⚡ Token Savior Recall

What it does

Claude Code reads whole files to answer questions about three lines, and forgets everything the moment a session ends. Token Savior Recall fixes both. It indexes your codebase by symbol — functions, classes, imports, call graph — so the model navigates by pointer instead of by cat. Measured reduction: 97% fewer chars injected across 170+ real sessions.

On top of that sits a persistent memory engine. Every decision, bugfix, convention, guardrail and session rollup is stored in SQLite WAL + FTS5 + vector embeddings, ranked by Bayesian validity and ROI, and re-injected as a compact delta at the start of the next session. Contradictions are detected at save time; observations decay with explicit TTLs; a 3-layer progressive-disclosure contract keeps lookup cost bounded.

Token savings

Full methodology and per-task results at github.com/Mibayy/tsbench.

Memory engine

vs claude-mem

Two projects share the goal — persistent memory for Claude Code. The axes below are measured, not marketing.

Token Savior Recall is a superset: it ships the memory engine plus the structural codebase server that gave the project its name.

Install

uvx (no venv, no clone)

uvx token-savior-recall

pip

pip install "token-savior-recall[mcp]"
# Optional hybrid vector search:
pip install "token-savior-recall[mcp,memory-vector]"

Claude Code one-liner

claude mcp add token-savior -- /path/to/venv/bin/token-savior

Configure

{
  "mcpServers": {
    "token-savior-recall": {
      "command": "/path/to/venv/bin/token-savior",
      "env": {
        "WORKSPACE_ROOTS": "/path/to/project1,/path/to/project2",
        "TOKEN_SAVIOR_CLIENT": "claude-code"
      }
    }
  }
}

Tools (105)

Progressive disclosure — memory search

Three layers, increasing cost. Always start at Layer 1. Escalate only if the previous layer paid off. Full contract: progressive-disclosure.md.

Each Layer 1 row ends with [ts://obs/{id}] — pass it straight to Layer 3.

Links