claude-self-reflect

Claude Self-Reflect

Table of Contents

• The Problem — Why Claude needs memory
• The Architecture — How CSR solves it
• The Pipeline — Progressive enrichment (9.3x improvement)
• Install — One command setup
• What You'll Ask — Natural language, no syntax
• Performance | MCP Tools | Hooks | CLI
• AI Narratives | Upgrading | Troubleshooting

---

The Forgetting Problem

Claude starts fresh every session. Solutions you found, architectures you designed, bugs you debugged — all gone.

Context retention drops below 20% after 10 sessions. CSR fixes this with a single binary that gives Claude perfect memory.

No special syntax. No commands. Install once, and past context appears automatically when you need it.

Explore the full documentation →

---

One Binary. 44MB.

Everything runs locally in a single process. No Docker, no database server, no API keys required.

• SQLite — storage for chunks, embeddings, enrichment state
• HNSW — sub-millisecond vector search (<1ms p95)
• FastEmbed — 384-dim local embeddings
• AST — code-aware search across 6 languages

6 hooks fire across the session lifecycle. 12 MCP tools for explicit search.

Explore the full documentation →

---

The Pipeline

Three layers progressively improve search quality from raw chunks to AI-enriched narratives — 9.3x improvement.

Higher quality context. Better decisions. Fewer tokens.

Explore the full documentation →

---

Install