CandiSift vs HRClaw

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.

HRClaw is a local-first recruiting copilot for creating job scorecards, reviewing batches of resumes and capturing candidate details from browser pages. It turns a job description into a reusable scorecard with hard filters, required and preferred signals, interview questions and red flags. Recruiters can import PDF, DOC and DOCX resumes in batches; HRClaw extracts candidate profiles and supports recommendations, reviews or rejections with evidence. An OCR fallback is included for scanned PDFs. A Chrome MV3 side panel captures candidate detail pages and sends them to the same scoring backend used for resume imports. The browser plugin also tracks candidate status, notes, communication results and follow-up times. Results can be shared as JSON or Markdown, or formatted for Feishu, DingTalk, Slack and Teams. The project is free and open source under the MIT license. Listed platforms include an extension, macOS, self-hosted use, web and Windows. The README describes a local app and lists workflow customization, team calibration, deployment assistance and enterprise process adaptation as private deployment or service options.