director-ai Files

Real-time LLM hallucination guardrail — NLI + RAG fact-checking

Brought to you by: anulum

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
README.md	2026-02-27	1.6 kB	0
v1.2.1 -- Scorer Hardening _ Rust Safety Lints source code.tar.gz	2026-02-27	1.3 MB	0
v1.2.1 -- Scorer Hardening _ Rust Safety Lints source code.zip	2026-02-27	1.5 MB	0
Totals: 3 Items		2.8 MB	0

What's New

Scorer hardening

strict_mode parameter — disables heuristic fallbacks when NLI is unavailable. Returns neutral 0.5 instead of keyword heuristics, preventing misleading scores in production deployments without torch installed.

python scorer = CoherenceScorer(strict_mode=True, threshold=0.6)

Configurable scoring weights — w_logic and w_fact constructor params (default 0.6/0.4) let you tune the logical vs. factual divergence balance for your domain.

python scorer = CoherenceScorer(w_logic=0.3, w_fact=0.7) # fact-heavy for RAG apps

Rust kernel safety

#![deny(unsafe_code)] enforced on 5 of 6 Backfire Kernel crates (backfire-types, backfire-core, backfire-physics, backfire-ssgf, backfire-observers). The compiler now rejects any future unsafe blocks.
backfire-ffi documents why deny(unsafe_code) can't apply (PyO3 proc macros generate unsafe internally) and carries FFI safety invariants.
4 safety invariants documented on backfire-core: halt irreversibility, NaN/Inf lethality, independent halt mechanisms, zero hot-path allocations.

Documentation

"Known Limitations" section in README — honest about heuristic accuracy, summarisation weakness, single-document NLI, and weight sensitivity.
Full CHANGELOG entries for both v1.2.0 and v1.2.1.

Tests

4 new tests: strict_mode logical/factual neutral return, heuristic mode divergence, custom weight assignment.
378 tests passing (8 skipped — optional deps).

Full Changelog

https://github.com/anulum/director-ai/compare/v1.2.0...v1.2.1

Source: README.md, updated 2026-02-27

Other Useful Business Software

Go From AI Idea to AI App Fast Icon

Go From AI Idea to AI App Fast

One platform to build, fine-tune, and deploy ML models. No MLOps team required.

Access Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.

Try Free

MongoDB Atlas runs apps anywhere Icon

MongoDB Atlas runs apps anywhere

Deploy in 115+ regions with the modern database for every enterprise.

MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.

Start Free

Go From AI Idea to AI App Fast

One platform to build, fine-tune, and deploy ML models. No MLOps team required.

Access Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.

Try Free

Recommended Projects

Node Director
The Node Director is a tool for managing distributed, hetergeneous UNIX Systems. Its functionality includes System Configuration, Application Distribution, NIS & NIS+ Management, User Creation and Dynamic System Documentation.
Opik
Debug, evaluate, and monitor your LLMapps, RAG systems, and agentic AI
DocsGPT
Private AI platform for agents, enterprise search and RAG pipelines
DeepEval
DeepEval is a simple-to-use, open-source LLM evaluation framework, for evaluating and testing large-language model systems. It is similar to Pytest but specialized for unit testing LLM outputs. DeepEval incorporates the latest research to evaluate LLM outputs based on metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., which uses LLMs and various other NLP models that run locally on your machine for evaluation. Whether your application is implemented via RAG or fine-tuning, LangChain, or LlamaIndex, DeepEval has you covered. With it, you can easily determine the optimal hyperparameters to improve your RAG pipeline, prevent prompt drifting, or even transition from OpenAI to hosting your own Llama2 with confidence.
Vector Admin
The universal tool suite for vector database management