Browse / Agent tools
FiredMosquito831/my-claude-code
My Claude Code (MCC) is a local multi-provider LLM proxy, model router and control plane for Claude Code, Codex, OpenCode, Gemini CLI and other AI coding agents — 57 providers, fallback routing, credential health, a native web-search tool proxy, and exhaustive analytics with cost provenance in one local dashboard.
- ai-agents
- ai-gateway
- anthropic
- claude-code
- claude-code-proxy
- codex
- coding-agents
- cost-tracking
- developer-tools
- gemini-cli
- llm-observability
- llm-proxy
- search
- CLI
Didn’t work.Tested on 2026-10-18. The recorded test did not run successfully. The page shows what happened.
If the re-run passes, this repo says Works.
Where the fix is
What we checked
Does it run from the README?Didn’t work.The run
Our test was blocked; no repo verdict.
Tested Oct 18, 2026, rev 9fa8f43.
Does it do what the README says?Not checked yet. It has to run first.Why
We check claims after it’s running.
Which setups did we try?Not yet with Haiku. Unverified with Luna.Setups
Linux / Haiku: not yet, Oct 18, rev 9fa8f43. Linux / Luna: unverified, Oct 26, rev 9fa8f43.
Is it safe to run?Made outbound HTTPS connections: yes (hosts not recorded) by mcc-serverWhat we saw
Review signals across current setups: connection review. 136 listed items (named-host connections, static matches, dependency advisories) are below and do not change this verdict. 25 static matches retained as context.
Repository processes attempted these non-loopback connections; proxies can hide the final hostname. 18 distinct locations. 15 attributed processes.
Source contains download and execute; review its purpose. 2 distinct locations. 3 findings.
OSV reports a known vulnerability in this dependency version. 32 distinct locations. 133 findings.
Full event, path and process lists for each observed setup:
A quiet run is not a safety guarantee.
Independent test, not endorsed by the project.