Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.
-
Updated
Apr 16, 2026
#
anti-hallucination
Here are 85 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
Score any document. Prove every claim.
rust ai sparql rdf owl ontology multi-agent knowledge-graph fact-checking owl-ontology audit-trail document-evaluation llm-evaluation hallucination-detection mcp-server evidence-verification anti-hallucination tender-evaluation
-
Updated
Apr 5, 2026 - Rust
Hierarchical RAG architecture scaling to 693K chunks on consumer hardware (4GB VRAM). Features 3-address routing, hybrid vector+graph fusion, and SetFit classification.
python knowledge-graph semantic-search postgress rag vector-search edge-ai network-routing setfit pgvector advanced-rag graphrag rust-optimization agentic-rag grounded-reasoning low-vram hierarchical-rag anti-hallucination vector-databse
-
Updated
Feb 11, 2026 - Python
Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.
rust mcp postgresql npm-package pagerank knowledge-graph graph-database semantic-search hebbian-learning rag episodic-memory pypi-package exponential-decay vector-search ai-tools ai-memory graphrag model-context-protocol mcp-server anti-hallucination
-
Updated
Jun 4, 2026 - Rust
Native rules, hooks, and guards that prevent Claude Code and Codex from hallucinating code, duplicating files, or shipping unverified changes.
hooks linter static-analysis developer-tools code-quality codex ai-safety ai-agents claude guardrails llm claude-code codex-cli agentic-engineering anti-hallucination agent-harness
-
Updated
Jun 13, 2026 - Shell
Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.
mcp citations python-sdk fact-checking clarity web-search ai-agent prompt-engineering langchain llamaindex llm-tools research-agent crewai agent-tools model-context-protocol mcp-server hallucination-prevention anti-hallucination browseaidev browseai-dev
-
Updated
Jun 7, 2026 - TypeScript
Verifies citations, flags retractions, audits bibliographies — and searches the web. Your AI research assistant that cites real sources and stays honest. Works with Claude, Cursor, any MCP client.
go golang research ai bibliography mcp web-scraping cursor fact-checking content-extraction claude web-search ai-agent llm claude-desktop citation-verification model-context-protocol mcp-server claude-code anti-hallucination
-
Updated
Jun 13, 2026 - Go
Reduce hallucinations through first-principles reasoning, verification, self-critique, and explicit uncertainty for AI agents.
security knowledge verification fact-checking reasoning cognitive-architecture knowledge-engineering system-thinking agent-ops philosophy-of-ai anti-hallucination hallucination-reduction first-principle-framework
-
Updated
Mar 28, 2026
Archive snapshot repo of the original concept and 0-1 invention features, please utilize the constantly updated cypher-tempre-genesis repo for running the skill.
bitcoin persistent-memory ai-agents timechain self-evolving agent-memory claude-code anti-hallucination claude-plugin self-model proof-of-qualia cypher-tempre
-
Updated
Jun 12, 2026 - Python
A minimal graph engine for grounded AI — records, associates, and retrieves, but never invents. Written in Rust.
rust cli ai mcp knowledge-graph graph-database embedded-database deterministic graph-engine ai-agents explainable-ai llm model-context-protocol grounded-ai anti-hallucination
-
Updated
Jun 13, 2026 - Rust
65 plugins that turn Claude Code into an autonomous development team. 24 agents, 34 skills, 5 hooks. Includes 12-plugin anti-hallucination suite. One-line install.
opensource ai developer-tools autonomous-agents ai-agents ai-tools ai-automation code-assistant anthropic claude-ai ai-coding mcp-tools claude-code ai-coding-assistant ai-plugins claude-code-hooks anti-hallucination claude-code-plugins claude-code-agents claude-code-skills
-
Updated
Mar 28, 2026 - Shell
A completion-claim gate for Claude Code. Refuses to let the agent say done without evidence.
-
Updated
Jun 3, 2026 - JavaScript
Claude Code plugin: catches LLM-fabricated names before they hit disk + restores deleted sessions. 89.3% measured hallucination reduction (n=400, p<1e-26)
mcp ai-tools llm hallucination-detection ai-memory fair-source ai-coding claude-code anti-hallucination fsl-license code-grounding
-
Updated
May 22, 2026 - Python
A high-performance C# SQL Agent MCP that eliminates LLM hallucinations and security risks. Instead of letting the AI write raw SQL, it extracts parameters to generate deterministic, injection-free queries across 6 major databases—complete with a visual Admin UI and enterprise guardrails.
mysql security postgres sql-server sqlite mcp postgresql oracle firebird accuracy admin-panel ai-safety sql-agent nl2sql mcp-servers mcp-server anti-hallucination ai-safety-design
-
Updated
Jun 2, 2026 - C#
Context governance kernel for LLM agents. Predicts entropy, blocks hallucinations. Pairs with opencode-dcp. llm, llm-agents, opencode, opencode-plugin, context-governance, anti-hallucination, claude-code, cursor, typescript.
opencode security-tools llm llm-agents claude-code llm-agent-framework anti-hallucination opencode-plugin
-
Updated
Jun 9, 2026 - TypeScript
EN: An overfitted SD prompt engine with severe "aesthetic snobbery," forcibly transforming mundane ideas into professional-grade physical rendering instructions. CN: 一个具备"审美洁癖"的过拟合提示词引擎,强行将平庸构思纠偏为具备极致物理质感的工业级渲染指令。
native cuda self-hosted python3 micro aesthetic industrial-automation echo-server lora gradio fine-tuning ai-art stable-diffusion local-inference prompt-generation qwen local-ai-agents blackwell-gpu anti-hallucination deterministic-ai
-
Updated
Jan 19, 2026 - Python
A strict, deterministic LLM protocol for loading, reading and activating the DCQN.MATRIX Axiomatics from the OSF DOI (10.17605/OSF.IO/QWA6S), including anti-simulation safeguards and full formal reconstruction into DCQN_LOGIK_SESSION_V1.
axiomatic-semantics neutrality axiomatic-thinking llm prompt-engineering llm-agent llm-evaluation anti-hallucination
-
Updated
Dec 15, 2025
A lightweight anti-hallucination wrapper for LLMs using Chain-of-Verification.
-
Updated
Jun 13, 2026 - Python
From one prompt to a finished product — fully autonomous. Auto-plans, remembers across sessions (persistent context), builds end-to-end, audits security & performance, deploys. 18 agents + 39 workflows for ChatGPT, Copilot, Codex, Cursor, and other AI coding tools. Built by NexVar.
ai context multi-agent project-management cursor copilot codex ai-agents agent-framework llm generative-ai chatgpt llm-agents context-memory autonomous-coding anti-hallucination nexvar nexgsd
-
Updated
Apr 25, 2026 - JavaScript
Claude Code plugin: runtime invariants + hooks (cycle-detector, approval gate, verification gate), four co-system agents (developer · analyzer · critic · epistemic-auditor), and a held-out evaluation harness. Anti-hallucination protocol grounded in game theory and the scientific method.
hooks developer-tools harness ai-agents claude llm prompt-engineering anthropic ai-code-review llm-evaluation claude-code subagents anti-hallucination claude-code-plugin claude-skills harness-engineering
-
Updated
Jun 13, 2026 - Python
Improve this page
Add a description, image, and links to the anti-hallucination topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the anti-hallucination topic, visit your repo's landing page and select "manage topics."