tokdash 0.0.5

Local token & cost dashboard for AI coding tools

Tokdash

Local token & cost dashboard for AI coding tools (Codex, OpenCode, Claude Code, Gemini CLI, OpenClaw, etc.).

Features

• Hierarchical breakdown: app → model with full token precision
• Multiple data sources: local session files + optional tokscale fallback
• Exact token counts: Input/Output/Cache token breakdowns
• Flexible ranges: today / week / month / N days
• Contribution calendar: 2D heatmap + 3D isometric view

Supported clients (explicit token fields)

✅ Supported:

• OpenCode: ~/.local/share/opencode/
• Codex: ~/.codex/sessions/
• Claude Code: ~/.claude/projects/
• Gemini CLI: ~/.gemini/tmp/*/chats/session-*.json
• OpenClaw: ~/.openclaw/agents/*/sessions/

Platform support

• Linux (including WSL2): supported
• macOS: experimental

Quick start

Prerequisites

• Python 3.10+
• One or more supported clients installed (above)

Install (pip)

From PyPI (after the first public release):

pip install tokdash
tokdash serve

Open: http://localhost:55423

Run (from source)

pip install -e .

# Option A: run directly
python3 main.py

# Option B: CLI wrapper (same server)
./tokdash serve

Open: http://localhost:55423

If port conflicts:

• python3 main.py --port <port>
• ./tokdash serve --port <port>

If you want to access Tokdash from another device (recommended):

• Tailscale Serve (private to your tailnet): tailscale serve 55423
• SSH port-forward: ssh -L 55423:127.0.0.1:55423 <user>@<host>

Binding to 0.0.0.0 is possible, but not recommended: it listens on all interfaces and can expose the dashboard beyond your LAN (VPN/Wi‑Fi/etc.). Only do this if you understand the risk and have firewall/auth in place.

Run in background

See docs/agents/systemd/BACKGROUND_RUN.md for:

• Linux systemd (user service) template
• macOS launchd (LaunchAgent) template

For Humans

Copy and paste this prompt to your LLM agent (Claude Code, AmpCode, Cursor, etc.):

Install and configure Tokdash to run in the background by following the instructions here:
https://raw.githubusercontent.com/JingbiaoMei/Tokdash/main/docs/agents/systemd/AGENTS.md

Or read the Background Run guide, but seriously, let an agent do it.

For LLM Agents

Fetch the installation guide and follow it:

curl -s https://raw.githubusercontent.com/JingbiaoMei/Tokdash/main/docs/agents/systemd/AGENTS.md

OpenClaw digest (scheduled reports)

Tokdash can power daily/weekly/monthly OpenClaw usage reports by querying the local API on a schedule.

For Humans

Copy and paste this prompt to your LLM agent (Claude Code, AmpCode, Cursor, etc.):

Install and configure scheduled Tokdash usage reports for OpenClaw by following the instructions here:
https://raw.githubusercontent.com/JingbiaoMei/Tokdash/main/docs/agents/openclaw_reporting/AGENTS.md

Or read the guide yourself, but seriously, let an agent do it.

For LLM Agents

Fetch the installation guide and follow it:

curl -s https://raw.githubusercontent.com/JingbiaoMei/Tokdash/main/docs/agents/openclaw_reporting/AGENTS.md

Configuration

Tokdash is localhost-only by default.

• TOKDASH_HOST (default: 127.0.0.1)
• TOKDASH_PORT (default: 55423)
• TOKDASH_CACHE_TTL (default: 120 seconds)
• TOKDASH_ALLOW_ORIGINS (comma-separated, default: empty)
• TOKDASH_ALLOW_ORIGIN_REGEX (default allows only localhost/127.0.0.1)

Example (remote access via Tailscale Serve; recommended):

tokdash serve --bind 127.0.0.1 --port 55423
tailscale serve --bg 55423

Privacy & security

• No telemetry: Tokdash does not intentionally send your data anywhere.
• Local parsing: usage is computed from local session files (see “Supported clients” paths above).
• Server exposure: Tokdash binds to 127.0.0.1 by default. Prefer Tailscale Serve or SSH tunneling for remote access; avoid --bind 0.0.0.0 unless you understand it listens on all interfaces and have firewall/auth in place.

API (local)

Tokdash is a local HTTP server. Common endpoints:

• GET /api/usage?period=today|week|month|N
• GET /api/tools?period=... (coding tools only)
• GET /api/openclaw?period=... (OpenClaw only)

Example:

curl 'http://127.0.0.1:55423/api/usage?period=today'

Cost Accuracy Note

Token counts depend on what each client logs locally. Costs are computed from src/tokdash/pricing_db.json and may lag real provider pricing — use as an estimate and verify against your billing source if it matters.

Roadmap

See docs/ROADMAP.md.

Contributing / security

• Contributing guide: docs/CONTRIBUTING.md
• Security policy: docs/SECURITY.md

Project structure

tokdash/
├── main.py                 # Source entrypoint (python3 main.py)
├── tokdash                 # Source CLI wrapper (./tokdash serve)
├── src/
│   └── tokdash/
│       ├── cli.py
│       ├── api.py                # FastAPI routes/app
│       ├── compute.py            # Aggregation/merging logic
│       ├── pricing.py            # PricingDatabase wrapper
│       ├── model_normalization.py
│       ├── pricing_db.json
│       ├── sources/
│       │   ├── openclaw.py       # OpenClaw session log parser
│       │   └── coding_tools.py   # Local coding tools parsers
│       └── static/
│           └── index.html
└── docs/                   # Roadmap + background-run docs + agent prompts

License

MIT License - see LICENSE.