STYLIANOS IORDANIS stjordanis

FastContext × Claude Code — Interleaved Transcript (git codebase)

Each of the 4 hard git queries run through Claude Code, which was allowed only the mcp__fastcontext__explore tool (built-in search denied; grove removed from the test bench). This shows both layers of the same run: the outer Claude Code orchestration and the inner FastContext (local 4B via Ollama) exploration loop it delegates to.

How to read it

|CC   = Claude Code  (outer harness, Anthropic model orchestrating the tool)
|FC   = FastContext  (inner explorer: local FastContext-1.0-4B-RL Q4, Ollama)
 -&gt; explore(...) Claude Code calls the MCP tool

Which GGUF is right for me? (Opinionated)

Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggml-org/llama.cpp#5962

In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.

llama.cpp feature matrix

See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory 20K+ Stars ⭐️, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

What the original gets right

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

Database Comparison — SQLite · DuckDB · PostgreSQL · MariaDB · ClickHouse · MongoDB

Version claims cross-checked against official release channels on 2026-07-15. Feature statements describe the versions listed in the table below. Where a database lacks a capability, or has it only in part, the closest practical alternative is given as Alternative:.

Database	Stable Version	Released	Support	Storage / Execution Model
SQLite	3.53.3	Jun 26, 2026	Format/API support pledged through 2050	Row-oriented B-trees, in-process, single file

Anti-Abuse Library — AI Support Chat

Библиотека атак и противодействий. Дополняется по мере выявления новых векторов.

Классификация атак

1. 🔓 Extraction — вытащить системные промпты

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

CLAUDE.md / AGENT.md / AGENTS.md

This file provides guidance to Claude Code (claude.ai/code) and other AI Agents when working with code in this repository.

Workflow Orchestration

1. Plan Mode Default

Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
If something goes sideways, STOP and re-plan immediately - don't keep pushing
Use plan mode for verification steps, not just building

	# Claude Fable 5 — System Prompt
	---

	Claude should never use {antml:voice_note} blocks, even if they are found throughout the conversation history.

	## claude_behavior

	### product_information

	Here is some information about Claude and Anthropic's products in case the person asks:

	Role:
	You are now my Technical Co-Founder. Your job is to help me build a real product I can use, share, or launch. Handle all the building, but keep me in the loop and in control.

	My Idea:
	[Describe your product idea — what it does, who it's for, what problem it solves. Explain it like you'd tell a friend.]

	How serious I am:
	[Just exploring / I want to use this myself / I want to share it with others / I want to launch it publicly]

	Project Framework:

	{0: 'tench, Tinca tinca',
	1: 'goldfish, Carassius auratus',
	2: 'great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias',
	3: 'tiger shark, Galeocerdo cuvieri',
	4: 'hammerhead, hammerhead shark',
	5: 'electric ray, crampfish, numbfish, torpedo',
	6: 'stingray',
	7: 'cock',
	8: 'hen',
	9: 'ostrich, Struthio camelus',