career-ops vs ZeroClaw
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
ZeroClaw
Single-binary Rust agent runtime that answers across 30+ chat channels
Verdict
career-ops ranks higher, 95 to 88. Of the 4 score parts we measure for both, career-ops leads on 2, ZeroClaw on none and 2 are even.
- Adoptioncareer-ops leads by 15 points, 97 to 82: a wide gap.
- FreshnessEven at 100.
- Maintenancecareer-ops leads by 12 points, 93 to 81.
- 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 ZeroClaw if you are
Self-hosters running an always-on personal agent across chat apps
- Single Rust binary with one TOML config at ~/.zeroclaw/config.toml
- 30+ channel adapters feed the same agent loop
| What we compare | career-ops | ZeroClaw |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 97, widely used | 82, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 93, healthy | 81, healthy |
| Agent-ready | 85, ready | 85, ready |
| Facts from GitHub and the README | ||
| Stars | 82.1k | 33.3k |
| License | MIT (permissive) | Apache-2.0 (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | Nov 2026 |
| Language | JavaScript | Rust |
| Docker | Yes | Yes |
| GPU | Not needed | Not stated |
| arm64 or Apple Silicon | Not stated | Mentioned |
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)
ZeroClaw
ZeroClaw is a Rust agent runtime configured with one TOML file. It connects to LLM providers (Anthropic, OpenAI, Ollama, about 20 others) and receives messages from 30+ channels such as Discord, Telegram, Matrix and email. The agent acts through shell, browser, HTTP, hardware and MCP tools, gated by a default supervised autonomy level and optional OS-level sandboxes.
Who it is for: Self-hosters running an always-on personal agent across chat apps
Strengths
- Single Rust binary with one TOML config at ~/.zeroclaw/config.toml
- 30+ channel adapters feed the same agent loop
- Default supervised autonomy, with Landlock, Bubblewrap, Seatbelt or Docker sandboxes
- Provider fallback chains and routing; any OpenAI-compatible endpoint works
Weaknesses
- Config needs provider, agent and risk-profile sections plus schema_version = 4
- YOLO mode disables safety gates, so misconfiguration risk sits with the user
- Memory is SQLite with embeddings; no other backends are listed
- Dual MIT or Apache-2.0 licensing, with the name and logo trademarked
- Docker + Compose
- Needs SQLite
- Models: Anthropic, OpenAI, Ollama, OpenAI-compatible endpoints
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.