CandiSift

6.7easy start · #6 of 36
in Candidate Screening Software

Free to practise onyes
Free trialnot on record
Well documentedyes
Runs where you worknot on record

Runs on api, self-hosted, Web.

CandiSift is ranked #6 of 36 in candidate screening software on The Geeks Club. It runs on API, Self-hosted, Web. There is a free plan.

CandiSift plans and pricing

All plans

Open-source self-hosted Free No software fee stated; LLM processing can incur per-token costs github.com · 4 Oct 2026

Compared on candidate screening software

Application screening: Yes
Deployment type: multi-platform

Best CandiSift alternatives

See all 20

CVViZ Job Distribution 0 of 4 in the starter kit Lesson 17.3 SkipCV 0 of 4 in the starter kit Lesson 27.0 Humanly Intelligent CV Screening 0 of 4 in the starter kit Lesson 36.9 Truffle 0 of 4 in the starter kit Lesson 46.8 X0PA AI 0 of 4 in the starter kit Lesson 56.8 Octagnt 0 of 4 in the starter kit Lesson 76.7

The record

Product: CandiSift is an open-source applicant tracking system for AI resume screening, CV parsing, job description and candidate matching, and bias-audited ranking.
Screening flow: Its workflow parses resumes, strips personally identifiable information, applies hard filters, ranks candidates, and sends survivors to persona agents and human review.
File formats: Resume ingestion supports PDF, DOCX, and plain-text files, including multi-file uploads.
Ranking and review: The product provides token-cosine ranking, technical and risk persona agents, synthesis, and a recruiter interface with ranked results and accept or reject decisions.
Cost controls: Users can see an estimated processing cost before confirming a staged batch, and deterministic hard filters run before the paid LLM stage.
LLM integration: CandiSift integrates with Anthropic Claude through Agno persona agents; without an API key, it can use an offline stub LLM.
Security: The repository describes HTTP Basic authentication, security headers, rate limiting, request body limits, upload validation, and prompt-injection defenses.
Privacy and audit: CandiSift says it strips PII before a model sees candidate data and keeps an append-only audit log of scores, rationales, decisions, and versions.
Bias audit: The API includes a bias-audit endpoint covering pass-through and recommendation mix.
Deployment and storage: The app can run in Docker, stores state in SQLite by default, and supports configuring a Postgres database URL.
Notable limits: The project says it has no shipped accuracy benchmark and that OCR, embeddings/FAISS, and skillNER are documented swaps rather than included default capabilities.
Intended users: The README describes a recruiter workflow for creating roles, screening uploaded resumes, reviewing ranked results, and accepting or rejecting candidates.
Price from: Free

Where it ranks on The Geeks Club

Best Candidate Screening Software in 2026#6 of 36
Best AI Recruiting Assistants in 2026#8 of 30

Is CandiSift yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote CandiSift

Sources

github.com/confused-ai/candisift· checked 4 Oct 2026