openhuman 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.
openhuman
Rust agent harness with desktop app, built-in memory and embeddable library
career-ops
Job-search agent that scores postings against your CV and drafts applications
Verdict
openhuman ranks higher, 84 to 77. Of the 5 score parts we measure for both, openhuman leads on 2, career-ops on 1 and 2 are even.
- Adoptioncareer-ops leads by 16 points, 91 to 75: a wide gap.
- FreshnessEven at 100.
- MaintenanceEven at 94.
- Easy to runopenhuman leads by 34 points, 67 to 33: a wide gap.
- Agent-readyopenhuman leads by 15 points, 100 to 85: a wide gap.
Pick openhuman if you are
Users wanting a self-run agent app, and Rust developers embedding agents
- Embeds as a typed Rust library, no sidecar or daemon needed
- Public benchmark repo; reports 68 MB peak memory and 19.8 s median task time
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 | openhuman | career-ops |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 75, popular | 91, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 94, healthy | 94, healthy |
| Easy to run | 67, easy | 33, some setup |
| Agent-ready | 100, ready | 85, ready |
| Facts from GitHub and the README | ||
| Stars | 42k | 74.6k |
| License | GPL-3.0 (copyleft) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Oct 2026 | Oct 2026 |
| Language | Rust | JavaScript |
| Docker | Yes | Yes |
| GPU | Optional | Optional |
| arm64 or Apple Silicon | Mentioned | Not stated |
openhuman
OpenHuman is a single-process Rust agent harness shipped as a desktop app (macOS, Windows, Linux), a terminal app, a headless server and an embeddable Rust crate. It bundles memory recalled with citations, browser and desktop control, MCP and skills, 14 messaging channels, durable workflows, and local or BYOK models. The README reports its own benchmark on ten SWE-bench tasks and claims 500 agents fit on a $10 VPS; it is labelled early beta.
Who it is for: Users wanting a self-run agent app, and Rust developers embedding agents
Strengths
- Embeds as a typed Rust library, no sidecar or daemon needed
- Public benchmark repo; reports 68 MB peak memory and 19.8 s median task time
- Local models (Ollama, LM Studio, MLX) or BYOK across 26 providers
- Approval gate, OS-jail or Docker sandboxing, secrets stored in OS keyring
Weaknesses
- Labelled early beta; README warns of rough edges
- Benchmark is self-run on only ten tasks
- GPL-3.0 license constrains embedding in proprietary products
- 119 OAuth app integrations go through Composio, an external service
- GPU optional
- Docker + Compose
- Needs Composio (OAuth integrations), Ollama / LM Studio / MLX (optional local models), Docker (optional sandbox)
- Models: Ollama, LM Studio, MLX, OpenAI-compatible APIs, 26 BYOK providers
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.