Developer Tools
Blume
Last updated 2026-08-31 · benchmark measured 2026-10-23 — deterministic & reproducible
Blume is a desktop sidecar app for monitoring and maintaining coding agents.
Blume at a glance
Blume is a desktop sidecar app that runs alongside coding agents like Cursor, Claude Code, and Codex to help developers see what each agent is doing, review its rules, and track provider quota.
Good for
- Developers who want visibility into what their coding agents are doing and why
- Teams managing multiple AI coding tools who need to keep rules, skills, and hooks organized
- Engineers who want to track token usage and quota across coding agent providers
Questions people ask
What does Blume actually do?
It runs alongside coding agents such as Cursor, Claude Code, and Codex, showing you what each agent is doing, the rules and skills guiding it, and how much provider quota remains.
Which coding agents does Blume work with?
It works with Cursor, Claude Code, and Codex.
Is my conversation data private?
Yes, conversation history and analysis are stored locally on your device rather than sent elsewhere.
Can I review changes before Blume applies them?
Yes, Blume shows you the evidence and exact diff for a suggestion, and you can apply, dismiss, or save it for later.
Does Blume help me avoid running out of usage limits?
Yes, it tracks your Claude Code and Codex plan limits and token usage so you can see your burn rate before hitting a wall.
Written by Legit.Show from blume.codes on 2026-09-30. It does not change the score.
Are you the maker of Blume? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/blume-codes/2026-10-23. That address never changes; this page moves with every re-measure.
Legit.Show scored Blume 80/100 on 2026-10-23, measured across all 7 frames from its public surface. legit.show/s/blume-codes/2026-10-23
Is Blume production-ready?
Legit.Show scores Blume 80 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Blume (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Accessibility; its weakest is Performance. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 19/100
- Accessibility — 100/100
- Security — 80/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 75/100How this compares across the catalogue: The Privacy Gap
- Reliability — 92/100
- Standards — 92/100
- Discoverability — 100/100
What we measured
- Security headers present: HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 589 ms to first byte.
- Returns a proper 404 for unknown routes.
- 0 of 0 sampled routes reachable.
- Has a reachable privacy policy.
- Sets cookies / loads scripts with no consent prompt.
Who built it
Peder Aaby · product account @BlumeDotCodes
Who it's for
Developers using coding agents · Teams managing multiple AI coding tools · Engineers optimizing agent performance
Sources and updates
- Description
- Taken from blume.codes's own website on 2026-08-31.
- Operator
- Blume Corporation, as named in blume.codes's terms, privacy page or footer.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-10-23.
Put together from public information, without Blume's involvement. If anything here is wrong, tell us and a person will check it.
Visit Blume → · Alternatives to Blume → · How this was measured →