What SAI (Sri's Personal AI) is and what it does.
SAI (Sri's Personal AI) is a personal AI assistant that doesn't just respond to requests - it actively learns from AI research and proposes improvements to how it operates.
Every change goes through explicit human approval. It's an experiment in building an AI system that gets better over time without losing human oversight. This is what happens when you take a 10-day AI course and keep building.
Beyond self-improvement - SAI is a working personal assistant used daily.
Self-improvement is the most technically interesting part, but SAI is also a daily-use assistant. Here's what it does on a regular basis:
| Capability | How It Works |
|---|---|
| AI News Digests | Daily Telegram messages summarizing the latest AI developments |
| Research Paper Summaries | Cron job extracts key findings from ingested papers and sends condensed briefings |
| Google Calendar | Reads upcoming events and provides schedule-aware context in conversations |
| Email Awareness | Reads and triages Gmail, sends notifications for important messages |
| Web Research | Searches the web and reads pages on demand via browser automation |
| Self-Improvement | Reads AI research, proposes operating rule changes, waits for human approval |
The self-improvement loop gets its own deep-dive below - but it's one part of a broader system that's useful every day, not just when it's learning.
System architecture diagram and data flow explanation.
Two cron-driven pipelines work together: one ingests research at zero LLM cost, the other reasons over the knowledge base and proposes changes.
arXiv RSS HuggingFace Semantic Scholar
Hybrid search: semantic + keyword (BM25)
Pinned Hot Warm Cold → auto-prune
Each diff shown individually
Backup + security audit after every write
The research-fetcher runs every 6 hours as a native Linux cron job, round-robin across three sources with automatic deduplication. The learning-report runs every 3 days, reads the vector store, reasons over ingested papers, and sends proposed changes to Telegram for per-diff human approval.
SAI reads research, proposes config changes, and waits for human approval on every diff.
SAI reads research papers, extracts techniques, and maps them to concrete changes in its own configuration. Every proposed change requires explicit approval - SAI shows the exact diff, waits for a "yes", and runs a security audit after applying.
Example: Learning from Self-RAG
After ingesting the Self-RAG paper (Asai et al., 2023), SAI proposed adding a retrieval decision gate: "Before any knowledge-base lookup, decide explicitly whether retrieval is actually needed." This was reviewed, approved, and applied as a 4-line change to AGENTS.md.
6 Approved Self-Improvements
| Change | Derived From |
|---|---|
| Selective retrieval gate | Self-RAG |
| Self-critique before sending | Self-RAG + Chain-of-Note |
| Separate evidence from inference | RAG Survey |
| Coverage check on retrieval answers | RAG Survey |
| Templated approval protocol | RAG + Self-RAG |
| Validated-only memory updates | Self-RAG |
5-layer progressive trust model with human approval at every critical step.
The system uses a 5-layer progressive trust model. The first two layers can't change SAI's behavior - they only add data and generate reports. From layer 3 onward, nothing happens without a human in the loop.
| Layer | What It Does | Changes Behavior? | Human Gate |
|---|---|---|---|
| 1. Ingest | Stores papers in vector DB | No | -- |
| 2. Synthesize | Generates a learning report | No | -- |
| 3. Propose | Sends proposed changes via Telegram | No | You read it |
| 4. Apply | Modifies config files | Yes | Per-diff approval |
| 5. Skill Creation | Drafts a new skill | Yes | Manual review + scan |
Multi-source fetcher, smart queries, and knowledge base maintenance tiers.
Multi-Source Research Fetcher
Round-robin across three sources with automatic deduplication. Runs as a native Linux cron job - zero LLM cost.
Smart Query Generation
Instead of generic searches, the fetcher reads SAI's current AGENTS.md and MEMORY.md to derive targeted research queries. If SAI recently added a rule about "self-critique", the fetcher searches for papers on LLM self-critique methods.
Knowledge Base Maintenance
Tier-based lifecycle management keeps the vector database clean as it grows.
Technology stack and hosting setup.
SAI runs on a ChatGPT Plus subscription for the AI engine and a shared Hetzner VPS for hosting. Everything else - vector storage, embeddings, parsing, fetching - is free and self-hosted.
| Component | Technology |
|---|---|
| AI Engine | OpenClaw on Docker (ChatGPT Plus) |
| Hosting | Hetzner VPS (shared with other services) |
| Vector DB | ChromaDB (on-disk) |
| Embeddings | all-MiniLM-L6-v2 (local) |
| PDF Parsing | Docling |
| Paper Fetching | Linux cron + Python |
| Channel | Telegram Bot |
| Search | Brave API (free tier) |
| Monitoring | Uptime Kuma + Glances |
Beyond the Course - everything built after completing the 10-day OpenClaw Mastery course.
This project started as the OpenClaw Mastery For Everyone 10-day course. Everything below was built after completing the course.
Teach It to Learn
RAG pipeline with ChromaDB, Docling PDF parsing, sentence-transformer embeddings, hybrid search skill, and human-gated self-improvement loop.
Multi-Source Research Fetcher
Round-robin fetcher across arXiv RSS, HuggingFace, and Semantic Scholar. Smart query generation from agent config. Zero-cost Linux cron.
Knowledge Base Maintenance
Tier system (pinned/hot/warm/cold), automatic weekly pruning, canonical URL deduplication.
Self-Improvement
SAI reads papers, proposes AGENTS.md changes, human approves each diff. Each approved change is traceable to the paper that inspired it.