接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y [email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add claude-self-reflect -- npx -y claude-self-reflect@9.5.8在終端機中執行。
{ "mcpServers": { "claude-self-reflect": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
Claude forgets everything. This fixes that.
Single 44MB binary. No databases. No containers. No API keys required.
Install | How It Works | MCP Tools | Paper | FAQ
v9.4 — Multi-Source Memory CSR now remembers more than transcripts: task outcomes, plan documents, and a cross-project session registry — each absorbed at the lifecycle stage it belongs to. Episodes carry real task state again (Claude Code's TodoWrite→TaskCreate rename had silently emptied them — found, fixed, and guarded with schema-miss telemetry). Sub-millisecond search, ~150ms cached startup, 720+ tests, zero external dependencies. Release notes
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.
Everything runs locally in a single process. No Docker, no database server, no API keys required.
6 hooks fire across the session lifecycle. 15 MCP tools for explicit search — including csr_code_graph, linking code symbols to the conversations that shaped them.
Three layers progressively improve search quality from raw chunks to AI-enriched narratives — 9.3x improvement.
Higher quality context. Better decisions. Fewer tokens.
CSR's retrieval design is documented in a research preprint, measured on the system's own development history:
Similarity Drowns Intent: Three-Trace Sagas and Reinstatement Recall for Provenance in Agentic Software Construction 2026 — PDF
Ask a memory system "why did we drop Qdrant?" and cosine similarity returns a recording of you asking that question earlier, at 0.984 similarity. The decision itself scores lower than its own echoes. The paper measures this failure, the multi-hop walk built to counter it (+53% and +47% ground-truth session coverage over one-shot kNN on two corpora, pre-registered gates, blind cross-vendor judging), and a second finding that fell out of evaluation: a self-recording memory system ingests its own eval dialogue and drowns the answers it's being tested on. It also keeps its negative results — a pre-registered ratification-weighting hypothesis died at ρ≈0 and forbade an entire staleness design.
curl -fsSL https://raw.githubusercontent.com/ramakay/claude-self-reflect/main/scripts/install.sh | sh
Downloads the binary (SHA256-verified), then asks before activating. Setup — which registers the MCP server, installs 6 hooks, and imports your conversations — only runs with your consent. Restart Claude Code after.
Non-interactive installs never activate on their own: set CSR_AUTO_SETUP=1 to opt in, or run csr-engine setup yourself.
npm install -g claude-self-reflect
csr-engine setup # activation is a separate, explicit step
By default npm install only downloads the checksummed binary — it does not touch ~/.claude or index conversations. Activation happens when you run csr-engine setup, or set CSR_AUTO_SETUP=1 during install to opt in.
git clone https://github.com/ramakay/claude-self-reflect.git
cd claude-self-reflect/csr-engine
cargo build --release
cp target/release/csr-engine ~/.local/bin/
csr-engine setup
No special syntax. No commands. CSR finds relevant past context and injects it automatically.
All tools include MCP tool annotations so Claude Code understands their safety characteristics.
All hooks use catch-all error handling. They never block Claude Code.
Transform raw conversations into rich, searchable narratives. Requires an Anthropic API key.
csr-engine daemon
Token transparency: Optional AI narratives (session briefings + story extraction) run
claude -pagainst your existing Claude subscription — smallest available model, capped prompts, debounced, and skipped entirely when nothing changed. Every call — including failures and timeouts — is counted:csr-engine statusshows calls and tokens spent today; cache read/creation tokens (often the majority of real usage) are tracked separately in the status JSON (cache_tokens_today/cache_tokens_total). Disable anytime withCSR_NO_AI_NARRATIVES=1; pin a model withCSR_NARRATIVE_MODEL=<model>.
csr-engine Start MCP server (default)
csr-engine setup One-shot setup: import + MCP + hooks
csr-engine status System status (JSON)
csr-engine status --compact One-line statusline output
csr-engine daemon Background enrichment daemon
csr-engine hook install --apply Install Claude Code hooks
csr-engine eval Quick eval (5 tests)
csr-engine eval --full Full eval (20 tests)
csr-engine quality <file> AST-based code quality analysis
v8.0 replaces the Python/Docker stack with a single Rust binary.
docker compose down 2>/dev/null
curl -fsSL https://raw.githubusercontent.com/ramakay/claude-self-reflect/main/scripts/install.sh | sh
Your conversation data (~/.claude/projects/) is untouched. The new engine re-imports from the same JSONL files.
Full guide: Documentation
claude mcp remove claude-self-reflect
rm -rf ~/.claude-self-reflect/
rm ~/.local/bin/csr-engine
npm uninstall -g claude-self-reflect # if installed via npm
Documentation | npm | Issues | MIT License
Give Claude perfect memory of all your conversations. Single binary, zero dependencies.
{ "mcpServers": { "claude-self-reflect": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Claude Self Reflect 透過 stdio 在本機執行。
上次檢查時間:2026-10-28。 Give Claude perfect memory of all your conversations. Single binary, zero dependencies.