career-ops vs nanoclaw
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.
career-ops
Job-search agent that scores listings, tailors CVs and drafts applications
nanoclaw
Personal assistant that runs Claude agents in per-agent Linux containers behind chat apps
Verdict
career-ops ranks higher, 96 to 90. Of the 4 score parts we measure for both, career-ops leads on 2, nanoclaw on none and 2 are even.
- Adoptioncareer-ops leads by 11 points, 98 to 87.
- FreshnessEven at 100.
- Maintenancecareer-ops leads by 10 points, 93 to 83.
- Agent-readyEven at 85.
Pick career-ops if you are
Job seekers comfortable with a terminal and an AI coding CLI
- Drafts only: no auto-submit, and no mail transport in the code
- No telemetry or backend; CV goes only to the AI provider you choose
Pick nanoclaw if you are
Self-hosters wanting a container-isolated chat assistant they can read and fork
- Agents run in Docker containers and see only explicitly mounted directories
- Credential gateway injects keys at request time, with per-agent policies and rate limits
| What we compare | career-ops | nanoclaw |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 98, widely used | 87, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 93, healthy | 83, healthy |
| Agent-ready | 85, ready | 85, ready |
| Facts from GitHub and the README | ||
| Stars | 84k | 31.1k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | Nov 2026 |
| Language | JavaScript | TypeScript |
| Docker | Yes | No |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Not stated | Not stated |
career-ops
Runs inside an AI coding CLI (Claude Code, Codex, OpenCode, Qwen and others). You paste a job URL or description, and it checks the posting is live, scores fit against your CV, and generates an ATS PDF CV, cover letter and draft answers. It never submits applications or sends email, and keeps data on your machine.
Who it is for: Job seekers comfortable with a terminal and an AI coding CLI
Strengths
- Drafts only: no auto-submit, and no mail transport in the code
- No telemetry or backend; CV goes only to the AI provider you choose
- Covers evaluation, tailored PDF CV, cover letter, contact drafts, tracker and interview prep
- Portal scanner preconfigured for 100+ companies across Ashby, Greenhouse, Lever and Wellfound
Weaknesses
- Needs a separate AI CLI and provider; it does not run models itself
- README says early runs are rough until it learns your profile
- In-code check on CV rewording cannot catch every altered claim
- PDF output needs Playwright Chromium; non-Debian Linux needs manual libraries
- no GPU
- Docker + Compose
- Needs Node.js, An AI coding CLI (Claude Code, Codex, OpenCode, Qwen), Playwright Chromium (PDF generation)
- Models: Claude Code, Codex, OpenCode, Qwen, local models (see docs/RUNNING_ON_A_BUDGET.md)
nanoclaw
NanoClaw is a small TypeScript host process that routes messages from chat channels (Slack, Telegram, Discord, WhatsApp, iMessage and others) to Claude Agent SDK agents running in separate Docker containers. Each agent group has its own CLAUDE.md, memory and mounts, and API credentials are injected by a gateway rather than held in the container. Channels and alternative providers are added as skills into your own fork.
Who it is for: Self-hosters wanting a container-isolated chat assistant they can read and fork
Strengths
- Agents run in Docker containers and see only explicitly mounted directories
- Credential gateway injects keys at request time, with per-agent policies and rate limits
- Small codebase: one host process and two SQLite files per session
- Per-agent-group provider choice: Claude, Codex, OpenCode, Cursor or Ollama via skills
Weaknesses
- Customization and setup recovery depend on Claude Code, not config files
- Default path is built around Anthropic credentials and the Claude Agent SDK
- Channel adapters are not in trunk; each needs an /add-<channel> skill
- Prebuilt hardened image and managed Slack app require a free account
- no GPU
- Needs Docker, Node.js, pnpm, jq, Claude Code, OneCLI Agent Vault
- Models: Claude (Agent SDK), OpenAI Codex, OpenRouter, Google, DeepSeek via OpenCode, Cursor Agent SDK, Ollama 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.