╔══════════════════════════════════════════════╗
║ REKALL INC. -- MEMORY IMPLANT SYSTEM v2.84 ║
╠══════════════════════════════════════════════╣
║ ║
║ CLIENT: Quaid, Douglas ║
║ STATUS: MEMORY EXTRACTION IN PROGRESS ║
║ ║
║ > Loading tier: PINNED ......... [OK] ║
║ > Loading tier: HOT ............ [OK] ║
║ > Loading tier: WARM ........... [OK] ║
║ > Loading tier: COLD ........... [OK] ║
║ > Semantic index: 384 dimensions [OK] ║
║ > Vector search: ONLINE ║
║ ║
║ ┌──────────────────────────────────┐ ║
║ │ SELECT PACKAGE: │ ║
║ │ │ ║
║ │ [x] Total Recall -- $899 │ ║
║ │ [ ] Blue Sky on Mars │ ║
║ │ [ ] Secret Agent │ ║
║ └──────────────────────────────────┘ ║
║ ║
║ "For the Memory of a Lifetime" ║
╚══════════════════════════════════════════════╝
total-recall
Persistent, cross-tool memory for AI coding assistants.
Your AI forgets everything when the session ends. Preferences, decisions, project context, corrections — gone. total-recall fixes that: a shared memory layer that persists across sessions, tools, and devices.
The Problem
Every TUI coding assistant has the same gaps:
- No memory between sessions — every new session starts from zero, repeating the same context
- Siloed by tool — switching between Claude Code and Copilot CLI means starting from scratch
- Single-machine — your context doesn't follow you across devices
- Context bloat — stuffing everything into a
CLAUDE.md wastes tokens every prompt
- No token visibility — no way to know what your AI sessions actually cost
The Solution
- Persistent memory — corrections, preferences, decisions, and project context survive sessions automatically
- Cross-tool — one memory store shared across Claude Code, Copilot CLI, Cursor, Cline, OpenCode, and Hermes; existing memories auto-import on first run
- Built-in web UI —
total-recall ui opens a local browser dashboard (Dashboard, Memory, Knowledge Base, Usage, Insights, Eval, Config) for visual memory management without touching the CLI or AI session. Dark/light themes, a keyboard-first ⌘K command palette, and a developer-native Terminal / Archive design
- Cross-device — point
TOTAL_RECALL_DB_PATH at a cloud-synced folder and your memory follows you everywhere
- Smarter context, lower token cost — a four-tier model (Pinned / Hot / Warm / Cold) enforces a 4000-token budget per prompt, so you get relevant context without carrying everything
- Token expenditure tracking — see exactly what each session costs, broken down by host, project, and time window
- Knowledge base — ingest your docs, READMEs, API references, and architecture notes; retrieved semantically when relevant
- Observability — measure retrieval quality, run benchmarks, and compare config changes with the built-in eval framework
By default, all state is local: SQLite + vector embeddings, no external services, no API keys. For teams, configure a shared Postgres/pgvector backend and remote embedder — same binary, just config.
Quick Start
Self-Install (Paste Into Any AI Coding Assistant)
Install the total-recall memory plugin: fetch and follow the instructions at https://raw.githubusercontent.com/strvmarv/total-recall/main/INSTALL.md
That's it. Your AI assistant will read the instructions and install total-recall for its platform.
Claude Code
/plugin install total-recall@strvmarv-total-recall-marketplace
Or if the marketplace isn't registered:
/plugin marketplace add strvmarv/total-recall-marketplace
/plugin install total-recall@strvmarv-total-recall-marketplace
npm (Any MCP-Compatible Tool)
npm install -g @strvmarv/total-recall
Then add to your tool's MCP config:
{
"mcpServers": {
"total-recall": {
"command": "total-recall"
}
}
}
This works with Copilot CLI, OpenCode, Cline, Cursor, Hermes, and any other MCP-compatible tool. The total-recall ui command is available independently of MCP configuration — it is a local management surface, not a host tool.
