proxy

Was war die Idee?

litellm-proxy A local, fast, and lightweight **OpenAI-compatible server** to call 100+ LLM APIs.

Warum angefangen?

Gestartet, um wiederholte Arbeit zu operationalisieren: Kontext sammeln, Entscheidungen sichtbar machen und Agentenarbeit prüfbar machen.

Warum nicht fertig?

Nicht fertig, weil Abschluss-Signale fehlen: 40 TODO/FIXME-Hinweise

Was ist heute wertvoll?

Heute wertvoll als Agent-Control-System, dokumentierte Absicht

Score-Reasons

• 40 TODO/FIXME/WIP hints
• README present

TODO/FIXME-Auszug

• /home/smlflg/.hermes/.uv-cache/archive-v0/9YH33THSokKdr36ExWiQN/litellm/proxy/proxy_cli.py:306 — with open(os.devnull, "w") as devnull:
• /home/smlflg/.hermes/.uv-cache/archive-v0/9YH33THSokKdr36ExWiQN/litellm/proxy/health_check.py:134 — idx, next_model = next(model_iter)
• /home/smlflg/.hermes/.uv-cache/archive-v0/9YH33THSokKdr36ExWiQN/litellm/proxy/openapi_registry.json:19 — { "name": "create_issue", "description": "Open a new issue in a repository" },
• /home/smlflg/.hermes/.uv-cache/archive-v0/9YH33THSokKdr36ExWiQN/litellm/proxy/openapi_registry.json:20 — { "name": "list_pull_requests", "description": "List open and merged pull requests" },
• /home/smlflg/.hermes/.uv-cache/archive-v0/9YH33THSokKdr36ExWiQN/litellm/proxy/openapi_registry.json:21 — { "name": "create_pull_request", "description": "Open a pull request between branches" },
• /home/smlflg/.hermes/.uv-cache/archive-v0/9YH33THSokKdr36ExWiQN/litellm/proxy/openapi_registry.json:41 — { "name": "create_issue", "description": "Create a new Jira issue or bug report" },