Instead of just prompting an LLM and hoping for the best, StillMe:

- Runs all answers through a *multi-layer validator chain* (6 core validators + conditional validators, up to 13 total depending on context) - Auto-fixes missing citations and hallucinated "experience" - Logs *system-level steps* (RAG retrieval, validators, timing breakdown) - Treats "I don't know" as a first-class, honest state with explicit epistemic tracking

---

## What StillMe actually does

For each user query, StillMe:

1. Detects intent (philosophical vs. technical vs. factual) 2. Routes and filters RAG context accordingly 3. Builds a safe prompt (token-aware, language-aware) 4. Calls the underlying LLM (local or cloud) 5. Runs a *ValidatorChain*: - `CitationRequired` → adds `[foundational knowledge]` or real web/RAG citations - `EvidenceOverlap` → checks answer vs. retrieved context (only when context available) - `Ego-Neutrality` → removes anthropomorphic language ("I feel", "my experience", etc.) - `SourceConsensus` → detects contradictions between multiple sources (only when 2+ sources available) - `EthicsAdapter` → avoids unsafe suggestions while staying honest 6. Logs structured timing: - RAG retrieval latency - LLM inference latency - Validation & post-processing

---

## A real log excerpt (single philosophical question)

```log StillMe philosophical query trace (real backend log excerpt)

[INFO] Philosophical question detected — filtering out technical RAG docs [INFO] Retrieved 3 foundational knowledge documents (RAG cache HIT) [WARNING] Estimated tokens exceed safe limit — switching to minimal philosophical prompt [WARNING] Missing citation detected — auto-patched with [foundational knowledge] [WARNING] Ego-Neutrality Validator removed anthropomorphic term: ['trải nghiệm'] --- LATENCY --- RAG: 3.30s | LLM: 5.41s | Total: 12.04s ```

---

## Why I'm building this

Most LLM systems today:

- Hide their reasoning - Hand-wave citations - Overstate confidence - Treat "I don't know" as a failure

StillMe goes the other way:

- *Transparency-first*: every major decision is logged - *Epistemic honesty*: it's allowed (and encouraged) to say "I don't know" - *Model-agnostic*: works with local and cloud LLMs (DeepSeek, OpenAI, Ollama) - *No fine-tuning required*: all behavior is enforced at the framework layer

---

## Looking for feedback & contributors

I'm a solo builder from Vietnam. StillMe is already:

- Running as a backend + dashboard - Integrated with a real learning pipeline (RSS, arXiv, Wikipedia - updates every 4 hours) - Using a live RAG system with foundational docs

Repo: https://github.com/anhmtk/StillMe-Learning-AI-System-RAG-Foundation

I would love feedback on:

- The validator architecture - Better ways to structure logs & observability - Making the project more contributor-friendly - Any ideas to stress-test the "honesty / transparency" claims

Thanks for reading — happy to answer questions and share more logs, diagrams, or internals if anyone's curious.