ai-job-search vs Hermes Agent
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
Hermes Agent
Self-hosted agent with skill learning, memory and Telegram/Discord/Slack gateway
Verdict
ai-job-search ranks higher, 97 to 87. Of the 4 score parts we measure for both, ai-job-search leads on 2, Hermes Agent on 1 and 1 is even.
- AdoptionHermes Agent leads by 4 points, 99 to 95: close to even.
- FreshnessEven at 100.
- Maintenanceai-job-search leads by 18 points, 99 to 81: a wide gap.
- Agent-readyai-job-search leads by 55 points, 85 to 30: 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 Hermes Agent if you are
Self-hosters wanting a persistent personal agent reachable from chat apps
- One gateway process serves Telegram, Discord, Slack, WhatsApp, Signal and email with shared history
- Seven terminal backends, including Docker, SSH, Modal, Daytona and Vercel Sandbox
| What we compare | ai-job-search | Hermes Agent |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 95, widely used | 99, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 99, healthy | 81, healthy |
| Agent-ready | 85, ready | 30, minimal |
| Facts from GitHub and the README | ||
| Stars | 71.4k | 262.9k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | Nov 2026 |
| Language | Python | Python |
| Docker | No | Yes |
| GPU | Not needed | Not needed |
| 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)
Hermes Agent
Hermes Agent is a Python agent from Nous Research that runs from a terminal UI or a single gateway process serving Telegram, Discord, Slack, WhatsApp, Signal and email. It keeps persistent memory, creates and refines skills after complex tasks, searches past sessions with FTS5, and runs cron-scheduled jobs. Model providers are switchable with `hermes model`, and tools can run on seven backends including local, Docker, SSH and Modal.
Who it is for: Self-hosters wanting a persistent personal agent reachable from chat apps
Strengths
- One gateway process serves Telegram, Discord, Slack, WhatsApp, Signal and email with shared history
- Seven terminal backends, including Docker, SSH, Modal, Daytona and Vercel Sandbox
- Built-in cron scheduler, FTS5 session search and agent-created skills compatible with agentskills.io
- Works with Nous Portal, OpenRouter, OpenAI or any custom endpoint; MCP servers supported
Weaknesses
- Windows installer may trigger antivirus false positives on the bundled uv.exe
- Installs via a curl-piped shell script rather than a pinned package on desktop
- Skill self-improvement and user modeling behavior is described, but no benchmarks are given
- no GPU
- Docker + Compose
- Needs Python, Node.js, ripgrep, FFmpeg, Honcho (user modeling)
- Models: Nous Portal, OpenRouter, OpenAI, custom 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.