Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily.
Repository Index
132,241 visible repositories in the index
1–24 of 46 · Most stars
Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.
- ai
- diagnostic-tool
- agent-evaluation
- ai-alignment
The LLM Evaluation Framework
- evaluation-metrics
- evaluation-framework
- llm-evaluation
- llm-evaluation-framework
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
- agent-orchestration
- ai-agents
- harness
- agentic-ai
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
可溯源、带时效判断的企业知识库问答:每条结论标明出自哪份文档的哪个版本、哪一处,以及在目标时间是否有效(Traceable, version- and time-aware enterprise RAG)
DeepTeam is a framework to red team LLMs and AI agents.
- llm-guardrails
- llm-red-teaming
- llm-safety
- python
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.
BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
FireRed-Image-Edit is a powerful image editing foundation model achieving open-source state-of-the-art performance with precise instruction following, high-fidelity generation, superior identity consistency, and seamless multi-element fusion.
A Docker-powered service for PDF document layout analysis. This service provides a powerful and flexible PDF analysis service. The service allows for the segmentation and classification of different parts of PDF pages, identifying the elements such as texts, titles, pictures, tables and so on.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
- ai-agents
- developer-tools
- binary-analysis
- ctf
Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform
[JMLR 2026] UQLM: A Python package for LLM hallucination detection using uncertainty quantification
- ai-evaluation
- ai-safety
- hallucination
- hallucination-detection
AuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery.
- agent-runtime
- agentic-rag
- ai-agent
- audit
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
- accuracy-decline
- ai-safety
- audit-trail
- fact-checking
A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baseline-tested generation, per-skill regression evals, ecosystem doctor, cross-runtime compile, and an opt-in proactive advisor.
AI molecular design tool for de novo design, scaffold hopping, R-group replacement, linker design and molecule optimization.
A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.
AI-powered data analysis workbench built for transparency, reproducibility and user control. Inspect the code and evidence behind results, verify calculations through replay, and choose from a wide range of models, including local open-weight models.
A Graph RAG System for Evidenced-based Medical Information Retrieval [ACL 2025]