat apps
Strengths
- Many channels: Telegram, Discord, Slack, WeChat, Email, Mattermost, Linear, Teams, Feishu
- Built-in long-term memory, cron automations and /goal long-running tasks
- Works with OpenAI-compatible APIs, Ollama and vLLM, with fallback models
- Installs via script, uv or pip; Python SDK and OpenAI-compatible API included
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; native TUI wheels cover limited platforms
- no GPU
- Docker + Compose
- Needs Python 3.11+, model provider or local model server
- Models: OpenAI-compatible APIs, Ollama, vLLM
- port 8765
career-ops
Runs inside an AI coding CLI (Claude Code, Codex, OpenCode, Qwen and others). You paste a job URL or text and it checks the posting is still live, scores fit against your CV, and drafts a tailored ATS PDF, cover letter and form answers. It never submits or sends anything; data stays local apart from calls to the AI provider you choose. It also has a portal scanner, a terminal dashboard and batch evaluation.
Who it is for: Job seekers comfortable running an AI CLI in a terminal
Strengths
- Drafts only: no auto-submit and no mail transport in the code, per the README
- No telemetry or backend; CV goes only to your chosen AI provider
- Portal scanner preconfigured for 100+ companies across Ashby, Greenhouse, Lever and Wellfound
- Works with several AI CLIs and can use local or free-tier models
Weaknesses
- Requires an AI CLI and a model provider; output quality depends on the model
- README says early runs are rough until it learns your profile
- CV rewording check cannot catch every fabrication; manual review required
- Playwright Chromium needed for PDF generation
- GPU optional
- Docker + Compose
- Needs Node.js, Playwright Chromium, AI CLI (Claude Code, Codex, OpenCode, Qwen)
- Models: Claude, Codex, OpenCode, Qwen, local models
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.