Does Tare send my logs anywhere?
No. Tare reads files on your machine and writes results to ~/.tare. It makes no network requests and never calls a model, so it costs no tokens.
AI DevOps
Tare
See where your AI coding agent's tokens go, cut the waste without breaking the prompt cache, and get a receipt for every saving
- Community votes0
- DR by Ahrefs0 no change since last check
Ahrefs Domain Rating set in type 8 Nov 2026, reset 7 Nov 2026.
Local tool that reads AI coding agent logs, shows token spending by category, installs safe fixes to reduce waste, and verifies savings on your own machine
The story so far
Tare analyzes the session logs that AI coding assistants like Claude Code already keep on your computer. It prices every token call, breaking down spending by startup context, tool output, cache operations, and other factors. The tool then installs safe fixes that reduce waste without rewriting cached content, and later compares cost-per-commit before and after to verify real savings.
All analysis happens locally on your machine with no network requests or model calls. Tare provides a detailed receipt showing the percentage reduction in cost per finished task, with a 90% confidence range, and confirms that work quality hasn't suffered. The tool supports Claude Code today with plans for other agents.
Typeset features
- Session log analysis with token pricing breakdown
- Categorized spending attribution by startup context, tool output, sub-agents, and cache rebuilds
- Safe automatic fixes for output trimming and cache countdown
- Undo capability for all changes
- Receipt comparing cost-per-commit before and after with 90% confidence range
- Shareable card with visualization of token usage
- Command output trimming to reduce context bloat
- Cache expiration countdown in status line
- MCP server integration for any agent
- Claude Code plugin with skill and MCP server
Pricing
Pricing model: Freemium
Free for open source (Wrapped, all fixes with undo, receipt, skill, plugin, MCP server). Team: $30 per developer, or 10% of verified savings, whichever is lower (spend by engineer, cost per merged PR, CI gate). Enterprise: contact for self-hosted, SSO, finance exports, procurement-grade reports.
Follow in print. Log in to follow Tare in print
Want to see what Tare does next? Follow them for milestones, new products and stories by email.
Tare metrics
| Metric | Value |
|---|---|
| Domain Rating | 0 no change since last check |
| Trust Flow | 0 no change since last check |
| Citation Flow | 0 no change since last check |
| Referring domains | 0 no change since last check |
| External backlinks | 0 no change since last check |
Ahrefs Domain Rating set in type 8 Nov 2026, reset 7 Nov 2026. Majestic set 7 Nov 2026, reset 7 Nov 2026. Link data typeset by Majestic. Trust Flow, Citation Flow and Topical Trust Flow are trademarks of Majestic-12 Ltd.
Tare domain colophon
Read the colophon
| Domain age | 7 months |
|---|---|
| Registered | |
| Expires | |
| Registrar | HOSTINGER operations, UAB |
| DNSSEC | Not signed |
Tare launch colophon
Measured after Tare went live on Zivaro Launch on 7 November 2026.
- Domain Rating (Ahrefs)
- 0
- First measured 7 Nov 2026
- Trust Flow (Majestic)
- 0
- First measured 7 Nov 2026
- Referring domains (Majestic)
- 0
- First measured 7 Nov 2026
Day 0 since launch. Next receipt: day 30, 7 Dec 2026. These are measurements, not proof of cause: many things move these numbers. Figures we have not measured are left out.
Your launch, step by step
Free tips from Zivaro Launch for getting ready, launch day, the week after and what to do next.
Compare and explore
Questions and answers
I'm on a subscription. Does this matter to me?
The dollar figures show what the same work would cost at API prices for comparison. On a subscription, waste shows up as hitting usage limits sooner, and the fixes help with that too.
Will the fixes make my agent worse?
The output trim keeps every line that looks like a failure plus the start and end, saves the full output for the agent to access, and the receipt checks that sessions still finish. You can undo everything with tare fix --undo.
Why not just compress the context?
Rewriting what's already in context breaks the prompt cache. A cache miss costs 12.5 to 25 times a hit, so a tool can cut tokens and still raise the bill. Tare only trims new content as it enters.
Which agents does it support?
Claude Code today. Codex CLI and Gemini CLI logs are next. The skill works in Claude Code and Codex now, and the MCP server works with any agent that speaks MCP.
Leave a review for Tare
No review of Tare set in type yet. Set the first.
Reviews are free to set. None are paid for. Read the proofs
Readers' notes · Reprints · Share the page · Your company in print? Claim it · Report a misprint
Tare has a free listing. The owner can unlock the full profile with a paid launch for $5:
- Founder story (locked)
- Milestones (locked)
- Demo video (locked)
- Dofollow website link (locked)
More pages like this
-
Number 1:
Kimchi CodingThe governed AI coding platform
DR 41 +1 (up) since last check 1 votes. Log in to vote for Kimchi Coding in print -
Number 2:
DocuSORContext gateway that gives coding agents verified codebase knowledge to skip rediscovery and work faster
DR 5 no change since last check 0 votes. Log in to vote for DocuSOR in print -
Number 3:
InterlokLockout/tagout for AI agents: risky actions stop, a person decides, and a signed record proves it
DR 0 no change since last check 0 votes. Log in to vote for Interlok in print -
Number 4:
Metrum AIAI infrastructure performance testing and autonomous operations platform
DR 19 no change since last check 0 votes. Log in to vote for Metrum AI in print