Nli Python Packages

proofpath

Verify that the sources behind a claim actually say what the claim says — citation existence, retraction and entailment checks in one offline-first CLI.

director-ai

Real-time LLM hallucination guardrail — NLI + RAG fact-checking with opt-in claim-level streaming contradiction halt. Drop-in for any LLM backend.

opendecision

OpenDecision is an open-source semantic decision engine like typesafe's jev.

backfire-kernel

Real-time LLM hallucination guardrail — NLI + RAG fact-checking with opt-in claim-level streaming contradiction halt. Drop-in for any LLM backend.

openagent-eval

Local-first evaluation framework for RAG systems and AI Agents. 18+ metrics, CLI + SDK, framework-agnostic. The pytest of AI evaluation.

poordjaevin

Djævin: calibrated local-first decision layer with a Devin ACP backend - no API key needed

dlk

A PyTorch Based Deep Learning Quick Develop Framework. One-Stop for train/predict/server/demo

citationguard

证伪优先的引用核验:论文存在性 / 元数据 / 论点支撑三重检查,可被 Claude Code、Codex、Cursor 以 MCP 调用 · Skeptical citation auditor for agent writing workflows · PyPI: citationguard

webfetch-llm

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with query-dependant TTL that no API offers.

director-ai-lite

Real-time LLM hallucination guardrail — NLI + RAG fact-checking with opt-in claim-level streaming contradiction halt. Drop-in for any LLM backend.

legal-rag-verifier

Proof of concept: sentence-level verification for legal RAG during generation, with KV-cache rollback. An LLM judge as the auditor improved answers; the packaged DeBERTa head did not.

omni-nli

A multi-interface (REST and MCP) server for natural language inference

longtracer

Detect hallucinations in LLM responses. Verify every claim against source documents using hybrid STS + NLI. Works with LangChain, LlamaIndex, or any RAG pipeline. pip install longtracer

llm-antibodies

Antibodies for LLMs hallucinations (grouping LLM as a judge, NLI, reward models)

gts-engine

GTS Engine: A powerful NLU Training System。GTS引擎（GTS-Engine）是一款开箱即用且性能强大的自然语言理解引擎，聚焦于小样本任务，能够仅用小样本就能自动化生产NLP模型。

antibodies-rafaelsandroni

Antibodies for LLMs hallucinations (grouping LLM as a judge, NLI, reward models)

ega

Runtime enforcement layer for LLM outputs. Verifies claims against source evidence before emit. Not an eval tool.