专门为 agent 打造的 agent 搜索工具，具备多语言搜索能力，覆盖中文/英文/学术/代码/购物/金融/新闻/百科。
Score any document. Prove every claim.
Search infrastructure for AI agents: free by default, MCP-ready, LLM-context aware, and production-grade when needed.
Evidence-grounded AI research workflow for traceable claims, explicit uncertainty, causal-language checks, and reviewable JSON, Markdown, and Excel exports.
Open-source verifier for document citations, source evidence, RAG, and agents, with built-in document parsing.
Pi-native execution contracts for AI agents — evidence-gated completion, ordered plans, atomic decomposition, and compaction-safe resume.
A file-based governance harness that turns loose research ideas into proposals that hold up. Makes three things checkable: which page a claim rests on, what would refute it, and what the AI just changed. Human stays the sole adjudicator. Bilingual (EN / 繁中).
Trace every claim to its source. Identify every hallucination. Before the report reaches your client.
Staged operating-picture system for source health, research signals, and auditable decision workflows.
Agentic entity search engine that converts natural language queries into source-grounded entity tables using web search, scraping, LLM extraction, evidence verification, deduplication, ranking, and observability.
Evidence-verification and controlled-publication architecture for traceable claims, counterarguments, and revision conditions.
Stage351: Hybrid PQC-ready context-bound enforcement signature manifest layer for Stage350 session_sha256, CI/local context, Sigstore OIDC requirements, and ML-DSA intent metadata.
Evidence grounded causal reasoning for SemEval-2026 Task 12 (AER) retrieval augmented pipeline with hybrid search, cross-encoder reranking, and calibrated verification. Full research journey from baseline to current version.
Mandatory web-first research workflow for any agentic runtime. Three-tier grounding: official docs → research papers → community perspectives. Evidence-verification pipeline with evidence-prediction (not confidence tags). Integrates with findout CLI and skill4eyes. No answer from parametric knowledge alone.
REMEDA Stage329: submit-ready AI security audit artifacts built on Stage328 evidence match verification.
论文证据驱动的科研工作流 Agent / Paper-grounded research workflow agent for code analysis, safe experiment planning, metric parsing, verification, and reproduction reporting
Local-first agent orchestration CLI with evidence verification, auditable ledger, and human gates.
Hybrid Signature Manifest Verification Layer for verification of enforcement session binding, context integrity, hash consistency, Sigstore OIDC requirements, and PQC-ready signature metadata.
Public evaluation portfolio for ngOStandard Evidence Verifier: demonstration, assessment guidance and approved public materials only.
Public AURORA GRID methodology, verified calls, source discipline, and decision-audit record.
To associate your repository with the evidence-verification topic, visit your repo's landing page and select "manage topics."