CandiSift vs Rezmatch.ai
CandiSift
github.comRezmatch.ai
rezmatch.aiSide by side
| Figure | CandiSift | Rezmatch.ai |
|---|---|---|
| Price from | Free | $19.99/mo |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | — |
| Plans published | 1 | 11 |
| Spec score · Candidate Screening Software | 8.0 (#6) | 8.5 (#3) |
| Security | The repository describes HTTP Basic authentication, security headers, rate limiting, request body limits, upload validation, and prompt-injection defenses. | The privacy policy lists encryption in transit and at rest, hashed API keys, managed secrets, least-privilege access controls, verified billing webhook signatures, and automatic expiry for temporary processing storage. |
Plans
Rezmatch.ai
- FreeFree
- 250 credits$15, paid once
- 250 credits one-time$15, paid once
- Starter$19.99 a month
- 1,000 credits$55, paid once
- 1,000 credits one-time$55, paid once
- Growth$79.99 a month
- 3,000 credits$150, paid once
- 3,000 credits one-time$150, paid once
- Scale$399.99 a month
In their own words
CandiSift
CandiSift is an open-source applicant tracking system for parsing resumes, matching candidates to job descriptions, and ranking applicants through a bias-audit workflow. Recruiters can create roles, upload PDF, DOCX, or plain-text resumes in batches, and review ranked results with accept or reject decisions. The screening sequence strips personally identifiable information, applies hard filters, ranks candidates, then sends those who remain to persona agents and human review. Token-cosine ranking, technical and risk personas, and synthesis contribute to that process. Before confirming a staged batch, users can view estimated processing costs; deterministic filters run before the paid LLM stage. CandiSift connects to Anthropic Claude through Agno persona agents, with an offline stub LLM available when there is no API key. It can run in Docker, uses SQLite by default, and supports a Postgres database URL. The project describes HTTP Basic authentication, security headers, rate limiting, upload validation, request limits, prompt-injection defenses, and an append-only audit log. The API includes a bias-audit endpoint. The project has no shipped accuracy benchmark; OCR, embeddings/FAISS, and skillNER are described as swaps rather than included defaults. The software fee is $0.00 per free; LLM processing may incur per-token costs.
Rezmatch.ai
Rezmatch.ai is an API that parses résumés and job descriptions into structured data and returns explainable candidate-role fit scores. Its endpoints accept text, URLs, or files; the site says PDFs parse natively and job-board URLs can be fetched directly. Parsing normalizes fields such as phone numbers, titles, employers, tenures, and skills. Matching identifies requirements that are met or missed and cites résumé evidence; a missing hard requirement caps the score. Rezmatch says automated parity tests check that name, age, and ethnicity signals do not affect scores. It returns scores and explanations, not hiring decisions, which remain the customer’s responsibility along with applicable legal compliance. Document content is held only during processing and, according to the privacy policy, is not written to the database or application logs. Developer tools include an OpenAPI specification, an interactive playground, and curl, Node.js, and Python examples. A hosted MCP server connects to Claude and other MCP-capable clients. The free plan includes 100 starter credits; paid plans start at $19.99 per month.