ai-job-search vs openhuman
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
openhuman
Rust agent harness with desktop app, built-in memory and embeddable library
Verdict
ai-job-search ranks higher, 92 to 85. Of the 3 score parts we measure for both, ai-job-search leads on 1, openhuman on 1 and 1 is even.
- Adoptionai-job-search leads by 10 points, 91 to 81.
- FreshnessEven at 100.
- MaintenanceWe do not score ai-job-search on this; openhuman has 95.
- Easy to runWe do not score ai-job-search on this; openhuman has 67.
- Agent-readyopenhuman leads by 30 points, 100 to 70: 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 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
| What we compare | ai-job-search | openhuman |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 91, widely used | 81, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | Not scored for this kind | 95, healthy |
| Easy to run | Not scored for this kind | 67, easy |
| Agent-ready | 70, partly | 100, ready |
| Facts from GitHub and the README | ||
| Stars | 63.1k | 42.2k |
| License | MIT (permissive) | GPL-3.0 (copyleft) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Oct 2026 | Oct 2026 |
| Language | Python | Rust |
| Docker | No | Yes |
| GPU | Not needed | Optional |
| 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)
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
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.