Total recall for your terminal. Shared memory for your AI agents.
概要
Total recall for your terminal. Shared memory for your AI agents.
README
Total recall for your terminal. Shared memory for your AI agents.
Suvadu replaces your shell history with a SQLite-backed store. Every command gets structured context — exit code, duration, directory, executor, session. AI agents can query it via MCP. 100% local.
- <2ms recording overhead, <10ms search across 1M+ entries
- AI agent tracking — auto-detects Claude Code, Cursor, OpenCode, Antigravity, Windsurf, pi.dev, Codex, Aider
- Prompt Explorer — trace every command back to the prompt that triggered it
- MCP Server — 15 tools + 7 resources. Agent session discovery, project context, failure learning, risk assessment. Configurable via
suv settings - 100% local — no cloud, no telemetry, no account. MIT licensed.
Website & Docs: suvadu.sh · CLI Reference: suvadu.sh/cli · Blog: suvadu.sh/blog · What’s new: CHANGELOG
Install
# Homebrew (macOS)
brew tap AppachiTech/suvadu && brew install suvadu
# Install script (macOS & Linux)
curl -fsSL https://downloads.appachi.tech/suvadu/install.sh | bash
# Cargo
cargo install suvadu
Then add shell hooks:
# Zsh
echo 'eval "$(suv init zsh)"' >> ~/.zshrc && source ~/.zshrc
# Bash
echo 'eval "$(suv init bash)"' >> ~/.bashrc && source ~/.bashrc
Verify: suv status
Troubleshooting
no such file or directory pointing at an old path (e.g. suv:8: no such file or directory: /opt/homebrew/bin/suv) — The shell hook records the absolute path of the suv binary when your session starts. If you move the binary — switching package managers (e.g. Homebrew → Cargo), running brew unlink suvadu, or uninstalling and reinstalling elsewhere — already-open shells keep pointing at the old, now-deleted path. Reload the shell to pick up the new location:
exec zsh # or: exec bash
(or just open a new terminal). Also make sure the new location, such as ~/.cargo/bin, is on your PATH.
More at suvadu.sh/cli/shell-integration.
Quick Start
suv search # Interactive search TUI (also Ctrl+R)
suv history # Print last 25 commands (pipeable)
suv history --json -n 100 # Last 100 commands as JSONL
suv stats # Stats dashboard with heatmap
suv replay --after today # Timeline of today's commands
suv doctor # Check installation health
suv agent dashboard # Monitor AI agent activity
suv agent prompts # Browse prompts and their commands
AI Agent Setup
suv init claude-code # Claude Code — hooks + MCP + prompt capture
suv init cursor # Cursor — hooks + MCP + prompt capture
suv init opencode # OpenCode — plugin + prompt capture
suv init pi # pi.dev — extension + prompt capture
suv init antigravity # Antigravity — auto-detect
Then ask your agent: “What commands failed in this project recently?”
See the full integration guide and MCP server docs.
Key Features
| Feature | Details |
|---|---|
| Search | Substring search TUI (your own commands by default; Ctrl+A shows agents, Ctrl+E shows failures only) with filters, Smart mode, detail pane, bookmarks |
| History | Non-interactive suv history with filters, --json, pipeable to other tools |
| Agent Dashboard | Timeline, risk assessment, per-agent analytics, exportable reports; suv agent report --fail-on for local CI / git-hook gating |
| MCP Server | 15 tools + 7 resources — agent session replay, project context, failure learning, configurable |
| Prompt Explorer | Trace commands back to the prompt that triggered them |
| Stats | Heatmap, hourly distribution, top commands, executor breakdown; --human (or h in the TUI) excludes AI-agent activity |
| Doctor | suv doctor checks shell, hooks, config, database, MCP, and agent hooks health |
| Organization | Tags, bookmarks (suv bookmark pick recalls one into your prompt), notes, alias suggestions |
| Privacy & Safety | Space-prefix exclusion, regex patterns, secret redaction (extend via redaction.extra_patterns), local-only. suv backup + an automatic snapshot before any suv delete. |
| Arrow Keys | Recency-first Up/Down recall — your most recent commands surface first, with the current directory as a tiebreaker. Agent commands are hidden by default; reveal them with Alt+A (per shell) or --include-agents. |
| Vim Bindings | Optional vim-style j/k/Ctrl+U/Ctrl+D navigation in search TUI |
Full feature documentation at suvadu.sh/cli.
Development
git clone https://github.com/AppachiTech/suvadu.git
cd suvadu
make dev # Run the app
make test # Run tests
make lint # Run clippy + format check
See CONTRIBUTING.md for guidelines.
Security
See SECURITY.md for vulnerability reporting, data storage design, and privacy details.
License
インストール
This server does not publish a one-line install command.
Open the repository installation guide