the purser for your coding agents
One local console for the coding agents you already pay for. Every run metered, every change recorded, every audit provable.
Someone edited a line out of the audit log. This is the CLI catching it, naming the entry and showing the hash that no longer matches.
Nobody can see what their coding agents actually cost. And the published numbers on what that code does once it ships are not flattering either.
the agent loop
The prompt is a rounding error. Spend happens in the loop: file reads, tool results, context resent every turn, retries.
No vendor shows you the total across the agents you actually use.
~5,000
apps found leaking corporate or personal data
source
RedAccess scan of ~380,000 apps, May 2026
21% to 3.8%
collapse in refactored code as AI authorship rose, while duplication climbed 81%
source
GitClear, 623M code changes, 2023 to 2026
run
your agent, your login
meter
real per-model tokenizer
ledger
append-only write
governor
warn, ask or stop
audit
hash-chained entry
Append-only, enforced by a database trigger, not convention.
Real tokenizers per model family. Costs only where they are real: metered API providers show dollars; subscription agents show tokens, because we cannot know your plan. Unpriced models say so instead of showing $0.00.
Budgets per run, per day, per month.
Scoped to a session, a workspace, or everything. Warn, ask, or hard stop.
Hash-chained log, verifiable from the CLI.
Written to ~/.purser/audit.jsonl. Tampering and truncation are detectable. purser audit verify names the first broken line.
placeholder
console screenshot goes here
Spend meter in the top bar, Spend / Files / Setup tabs, a decision card and the diff view. Add the files to /public and set productShot in src/lib/content.ts.
No model vendor will ever show you Claude spend next to Codex spend next to Cursor spend in one ledger. That comparison is against their interest.
purser ledger
append-only, hash-chained
Works with the agents you already have logins for. Purser meters them; it does not resell them.
Claude Code
Codex
Cursor CLI
Gemini CLI
Grok, Perplexity, OpenAI-compatible
Ollama
Echo
| Adapter | Kind | Auth | Metering |
|---|---|---|---|
| Claude Code | SDK / CLI | your login | tokens |
| Codex | CLI | your login | tokens |
| Cursor CLI | CLI | your login | tokens |
| Gemini CLI | CLI | your login | tokens |
| Grok, Perplexity, OpenAI-compatible | HTTP | your API key | metered, real cost |
| Ollama | HTTP, local | none | free |
| Echo | fake, for testing | none | not metered |
Subscription agents report tokens, not dollars. Your plan price is not knowable from the outside.
Only what has shipped is listed as shipped. In a market full of demos that die on the second prompt, this section is the point.
11 shipped·5 in build·16 total