Removed CLAUDE.md from gitignore

Author: marcobambini

.gitignore

@@ -2,5 +2,4 @@
 test/unittest.dSYM/Contents/Info.plist
 test/unittest.dSYM/Contents/Resources/DWARF/unittest
 test/unittest.dSYM/Contents/Resources/Relocations/aarch64/unittest.yml
-CLAUDE.md
 /build

CLAUDE.md

@@ -0,0 +1,65 @@
+# CLAUDE.md
+
+Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
+
+**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+## 1. Think Before Coding
+
+**Don't assume. Don't hide confusion. Surface tradeoffs.**
+
+Before implementing:
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them - don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+## 2. Simplicity First
+
+**Minimum code that solves the problem. Nothing speculative.**
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+## 3. Surgical Changes
+
+**Touch only what you must. Clean up only your own mess.**
+
+When editing existing code:
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it - don't delete it.
+
+When your changes create orphans:
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: Every changed line should trace directly to the user's request.
+
+## 4. Goal-Driven Execution
+
+**Define success criteria. Loop until verified.**
+
+Transform tasks into verifiable goals:
+- "Add validation" → "Write tests for invalid inputs, then make them pass"
+- "Fix the bug" → "Write a test that reproduces it, then make it pass"
+- "Refactor X" → "Ensure tests pass before and after"
+
+For multi-step tasks, state a brief plan:
+```
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+```
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
+
+---
+
+**These guidelines are working if:** fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.

sessions/session-2026-02-10.md

@@ -0,0 +1,70 @@
+# Session Summary - 2026-02-10
+
+## Project: sqlite-memory
+
+SQLite extension for AI agent memory with semantic search, hybrid retrieval, and offline-first sync between agents.
+
+---
+
+## Work Completed
+
+### 1. Documentation Updates
+
+Updated `README.md` and `API.md` to reflect changes to the `memory_search` virtual table:
+
+- **Renamed column**: `score` → `ranking` in all query examples and documentation
+- **Documented columns**: `path`, `snippet`, `ranking` properly described
+- **Preserved settings**: `min_score` setting name unchanged (configuration option, not column)
+
+### 2. GitHub Project Description
+
+Created project descriptions for GitHub:
+
+**Short (About field):**
+> SQLite extension for AI agent memory with semantic search, hybrid retrieval, and offline-first sync between agents
+
+**Full description:**
+> A SQLite extension that gives AI agents persistent, searchable memory. Features hybrid semantic search (vector similarity + FTS5), markdown-aware chunking, and local embedding via llama.cpp. Memory databases can be synced between agents using offline-first technology—each agent works independently and syncs when connected, making it ideal for distributed AI systems, edge deployments, and collaborative agent architectures.
+
+---
+
+## Key Files Modified
+
+| File | Changes |
+|------|---------|
+| `README.md` | Updated `memory_search` examples to use `ranking` column |
+| `API.md` | Updated column documentation and examples for `memory_search` |
+
+---
+
+## memory_search Virtual Table Schema
+
+```sql
+SELECT * FROM memory_search WHERE query = 'search text';
+```
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `query` | TEXT (HIDDEN) | Search query (required in WHERE clause) |
+| `hash` | INTEGER | Content hash identifier |
+| `path` | TEXT | Source file path or generated UUID |
+| `context` | TEXT | Context label (NULL if not set) |
+| `snippet` | TEXT | Text snippet from matching chunk |
+| `ranking` | REAL | Combined similarity score (0.0 - 1.0) |
+
+---
+
+## Previous Session Context
+
+This session continued from earlier work that included:
+- Implementing memory deletion, timestamps, and statistics features
+- Building Makefile with conditional llama.cpp/remote engine support
+- Adding support for both local (llama.cpp) and remote (vector.space) embedding
+- Renaming `max_items` to `max_results` throughout codebase
+- Creating comprehensive README.md and API.md documentation
+
+---
+
+## Version
+
+sqlite-memory v0.5.1